Smart Cities Latest open access articles published in Smart Cities at https://www.mdpi.com/journal/smartcities https://www.mdpi.com/journal/smartcities MDPI en Creative Commons Attribution (CC-BY) MDPI support@mdpi.com Smart Cities, Vol. 9, Pages 134: MemGeoSeg: Location-Aware Semantic Segmentation with Spatially Indexed Memory for Repetitive Driving Scenarios https://www.mdpi.com/2624-6511/9/8/134 Current visual perception techniques for self-driving vehicles mainly focus on the generalization across diverse scenes, and they often overlook the valuable spatial consistency present in the repetitive driving routes such as public transit lines, delivery and shuttle services. In this paper, we introduce MemGeoSeg, which is a novel multi-modal framework that enhances semantic segmentation by exploiting scene repetitions through GPS-guided spatial priors and historical memory. Our approach introduces a hierarchical GPS embedding module, which is a spatially indexed memory bank that accumulates location-specific visual knowledge and a cross-modal fusion mechanism with contrastive learning. To validate the idea of improving visual perception with repetitive driving scenarios, a new dataset, RMTD-AD, is constructed for evaluation. It contains over 13,000 annotated images across various weather and lighting conditions on repeated routes. Extensive experiments conducted on the dataset have demonstrated that MemGeoSeg significantly outperforms the state-of-the-art baseline, achieving an mIoU of 76.5% compared to SegFormer’s 71.8% (a 4.7 percentage-point improvement), with particularly strong gains in challenging scenarios like low-light and adverse weather conditions. The result shows that there are substantial benefits to incorporating geographical contexts and historical memory for location-aware perception in intelligent vehicles. 2026-08-19 Smart Cities, Vol. 9, Pages 134: MemGeoSeg: Location-Aware Semantic Segmentation with Spatially Indexed Memory for Repetitive Driving Scenarios

Smart Cities doi: 10.3390/smartcities9080134

Authors: Huei-Yung Lin Jou-An Tsai

Current visual perception techniques for self-driving vehicles mainly focus on the generalization across diverse scenes, and they often overlook the valuable spatial consistency present in the repetitive driving routes such as public transit lines, delivery and shuttle services. In this paper, we introduce MemGeoSeg, which is a novel multi-modal framework that enhances semantic segmentation by exploiting scene repetitions through GPS-guided spatial priors and historical memory. Our approach introduces a hierarchical GPS embedding module, which is a spatially indexed memory bank that accumulates location-specific visual knowledge and a cross-modal fusion mechanism with contrastive learning. To validate the idea of improving visual perception with repetitive driving scenarios, a new dataset, RMTD-AD, is constructed for evaluation. It contains over 13,000 annotated images across various weather and lighting conditions on repeated routes. Extensive experiments conducted on the dataset have demonstrated that MemGeoSeg significantly outperforms the state-of-the-art baseline, achieving an mIoU of 76.5% compared to SegFormer’s 71.8% (a 4.7 percentage-point improvement), with particularly strong gains in challenging scenarios like low-light and adverse weather conditions. The result shows that there are substantial benefits to incorporating geographical contexts and historical memory for location-aware perception in intelligent vehicles.

]]> MemGeoSeg: Location-Aware Semantic Segmentation with Spatially Indexed Memory for Repetitive Driving Scenarios Huei-Yung Lin Jou-An Tsai doi: 10.3390/smartcities9080134 Smart Cities 2026-08-19 Smart Cities 2026-08-19 9 8 Article 134 10.3390/smartcities9080134 https://www.mdpi.com/2624-6511/9/8/134 Smart Cities, Vol. 9, Pages 133: Data-Driven Child-Friendly Street Renewal for Health Equity in Older Urban Districts: Latent Activity–Health Profiles in Xi’an, China https://www.mdpi.com/2624-6511/9/8/133 Data-driven urban governance increasingly seeks to incorporate the needs of different population groups, yet child-sensitive evidence for public street-space renewal remains limited in older urban districts. Most studies still evaluate environmental conditions through population averages, with insufficient attention to heterogeneous child groups that may require differentiated planning responses. Based on an analytic sample of 314 children retained from 343 usable questionnaire responses collected from children aged 6–12 in the older urban districts of Xi’an, China, this study integrates street-activity characteristics and age- and sex-standardized body mass index (zBMI) using an established person-centered analytical approach. Latent Class Analysis (LCA) was used to identify children’s activity–health profiles, and multinomial logistic regression was used to examine associations between individual, family, and perceived street-environment factors and profile membership. Three profiles were identified: high-activity–healthy, high-intensity active, and low-activity–high-risk. The model-estimated low-activity–high-risk profile represented 35.7% of the analytic sample, and children assigned to this profile reported the lowest perceived safety and convenience. The findings suggest that profile-based analysis may inform child-sensitive street-renewal prioritization. Perceived safety and convenience showed the strongest and most consistent associations with membership in either the high-activity–healthy or high-intensity active profile relative to the low-activity–high-risk profile. These findings are associative and do not establish the effects of street interventions. The study therefore represents a context-specific extension and planning application of established analytical methods. 2026-08-18 Smart Cities, Vol. 9, Pages 133: Data-Driven Child-Friendly Street Renewal for Health Equity in Older Urban Districts: Latent Activity–Health Profiles in Xi’an, China

Smart Cities doi: 10.3390/smartcities9080133

Authors: Zhanhao Zhang Xin Dong Weijie Hou Sitong Liu

Data-driven urban governance increasingly seeks to incorporate the needs of different population groups, yet child-sensitive evidence for public street-space renewal remains limited in older urban districts. Most studies still evaluate environmental conditions through population averages, with insufficient attention to heterogeneous child groups that may require differentiated planning responses. Based on an analytic sample of 314 children retained from 343 usable questionnaire responses collected from children aged 6–12 in the older urban districts of Xi’an, China, this study integrates street-activity characteristics and age- and sex-standardized body mass index (zBMI) using an established person-centered analytical approach. Latent Class Analysis (LCA) was used to identify children’s activity–health profiles, and multinomial logistic regression was used to examine associations between individual, family, and perceived street-environment factors and profile membership. Three profiles were identified: high-activity–healthy, high-intensity active, and low-activity–high-risk. The model-estimated low-activity–high-risk profile represented 35.7% of the analytic sample, and children assigned to this profile reported the lowest perceived safety and convenience. The findings suggest that profile-based analysis may inform child-sensitive street-renewal prioritization. Perceived safety and convenience showed the strongest and most consistent associations with membership in either the high-activity–healthy or high-intensity active profile relative to the low-activity–high-risk profile. These findings are associative and do not establish the effects of street interventions. The study therefore represents a context-specific extension and planning application of established analytical methods.

]]> Data-Driven Child-Friendly Street Renewal for Health Equity in Older Urban Districts: Latent Activity–Health Profiles in Xi’an, China Zhanhao Zhang Xin Dong Weijie Hou Sitong Liu doi: 10.3390/smartcities9080133 Smart Cities 2026-08-18 Smart Cities 2026-08-18 9 8 Article 133 10.3390/smartcities9080133 https://www.mdpi.com/2624-6511/9/8/133 Smart Cities, Vol. 9, Pages 132: Definition of Charging Fee for Drainage Services and Incentives Based on LID Simulation https://www.mdpi.com/2624-6511/9/8/132 Given the scarcity of initiatives to charge for urban stormwater services in Brazil and the need to recognise users’ efforts in adopting technologies such as Low Impact Development (LID), a proposal was developed for a stormwater drainage fee and incentives for environmental services in a Brazilian municipality, based on flows retained by LIDs, specifically infiltration wells. To this end, simulations were carried out using the Storm Water Management Model (SWMM) for a 0.5 km2 area in a Brazilian city that does not yet implement such charges. Based on the identification of the total flow retained by users within the watershed, the avoided cost to the drainage system was estimated. The charging model was defined using the avoided cost method associated with the Simplified Equivalent Residential Unit (SERU). In the baseline scenario that allocates the operation and maintenance cost, the estimated annual fee was USD 17.22 per household without LID and USD 14.64 per household with LID, and the SERU area was 371.11 m2, used as a property-area reference; in an incentive scenario designed to reduce the user payback period to approximately 10 years, the fee for households without LID was set at USD 73.78. An economic incentive policy was identified, consisting of fee discounts upon adoption of LIDs, as well as support for their installation and maintenance. Thus, it was validated that combining a drainage fee with economic incentives is both feasible and motivating for both system users and managers. 2026-08-18 Smart Cities, Vol. 9, Pages 132: Definition of Charging Fee for Drainage Services and Incentives Based on LID Simulation

Smart Cities doi: 10.3390/smartcities9080132

Authors: Ana Paula Camargo de Vicente Klebber Teodomiro Martins Formiga

Given the scarcity of initiatives to charge for urban stormwater services in Brazil and the need to recognise users’ efforts in adopting technologies such as Low Impact Development (LID), a proposal was developed for a stormwater drainage fee and incentives for environmental services in a Brazilian municipality, based on flows retained by LIDs, specifically infiltration wells. To this end, simulations were carried out using the Storm Water Management Model (SWMM) for a 0.5 km2 area in a Brazilian city that does not yet implement such charges. Based on the identification of the total flow retained by users within the watershed, the avoided cost to the drainage system was estimated. The charging model was defined using the avoided cost method associated with the Simplified Equivalent Residential Unit (SERU). In the baseline scenario that allocates the operation and maintenance cost, the estimated annual fee was USD 17.22 per household without LID and USD 14.64 per household with LID, and the SERU area was 371.11 m2, used as a property-area reference; in an incentive scenario designed to reduce the user payback period to approximately 10 years, the fee for households without LID was set at USD 73.78. An economic incentive policy was identified, consisting of fee discounts upon adoption of LIDs, as well as support for their installation and maintenance. Thus, it was validated that combining a drainage fee with economic incentives is both feasible and motivating for both system users and managers.

]]> Definition of Charging Fee for Drainage Services and Incentives Based on LID Simulation Ana Paula Camargo de Vicente Klebber Teodomiro Martins Formiga doi: 10.3390/smartcities9080132 Smart Cities 2026-08-18 Smart Cities 2026-08-18 9 8 Article 132 10.3390/smartcities9080132 https://www.mdpi.com/2624-6511/9/8/132 Smart Cities, Vol. 9, Pages 131: SEMG-Net: State-Event Guided Multi-Scale Gated Network for Non-Intrusive Load Monitoring in Smart Buildings https://www.mdpi.com/2624-6511/9/8/131 Non-intrusive load monitoring (NILM) provides a cost-effective way to obtain appliance-level electricity information from aggregate smart-meter measurements and is therefore important for energy management, demand-side response, and sustainable operation in smart buildings. However, accurate appliance-level power disaggregation remains challenging because residential load signals usually involve overlapping appliance signatures, sparse activations, heterogeneous temporal patterns, and transient switching events. To address these challenges, this paper proposes a State-Event-Guided Multi-Scale Gated Network (SEMG-Net) for NILM. The proposed framework integrates a residual temporal encoder, multi-scale dilated convolutional blocks, and a state-event-guided gating mechanism within a unified multi-task learning architecture. The shared encoder extracts hierarchical temporal representations from aggregate mains windows, while task-specific branches jointly estimate appliance power, on/off state, and switching event type. The predicted state probability, three-class event probability distribution, and shared temporal representation are jointly used to construct a continuous gate that modulates the raw power estimate, thereby directly incorporating behavioral predictions into final power estimation. Experimental results on public datasets show that SEMG-Net achieves competitive overall performance, with clear advantages in power estimation, energy consistency, and state identification, particularly for appliances with complex operating stages or transient switching behavior. The ablation results further demonstrate the benefits of multi-scale feature extraction and auxiliary supervision, as well as the effectiveness of the proposed state-event-guided power modulation mechanism. 2026-08-15 Smart Cities, Vol. 9, Pages 131: SEMG-Net: State-Event Guided Multi-Scale Gated Network for Non-Intrusive Load Monitoring in Smart Buildings

Smart Cities doi: 10.3390/smartcities9080131

Authors: Keqin Li Chengyuan Sun

Non-intrusive load monitoring (NILM) provides a cost-effective way to obtain appliance-level electricity information from aggregate smart-meter measurements and is therefore important for energy management, demand-side response, and sustainable operation in smart buildings. However, accurate appliance-level power disaggregation remains challenging because residential load signals usually involve overlapping appliance signatures, sparse activations, heterogeneous temporal patterns, and transient switching events. To address these challenges, this paper proposes a State-Event-Guided Multi-Scale Gated Network (SEMG-Net) for NILM. The proposed framework integrates a residual temporal encoder, multi-scale dilated convolutional blocks, and a state-event-guided gating mechanism within a unified multi-task learning architecture. The shared encoder extracts hierarchical temporal representations from aggregate mains windows, while task-specific branches jointly estimate appliance power, on/off state, and switching event type. The predicted state probability, three-class event probability distribution, and shared temporal representation are jointly used to construct a continuous gate that modulates the raw power estimate, thereby directly incorporating behavioral predictions into final power estimation. Experimental results on public datasets show that SEMG-Net achieves competitive overall performance, with clear advantages in power estimation, energy consistency, and state identification, particularly for appliances with complex operating stages or transient switching behavior. The ablation results further demonstrate the benefits of multi-scale feature extraction and auxiliary supervision, as well as the effectiveness of the proposed state-event-guided power modulation mechanism.

]]> SEMG-Net: State-Event Guided Multi-Scale Gated Network for Non-Intrusive Load Monitoring in Smart Buildings Keqin Li Chengyuan Sun doi: 10.3390/smartcities9080131 Smart Cities 2026-08-15 Smart Cities 2026-08-15 9 8 Article 131 10.3390/smartcities9080131 https://www.mdpi.com/2624-6511/9/8/131 Smart Cities, Vol. 9, Pages 130: Curbside Parking Use, Turnover, and Regulatory Compliance in an Intermediate Latin American City: Field Evidence from Loja, Ecuador https://www.mdpi.com/2624-6511/9/8/130 Direct evidence on curbside parking use in intermediate Latin American cities remains limited. This study characterized parking duration, purpose, turnover, accumulation, and regulatory compliance across six segment–date sessions in central Loja, Ecuador. Of 1426 observed curbside events, 1397 were retained after quality control. Analyses included descriptive and non-parametric tests, multivariable models with CR2 standard errors clustered by segment–date, and sensitivity analyses. Duration was strongly right-skewed (median 4 min; interquartile range 1–13 min; mean 36.3 min; P95 332.6 min), while passenger pick-up/drop-off accounted for 54.5% of events. Non-permitted maneuvers represented 64.0%. The four segment-sessions containing SIMERT coverage comprised 862 valid events, of which 776 occurred within marked SIMERT locations. Among the 644 marked-location events observed during payment-required hours, visible SIMERT use was recorded in 70 events (10.9%). After restricting the SIMERT component to marked locations during payment-required hours, composite non-compliance was identified in 1167 events (83.5%). During the common 06:30–18:30 comparison window, hourly turnover ranged from 0.54 to 1.96 events per legal space per hour, while cumulative space–time demand ranged from 11.6% to 154.8% of nominal legal space–time capacity. The value above 100% represents summed parking duration relative to nominal legal capacity and does not indicate simultaneous occupancy above 100%. Excluding session-boundary proxies left the median and interquartile range unchanged, although upper-tail estimates remained sensitive. Because each segment was observed on a single date, between-session differences cannot be interpreted as independent corridor effects. Natural-spline specifications provided better temporal fit than linear-hour specifications for both non-permitted maneuvers and revised composite non-compliance. These findings provide a reproducible local baseline for testing conventional and smart curb-management measures through repeated pilot studies. 2026-08-14 Smart Cities, Vol. 9, Pages 130: Curbside Parking Use, Turnover, and Regulatory Compliance in an Intermediate Latin American City: Field Evidence from Loja, Ecuador

Smart Cities doi: 10.3390/smartcities9080130

Authors: Yasmany García-Ramírez Juan Diego Ríos-Arévalo Michael Sanmartín-Jaramillo Eduardo Romero-Aguilar

Direct evidence on curbside parking use in intermediate Latin American cities remains limited. This study characterized parking duration, purpose, turnover, accumulation, and regulatory compliance across six segment–date sessions in central Loja, Ecuador. Of 1426 observed curbside events, 1397 were retained after quality control. Analyses included descriptive and non-parametric tests, multivariable models with CR2 standard errors clustered by segment–date, and sensitivity analyses. Duration was strongly right-skewed (median 4 min; interquartile range 1–13 min; mean 36.3 min; P95 332.6 min), while passenger pick-up/drop-off accounted for 54.5% of events. Non-permitted maneuvers represented 64.0%. The four segment-sessions containing SIMERT coverage comprised 862 valid events, of which 776 occurred within marked SIMERT locations. Among the 644 marked-location events observed during payment-required hours, visible SIMERT use was recorded in 70 events (10.9%). After restricting the SIMERT component to marked locations during payment-required hours, composite non-compliance was identified in 1167 events (83.5%). During the common 06:30–18:30 comparison window, hourly turnover ranged from 0.54 to 1.96 events per legal space per hour, while cumulative space–time demand ranged from 11.6% to 154.8% of nominal legal space–time capacity. The value above 100% represents summed parking duration relative to nominal legal capacity and does not indicate simultaneous occupancy above 100%. Excluding session-boundary proxies left the median and interquartile range unchanged, although upper-tail estimates remained sensitive. Because each segment was observed on a single date, between-session differences cannot be interpreted as independent corridor effects. Natural-spline specifications provided better temporal fit than linear-hour specifications for both non-permitted maneuvers and revised composite non-compliance. These findings provide a reproducible local baseline for testing conventional and smart curb-management measures through repeated pilot studies.

]]> Curbside Parking Use, Turnover, and Regulatory Compliance in an Intermediate Latin American City: Field Evidence from Loja, Ecuador Yasmany García-Ramírez Juan Diego Ríos-Arévalo Michael Sanmartín-Jaramillo Eduardo Romero-Aguilar doi: 10.3390/smartcities9080130 Smart Cities 2026-08-14 Smart Cities 2026-08-14 9 8 Article 130 10.3390/smartcities9080130 https://www.mdpi.com/2624-6511/9/8/130 Smart Cities, Vol. 9, Pages 129: Urban Lifeline Security Projects: Research on the Holistic Governance Model of Urban Public Security Empowered by Digital Technology https://www.mdpi.com/2624-6511/9/8/129 With the rapid advancement of urbanization, the density and vulnerability of urban lifeline networks are increasing, and urban lifeline security risks have become a major challenge to urban public security governance. The backward governance means and fragmented governance mechanisms cannot adapt to the complex emerging urban public security risks. Digital empowerment is considered to be a new solution for the holistic governance of urban lifeline security, but related research has only focused on a single scenario, a single risk type or a single risk management link. This study shifted from a single perspective to a holistic perspective and explored how to use digital technology to develop the urban lifeline security project from three levels, that is, overall methods, key supporting technology, and governance mechanism innovation, so as to enable a holistic governance model for lifeline security. Specifically, this study constructed the main processes and methods for constructing urban lifeline security projects, the key supporting technology system for the scenario-driven urban lifeline security project, and the overall governance mechanism for the urban lifeline security project. The case from Hefei, China, further verifies the effectiveness of urban lifeline security engineering. The contribution of this study is to promote the collaborative innovation and integrated application of engineering technology and governance mechanisms in the field of holistic governance of urban lifeline security. 2026-08-13 Smart Cities, Vol. 9, Pages 129: Urban Lifeline Security Projects: Research on the Holistic Governance Model of Urban Public Security Empowered by Digital Technology

Smart Cities doi: 10.3390/smartcities9080129

Authors: Qi Zou Shuai Liu Hongyong Yuan Jiaojiao Liu

With the rapid advancement of urbanization, the density and vulnerability of urban lifeline networks are increasing, and urban lifeline security risks have become a major challenge to urban public security governance. The backward governance means and fragmented governance mechanisms cannot adapt to the complex emerging urban public security risks. Digital empowerment is considered to be a new solution for the holistic governance of urban lifeline security, but related research has only focused on a single scenario, a single risk type or a single risk management link. This study shifted from a single perspective to a holistic perspective and explored how to use digital technology to develop the urban lifeline security project from three levels, that is, overall methods, key supporting technology, and governance mechanism innovation, so as to enable a holistic governance model for lifeline security. Specifically, this study constructed the main processes and methods for constructing urban lifeline security projects, the key supporting technology system for the scenario-driven urban lifeline security project, and the overall governance mechanism for the urban lifeline security project. The case from Hefei, China, further verifies the effectiveness of urban lifeline security engineering. The contribution of this study is to promote the collaborative innovation and integrated application of engineering technology and governance mechanisms in the field of holistic governance of urban lifeline security.

]]> Urban Lifeline Security Projects: Research on the Holistic Governance Model of Urban Public Security Empowered by Digital Technology Qi Zou Shuai Liu Hongyong Yuan Jiaojiao Liu doi: 10.3390/smartcities9080129 Smart Cities 2026-08-13 Smart Cities 2026-08-13 9 8 Article 129 10.3390/smartcities9080129 https://www.mdpi.com/2624-6511/9/8/129 Smart Cities, Vol. 9, Pages 128: Impact of Spatial Knowledge on Fire Evacuation Performance in Large Buildings: An Integrated Simulation Approach https://www.mdpi.com/2624-6511/9/8/128 This study examines human evacuation performance in complex building environments under highly uncertain fire conditions, with a focus on how spatial knowledge and decision-making strategies influence exposure to hazardous conditions during emergencies in smart building contexts. A hybrid simulation framework integrating physical fire modeling, agent-based simulation (ABM), and data-driven analysis is applied to a large academic building in Santiago, Chile, incorporating heterogeneous occupant profiles with different levels of spatial knowledge while evaluating key environmental variables such as temperature, oxygen (O2) concentration, carbon dioxide (CO2) levels, and carbon monoxide (CO) concentrations. Stochastic behavioral variability is captured through Monte Carlo simulation, and associations between environmental conditions and evacuation responses are analyzed using Kendall’s correlation. Results show that evacuation strategies based on optimal route knowledge significantly reduce exposure to life-threatening conditions and decrease evacuation times by 34% for adults and 8.5% for young occupants compared with scenarios without prior spatial information. These findings highlight the critical role of spatial knowledge in evacuation decision-making and provide a transferable methodological framework for improving smart building safety systems and data-driven evacuation planning in high-occupancy urban environments. 2026-08-05 Smart Cities, Vol. 9, Pages 128: Impact of Spatial Knowledge on Fire Evacuation Performance in Large Buildings: An Integrated Simulation Approach

Smart Cities doi: 10.3390/smartcities9080128

Authors: Rodrigo Ternero Miguel Alfaro Gabriel Larrain Guillermo Fuertes Juan Pablo Torres Pavlo Santander

This study examines human evacuation performance in complex building environments under highly uncertain fire conditions, with a focus on how spatial knowledge and decision-making strategies influence exposure to hazardous conditions during emergencies in smart building contexts. A hybrid simulation framework integrating physical fire modeling, agent-based simulation (ABM), and data-driven analysis is applied to a large academic building in Santiago, Chile, incorporating heterogeneous occupant profiles with different levels of spatial knowledge while evaluating key environmental variables such as temperature, oxygen (O2) concentration, carbon dioxide (CO2) levels, and carbon monoxide (CO) concentrations. Stochastic behavioral variability is captured through Monte Carlo simulation, and associations between environmental conditions and evacuation responses are analyzed using Kendall’s correlation. Results show that evacuation strategies based on optimal route knowledge significantly reduce exposure to life-threatening conditions and decrease evacuation times by 34% for adults and 8.5% for young occupants compared with scenarios without prior spatial information. These findings highlight the critical role of spatial knowledge in evacuation decision-making and provide a transferable methodological framework for improving smart building safety systems and data-driven evacuation planning in high-occupancy urban environments.

]]> Impact of Spatial Knowledge on Fire Evacuation Performance in Large Buildings: An Integrated Simulation Approach Rodrigo Ternero Miguel Alfaro Gabriel Larrain Guillermo Fuertes Juan Pablo Torres Pavlo Santander doi: 10.3390/smartcities9080128 Smart Cities 2026-08-05 Smart Cities 2026-08-05 9 8 Article 128 10.3390/smartcities9080128 https://www.mdpi.com/2624-6511/9/8/128 Smart Cities, Vol. 9, Pages 127: Impact of Electrical Vehicle Charging Stations on the Electric Grid: Lessons Learnt and Challenges https://www.mdpi.com/2624-6511/9/8/127 The ambitious roadmap for a sustainable transport system adopted by the European Commission (EC) by 2050 includes the deployment of an extensive Electric Vehicle Charging Stations (EVCSs) infrastructure, which introduces significant challenges for distribution power grids. High power demand, particularly from fast-charging systems, may lead to network overloading and voltage unbalance. In addition, recent measurement campaigns highlight substantial changes in grid impedance and the emergence of resonance phenomena, together with the injection and propagation of high-frequency conducted disturbances. These effects extend over a wide frequency range, up to several hundreds of kHz, causing degradation, aging and malfunction of network assets, in particular Power Line Communications. This paper provides a comprehensive and updated review of the impact of EVCSs on electrical grids, covering power flow, power quality, stability, and impedance-related interactions. Particular attention is given to the role of power-electronic converters, high-frequency emissions, and the associated challenges in measurement and standardization. The analysis highlights that EVCS integration fundamentally alters the nature of electrical loads, requiring new approaches for grid planning, monitoring, and regulation. The study identifies key research gaps and outlines future directions to ensure the reliable and sustainable integration of electromobility into modern power systems. 2026-08-04 Smart Cities, Vol. 9, Pages 127: Impact of Electrical Vehicle Charging Stations on the Electric Grid: Lessons Learnt and Challenges

Smart Cities doi: 10.3390/smartcities9080127

Authors: Andrea Mariscotti Alexander Gallarreta Yljon Seferi Sahil Bhagat Brian G. Stewart Igor Fernandez David De la Vega Graeme Burt

The ambitious roadmap for a sustainable transport system adopted by the European Commission (EC) by 2050 includes the deployment of an extensive Electric Vehicle Charging Stations (EVCSs) infrastructure, which introduces significant challenges for distribution power grids. High power demand, particularly from fast-charging systems, may lead to network overloading and voltage unbalance. In addition, recent measurement campaigns highlight substantial changes in grid impedance and the emergence of resonance phenomena, together with the injection and propagation of high-frequency conducted disturbances. These effects extend over a wide frequency range, up to several hundreds of kHz, causing degradation, aging and malfunction of network assets, in particular Power Line Communications. This paper provides a comprehensive and updated review of the impact of EVCSs on electrical grids, covering power flow, power quality, stability, and impedance-related interactions. Particular attention is given to the role of power-electronic converters, high-frequency emissions, and the associated challenges in measurement and standardization. The analysis highlights that EVCS integration fundamentally alters the nature of electrical loads, requiring new approaches for grid planning, monitoring, and regulation. The study identifies key research gaps and outlines future directions to ensure the reliable and sustainable integration of electromobility into modern power systems.

]]> Impact of Electrical Vehicle Charging Stations on the Electric Grid: Lessons Learnt and Challenges Andrea Mariscotti Alexander Gallarreta Yljon Seferi Sahil Bhagat Brian G. Stewart Igor Fernandez David De la Vega Graeme Burt doi: 10.3390/smartcities9080127 Smart Cities 2026-08-04 Smart Cities 2026-08-04 9 8 Review 127 10.3390/smartcities9080127 https://www.mdpi.com/2624-6511/9/8/127 Smart Cities, Vol. 9, Pages 126: Development of an RAG-Integrated Agentic BIM System for Intelligent Railway Maintenance https://www.mdpi.com/2624-6511/9/8/126 Modern railway maintenance is transitioning toward a condition-based maintenance system to stably operate the core infrastructure of sustainable smart cities. However, technical limitations remain in manually converting and analyzing massive amounts of inspection data into Building Information Modeling (BIM) objects. This causes information delays and technical severance in data-driven smart-city infrastructure. To address these challenges, this study proposes an Agentic BIM framework that integrates Large Language Model (LLM), Model Context Protocol (MCP), and Retrieval Augmented Generation (RAG) technologies. The proposed methodology standardizes the control channel between the LLM and BIM software through a central MCP server, while securing the accuracy of engineering judgments by utilizing the RAG pipeline to reference national railway-track-maintenance guidelines. System validation results demonstrated that geometric inspection data, including gauge and alignment, were automatically generated as BIM objects without human intervention. Furthermore, the maintenance grades and deadlines for sections exceeding thresholds were immediately highlighted within the model as visual attributes. Consequently, this framework proves an autonomous decision-making system that organically links inspection data with maintenance regulations. By transforming static, manual-labor-centered maintenance workflows into intelligent automated models, it increases the efficiency of railway infrastructure management while providing a scalable technical foundation for overall asset management of future smart-city infrastructure. 2026-08-04 Smart Cities, Vol. 9, Pages 126: Development of an RAG-Integrated Agentic BIM System for Intelligent Railway Maintenance

Smart Cities doi: 10.3390/smartcities9080126

Authors: Minjae Jeon Yonggun Kim Seok Kim

Modern railway maintenance is transitioning toward a condition-based maintenance system to stably operate the core infrastructure of sustainable smart cities. However, technical limitations remain in manually converting and analyzing massive amounts of inspection data into Building Information Modeling (BIM) objects. This causes information delays and technical severance in data-driven smart-city infrastructure. To address these challenges, this study proposes an Agentic BIM framework that integrates Large Language Model (LLM), Model Context Protocol (MCP), and Retrieval Augmented Generation (RAG) technologies. The proposed methodology standardizes the control channel between the LLM and BIM software through a central MCP server, while securing the accuracy of engineering judgments by utilizing the RAG pipeline to reference national railway-track-maintenance guidelines. System validation results demonstrated that geometric inspection data, including gauge and alignment, were automatically generated as BIM objects without human intervention. Furthermore, the maintenance grades and deadlines for sections exceeding thresholds were immediately highlighted within the model as visual attributes. Consequently, this framework proves an autonomous decision-making system that organically links inspection data with maintenance regulations. By transforming static, manual-labor-centered maintenance workflows into intelligent automated models, it increases the efficiency of railway infrastructure management while providing a scalable technical foundation for overall asset management of future smart-city infrastructure.

]]> Development of an RAG-Integrated Agentic BIM System for Intelligent Railway Maintenance Minjae Jeon Yonggun Kim Seok Kim doi: 10.3390/smartcities9080126 Smart Cities 2026-08-04 Smart Cities 2026-08-04 9 8 Article 126 10.3390/smartcities9080126 https://www.mdpi.com/2624-6511/9/8/126 Smart Cities, Vol. 9, Pages 125: Hierarchical Reinforcement Learning with Hungarian Assignment for Reliable Urban Smart Metering Under Cognitive Spectrum Access https://www.mdpi.com/2624-6511/9/8/125 Advanced metering infrastructure (AMI) is the sensing backbone of the smart grid, and its reliability underpins urban energy services such as state estimation, demand response, and distributed-energy integration. When AMI uses cellular spectrum leased through a cognitive mobile virtual network operator (C-MVNO), allocating channels to data aggregation points (DAPs) each frame is difficult because three uncertainties interact: imperfect spectrum sensing, time-varying and cross-channel-correlated primary-user activity, and stochastic urban propagation. Classical Hungarian assignment is optimal per frame but blind to primary-user dynamics, while cognitive-radio heuristics ignore queue state and cross-channel structure. We propose a two-timescale hierarchy that couples these established tools in a new way: a Proximal Policy Optimization (PPO) agent decides, once per epoch, which opportunistic channels to expose, and an exact Hungarian solver performs the per-frame DAP-to-channel assignment. To our knowledge this is the first coupling of a learned cognitive layer with exact Hungarian assignment for cognitive-radio resource allocation. On a 3GPP TR 38.901-compliant simulator, PPO significantly outperforms a Bayesian-belief baseline and the Hungarian-only configuration in delivery ratio, latency, and a strict per-meter satisfaction metric, and is robust across independent seeds and sensitivity sweeps. An architectural ablation shows the DAP tier is a precondition for viability, not merely an optimization. 2026-07-31 Smart Cities, Vol. 9, Pages 125: Hierarchical Reinforcement Learning with Hungarian Assignment for Reliable Urban Smart Metering Under Cognitive Spectrum Access

Smart Cities doi: 10.3390/smartcities9080125

Authors: Muhammed Al-Ali Esteban Inga Juan Inga Elias Yaacoub

Advanced metering infrastructure (AMI) is the sensing backbone of the smart grid, and its reliability underpins urban energy services such as state estimation, demand response, and distributed-energy integration. When AMI uses cellular spectrum leased through a cognitive mobile virtual network operator (C-MVNO), allocating channels to data aggregation points (DAPs) each frame is difficult because three uncertainties interact: imperfect spectrum sensing, time-varying and cross-channel-correlated primary-user activity, and stochastic urban propagation. Classical Hungarian assignment is optimal per frame but blind to primary-user dynamics, while cognitive-radio heuristics ignore queue state and cross-channel structure. We propose a two-timescale hierarchy that couples these established tools in a new way: a Proximal Policy Optimization (PPO) agent decides, once per epoch, which opportunistic channels to expose, and an exact Hungarian solver performs the per-frame DAP-to-channel assignment. To our knowledge this is the first coupling of a learned cognitive layer with exact Hungarian assignment for cognitive-radio resource allocation. On a 3GPP TR 38.901-compliant simulator, PPO significantly outperforms a Bayesian-belief baseline and the Hungarian-only configuration in delivery ratio, latency, and a strict per-meter satisfaction metric, and is robust across independent seeds and sensitivity sweeps. An architectural ablation shows the DAP tier is a precondition for viability, not merely an optimization.

]]> Hierarchical Reinforcement Learning with Hungarian Assignment for Reliable Urban Smart Metering Under Cognitive Spectrum Access Muhammed Al-Ali Esteban Inga Juan Inga Elias Yaacoub doi: 10.3390/smartcities9080125 Smart Cities 2026-07-31 Smart Cities 2026-07-31 9 8 Article 125 10.3390/smartcities9080125 https://www.mdpi.com/2624-6511/9/8/125 Smart Cities, Vol. 9, Pages 124: Intelligent Community Monitoring Through Citizen Science and AI: An ISO 37120-Based Framework for Sustainable Development in Ecuador https://www.mdpi.com/2624-6511/9/8/124 This paper proposes a comprehensive approach for data-driven participatory community monitoring based on “Citizen Science” (CS), ISO 37120, and artificial intelligence (AI). The design integrates AI with the CS six-stage life cycle and citizen data governance principles through an AI-CS framework, aligning with the Copenhagen Social Summit. The framework was developed for local governments in Ecuador, a country where territorial planning lacks citizen data disaggregated by territorial, sociodemographic, and contextual variables. This fact limits the capacity of local governments to make evidence-based decisions. Between October 2025 and February 2026, data from 30,253 events were collected in 22 provinces and 93 cantons of the country. The data were analyzed by means of ordinal logistic regression to identify predictors of perceived severity and by means of DBSCAN, an unsupervised machine learning clustering algorithm, to characterize territorial patterns. The results suggest that citizen perception is organized into systemic and predictable patterns when structured using ISO 37120 categories. The spatial analysis reveals heterogeneous territorial patterns with levels of urgency that differ depending on the canton and the urban–rural context. The proposed approach allows local governments to obtain disaggregated territorial data for participatory planning. Its design may be transferable to other Global South contexts facing similar data gaps and is aligned with SDGs 9, 11, 16, and 17. 2026-07-31 Smart Cities, Vol. 9, Pages 124: Intelligent Community Monitoring Through Citizen Science and AI: An ISO 37120-Based Framework for Sustainable Development in Ecuador

Smart Cities doi: 10.3390/smartcities9080124

Authors: Segundo Benitez-Hurtado Daniel Guamán Priscila Valdiviezo-Diaz Janneth Chicaiza

This paper proposes a comprehensive approach for data-driven participatory community monitoring based on “Citizen Science” (CS), ISO 37120, and artificial intelligence (AI). The design integrates AI with the CS six-stage life cycle and citizen data governance principles through an AI-CS framework, aligning with the Copenhagen Social Summit. The framework was developed for local governments in Ecuador, a country where territorial planning lacks citizen data disaggregated by territorial, sociodemographic, and contextual variables. This fact limits the capacity of local governments to make evidence-based decisions. Between October 2025 and February 2026, data from 30,253 events were collected in 22 provinces and 93 cantons of the country. The data were analyzed by means of ordinal logistic regression to identify predictors of perceived severity and by means of DBSCAN, an unsupervised machine learning clustering algorithm, to characterize territorial patterns. The results suggest that citizen perception is organized into systemic and predictable patterns when structured using ISO 37120 categories. The spatial analysis reveals heterogeneous territorial patterns with levels of urgency that differ depending on the canton and the urban–rural context. The proposed approach allows local governments to obtain disaggregated territorial data for participatory planning. Its design may be transferable to other Global South contexts facing similar data gaps and is aligned with SDGs 9, 11, 16, and 17.

]]> Intelligent Community Monitoring Through Citizen Science and AI: An ISO 37120-Based Framework for Sustainable Development in Ecuador Segundo Benitez-Hurtado Daniel Guamán Priscila Valdiviezo-Diaz Janneth Chicaiza doi: 10.3390/smartcities9080124 Smart Cities 2026-07-31 Smart Cities 2026-07-31 9 8 Article 124 10.3390/smartcities9080124 https://www.mdpi.com/2624-6511/9/8/124 Smart Cities, Vol. 9, Pages 123: Digital Twins in Intelligent Transport Systems: A Systematic Review of Resilience Mechanisms and Smart City Implications https://www.mdpi.com/2624-6511/9/8/123 The intensification of urbanization, the growth in mobility demand and the multiplication of disruptions expose intelligent transport systems to new operational vulnerabilities, making resilience a central issue for the management of transport networks. By conducting a systematic literature review, in accordance with the PRISMA 2020 and PRISMA-S recommendations, this article examines the extent to which, through which functions, under which conditions, and with what level of evidence digital twins can support the resilience of intelligent transport systems. The literature search covered the 2020–2025 period across Scopus, IEEE Xplore, and TRID and was complemented by backward and forward citation chaining, targeting research and review articles dealing with digital twins in transport, mobility, transport infrastructures, or ITS, as well as their links with resilience mechanisms. After screening and eligibility assessment, 61 studies were included in the final analytical corpus. The results show that digital twins are no longer limited to a simple virtual representation of the physical system but are increasingly established as service-oriented cyber–physical layers capable of supporting functions that may contribute to resilience, including real-time visibility, disruption anticipation, scenario simulation, dynamic optimization, decision support, service continuity, and post-disruption learning. The study also highlights several persistent limitations, notably conceptual instability, the sectoral concentration of studies, the lack of large-scale empirical validation, and the insufficient consideration of organizational, human, and governance dimensions. It concludes that digital twins should not be interpreted as automatically enhancing the resilience of ITS, but rather as having the potential to support resilience when they are associated with reliable data, interoperability, synchronization, model reliability, and the ability of stakeholders to transform digital intelligence into coordinated operational responses. 2026-07-31 Smart Cities, Vol. 9, Pages 123: Digital Twins in Intelligent Transport Systems: A Systematic Review of Resilience Mechanisms and Smart City Implications

Smart Cities doi: 10.3390/smartcities9080123

Authors: Badr Machkour Naoufal Rouky Ahmed Abriane Mouhsene Fri Othmane Benmoussa

The intensification of urbanization, the growth in mobility demand and the multiplication of disruptions expose intelligent transport systems to new operational vulnerabilities, making resilience a central issue for the management of transport networks. By conducting a systematic literature review, in accordance with the PRISMA 2020 and PRISMA-S recommendations, this article examines the extent to which, through which functions, under which conditions, and with what level of evidence digital twins can support the resilience of intelligent transport systems. The literature search covered the 2020–2025 period across Scopus, IEEE Xplore, and TRID and was complemented by backward and forward citation chaining, targeting research and review articles dealing with digital twins in transport, mobility, transport infrastructures, or ITS, as well as their links with resilience mechanisms. After screening and eligibility assessment, 61 studies were included in the final analytical corpus. The results show that digital twins are no longer limited to a simple virtual representation of the physical system but are increasingly established as service-oriented cyber–physical layers capable of supporting functions that may contribute to resilience, including real-time visibility, disruption anticipation, scenario simulation, dynamic optimization, decision support, service continuity, and post-disruption learning. The study also highlights several persistent limitations, notably conceptual instability, the sectoral concentration of studies, the lack of large-scale empirical validation, and the insufficient consideration of organizational, human, and governance dimensions. It concludes that digital twins should not be interpreted as automatically enhancing the resilience of ITS, but rather as having the potential to support resilience when they are associated with reliable data, interoperability, synchronization, model reliability, and the ability of stakeholders to transform digital intelligence into coordinated operational responses.

]]> Digital Twins in Intelligent Transport Systems: A Systematic Review of Resilience Mechanisms and Smart City Implications Badr Machkour Naoufal Rouky Ahmed Abriane Mouhsene Fri Othmane Benmoussa doi: 10.3390/smartcities9080123 Smart Cities 2026-07-31 Smart Cities 2026-07-31 9 8 Review 123 10.3390/smartcities9080123 https://www.mdpi.com/2624-6511/9/8/123 Smart Cities, Vol. 9, Pages 122: Mapping the Affordability of Campus Digital Twin Implementation in the United States https://www.mdpi.com/2624-6511/9/8/122 Digital Twin technologies hold significant promise for advancing smart campus initiatives by enabling data-driven management of facilities, sustainability planning, and safety monitoring. Despite this potential, affordability remains a critical barrier to widespread adoption across higher education institutions. This study introduces an initial exploratory scenario-based affordability index for campus digital twin and maps the affordability of implementing campus digital twin across 1872 U.S. higher education institutions using spatial analysis techniques. Sensitivity analysis is also conducted to evaluate the robustness of the results. Our analysis yields three key findings: (1) Under the baseline scenario, most campuses show moderate-to-high affordability with spatial clusters concentrated in coastal and metropolitan regions, while nearly one-quarter remain unaffordable or marginally affordable, with clusters located in the Midwest. (2) Private institutions demonstrate relatively greater affordability than public institutions, with for-profit private institutions exhibiting higher affordability than their non-profit counterparts. Spatial aggregation patterns further reveal heterogeneity in affordability between these sectors. (3) States with strong economic and educational infrastructures, such as California, contain a greater number of affordable campuses for digital twin implementation, while resource-constrained states face significant barriers. These findings remain generally robust and consistent across the baseline and sensitivity scenarios. The results underscore the need for standardized cost models, public cost databases, targeted policy guidance, and multi-stakeholder collaboration to promote equitable adoption. By positioning digital twins as strategic tools for campus resilience, efficiency, and innovation, this study advances the conceptual understanding of their role in higher education and provides exploratory yet actionable insights for institutional leaders and policymakers to support inclusive digital transformation. 2026-07-29 Smart Cities, Vol. 9, Pages 122: Mapping the Affordability of Campus Digital Twin Implementation in the United States

Smart Cities doi: 10.3390/smartcities9080122

Authors: Yuchen Wang Xinyue Ye Sicheng Wang Devika Jain

Digital Twin technologies hold significant promise for advancing smart campus initiatives by enabling data-driven management of facilities, sustainability planning, and safety monitoring. Despite this potential, affordability remains a critical barrier to widespread adoption across higher education institutions. This study introduces an initial exploratory scenario-based affordability index for campus digital twin and maps the affordability of implementing campus digital twin across 1872 U.S. higher education institutions using spatial analysis techniques. Sensitivity analysis is also conducted to evaluate the robustness of the results. Our analysis yields three key findings: (1) Under the baseline scenario, most campuses show moderate-to-high affordability with spatial clusters concentrated in coastal and metropolitan regions, while nearly one-quarter remain unaffordable or marginally affordable, with clusters located in the Midwest. (2) Private institutions demonstrate relatively greater affordability than public institutions, with for-profit private institutions exhibiting higher affordability than their non-profit counterparts. Spatial aggregation patterns further reveal heterogeneity in affordability between these sectors. (3) States with strong economic and educational infrastructures, such as California, contain a greater number of affordable campuses for digital twin implementation, while resource-constrained states face significant barriers. These findings remain generally robust and consistent across the baseline and sensitivity scenarios. The results underscore the need for standardized cost models, public cost databases, targeted policy guidance, and multi-stakeholder collaboration to promote equitable adoption. By positioning digital twins as strategic tools for campus resilience, efficiency, and innovation, this study advances the conceptual understanding of their role in higher education and provides exploratory yet actionable insights for institutional leaders and policymakers to support inclusive digital transformation.

]]> Mapping the Affordability of Campus Digital Twin Implementation in the United States Yuchen Wang Xinyue Ye Sicheng Wang Devika Jain doi: 10.3390/smartcities9080122 Smart Cities 2026-07-29 Smart Cities 2026-07-29 9 8 Article 122 10.3390/smartcities9080122 https://www.mdpi.com/2624-6511/9/8/122 Smart Cities, Vol. 9, Pages 121: Agent-Based Analysis of Cryptocurrency Adoption in Transit Systems https://www.mdpi.com/2624-6511/9/8/121 As cryptocurrency adoption accelerates globally, cities face a critical question: can digital currencies be adapted by different agencies without compromising financial stability? This paper develops an agent-based modeling framework that enables transit authorities to systematically explore cryptocurrency integration strategies. We simulate 1000 heterogeneous agents with varying risk tolerance, technological proficiency, and social influence susceptibility over 365 days, testing five policy regimes across a comprehensive scenario matrix comprising four risk-attitude compositions, four technology-adoption levels, four social-influence intensities, and three market conditions (bullish, neutral, bearish)—creating 192 distinct population-market configurations evaluated across all five policies with 15 independent replications per configuration (14,400 total simulation runs). The framework produces adoption outcomes ranging from near-zero to over 49% depending on scenario assumptions, with technology familiarity emerging as the dominant driver. The framework provides transit authorities with a practical tool for scenario-based planning: testing policy interventions, stress-testing financial stability under various market conditions, identifying potential vulnerabilities before deployment, and comparing alternative strategies across diverse demographic contexts. This simulation-based approach enables data-driven decision-making in the absence of real-world precedent, offering a structured methodology for evaluating cryptocurrency integration while managing financial stability risks. 2026-07-26 Smart Cities, Vol. 9, Pages 121: Agent-Based Analysis of Cryptocurrency Adoption in Transit Systems

Smart Cities doi: 10.3390/smartcities9080121

Authors: Mahdieh Allahviranloo

As cryptocurrency adoption accelerates globally, cities face a critical question: can digital currencies be adapted by different agencies without compromising financial stability? This paper develops an agent-based modeling framework that enables transit authorities to systematically explore cryptocurrency integration strategies. We simulate 1000 heterogeneous agents with varying risk tolerance, technological proficiency, and social influence susceptibility over 365 days, testing five policy regimes across a comprehensive scenario matrix comprising four risk-attitude compositions, four technology-adoption levels, four social-influence intensities, and three market conditions (bullish, neutral, bearish)—creating 192 distinct population-market configurations evaluated across all five policies with 15 independent replications per configuration (14,400 total simulation runs). The framework produces adoption outcomes ranging from near-zero to over 49% depending on scenario assumptions, with technology familiarity emerging as the dominant driver. The framework provides transit authorities with a practical tool for scenario-based planning: testing policy interventions, stress-testing financial stability under various market conditions, identifying potential vulnerabilities before deployment, and comparing alternative strategies across diverse demographic contexts. This simulation-based approach enables data-driven decision-making in the absence of real-world precedent, offering a structured methodology for evaluating cryptocurrency integration while managing financial stability risks.

]]> Agent-Based Analysis of Cryptocurrency Adoption in Transit Systems Mahdieh Allahviranloo doi: 10.3390/smartcities9080121 Smart Cities 2026-07-26 Smart Cities 2026-07-26 9 8 Article 121 10.3390/smartcities9080121 https://www.mdpi.com/2624-6511/9/8/121 Smart Cities, Vol. 9, Pages 120: ULSTM: Multi-Scale and Full-Level Temporal Consistency for Traffic Anomaly Detection https://www.mdpi.com/2624-6511/9/7/120 Urban traffic anomaly detection is essential for intelligent transportation systems, particularly in smart city environments where fast identification of abnormal events can improve road safety and traffic management. This work proposes a novel ULSTM-driven architecture that explicitly models temporal dependencies across consecutive traffic frames to achieve more stable and temporally coherent reconstructions. The proposed framework leverages sequential spatio-temporal representations to improve the distinction between normal traffic patterns and anomalous events. To further enhance reliability, we introduce a Hybrid Weighted Fusion strategy that synergistically combines structural, perceptual and pixel-wise metrics. The framework’s parameters are optimized using a Discrete Dirichlet Sampling approach, achieving a peak F1 Score of 70.28%. Evaluations were conducted on a manually curated traffic anomaly dataset with frame-level annotations. Experimental results demonstrate that the ULSTM framework significantly outperforms frame-independent generative models by suppressing high-frequency reconstruction noise, providing a robust solution for real-world smart city deployments. While highly effective in complex scenarios, the proposed framework is strictly applicable to highly dynamic traffic environments with active motion, as static background ensembles can degrade performance. 2026-07-22 Smart Cities, Vol. 9, Pages 120: ULSTM: Multi-Scale and Full-Level Temporal Consistency for Traffic Anomaly Detection

Smart Cities doi: 10.3390/smartcities9070120

Authors: Borja Pérez Mario Resino Jaime Godoy Abdulla Al-Kaff Fernando García

Urban traffic anomaly detection is essential for intelligent transportation systems, particularly in smart city environments where fast identification of abnormal events can improve road safety and traffic management. This work proposes a novel ULSTM-driven architecture that explicitly models temporal dependencies across consecutive traffic frames to achieve more stable and temporally coherent reconstructions. The proposed framework leverages sequential spatio-temporal representations to improve the distinction between normal traffic patterns and anomalous events. To further enhance reliability, we introduce a Hybrid Weighted Fusion strategy that synergistically combines structural, perceptual and pixel-wise metrics. The framework’s parameters are optimized using a Discrete Dirichlet Sampling approach, achieving a peak F1 Score of 70.28%. Evaluations were conducted on a manually curated traffic anomaly dataset with frame-level annotations. Experimental results demonstrate that the ULSTM framework significantly outperforms frame-independent generative models by suppressing high-frequency reconstruction noise, providing a robust solution for real-world smart city deployments. While highly effective in complex scenarios, the proposed framework is strictly applicable to highly dynamic traffic environments with active motion, as static background ensembles can degrade performance.

]]> ULSTM: Multi-Scale and Full-Level Temporal Consistency for Traffic Anomaly Detection Borja Pérez Mario Resino Jaime Godoy Abdulla Al-Kaff Fernando García doi: 10.3390/smartcities9070120 Smart Cities 2026-07-22 Smart Cities 2026-07-22 9 7 Article 120 10.3390/smartcities9070120 https://www.mdpi.com/2624-6511/9/7/120 Smart Cities, Vol. 9, Pages 119: Effective Job Accessibility: Bicycles/E-Bikes vs. Cars Within the Smart City and Countryside (A Digital Model of England and Wales) https://www.mdpi.com/2624-6511/9/7/119 Background: Despite a growing awareness of the obvious disadvantages of car travel for drivers (e.g., cost and health) and society (e.g., external costs and infrastructure maintenance), commuting by car to work is the prevailing mode of transport in the UK. Methods: A digital model of work and home locations in England and Wales using OSRM was created to compare the effective accessibility of e-bikes and cars for those working in an office five days a week. This accessibility metric is extended by the effective speed concept. The latter accounts for time spent travelling alongside the time spent working to offset commuting costs. Results: s-pedelecs offer, in various settings, the highest effective accessibility scores. Commuting by car is only advisable for individuals with a higher wage and time availability. If only the variable cost of the car commute is considered, then driving becomes the most expedient choice for many. Conclusions: Commuting by car is undoubtedly the fastest option for wealthy individuals. Whereas those less affluent in terms of time and money may opt for an e-bike, as commuting by car may not yield the commonly anticipated savings. 2026-07-12 Smart Cities, Vol. 9, Pages 119: Effective Job Accessibility: Bicycles/E-Bikes vs. Cars Within the Smart City and Countryside (A Digital Model of England and Wales)

Smart Cities doi: 10.3390/smartcities9070119

Authors: Maren Schnieder

Background: Despite a growing awareness of the obvious disadvantages of car travel for drivers (e.g., cost and health) and society (e.g., external costs and infrastructure maintenance), commuting by car to work is the prevailing mode of transport in the UK. Methods: A digital model of work and home locations in England and Wales using OSRM was created to compare the effective accessibility of e-bikes and cars for those working in an office five days a week. This accessibility metric is extended by the effective speed concept. The latter accounts for time spent travelling alongside the time spent working to offset commuting costs. Results: s-pedelecs offer, in various settings, the highest effective accessibility scores. Commuting by car is only advisable for individuals with a higher wage and time availability. If only the variable cost of the car commute is considered, then driving becomes the most expedient choice for many. Conclusions: Commuting by car is undoubtedly the fastest option for wealthy individuals. Whereas those less affluent in terms of time and money may opt for an e-bike, as commuting by car may not yield the commonly anticipated savings.

]]> Effective Job Accessibility: Bicycles/E-Bikes vs. Cars Within the Smart City and Countryside (A Digital Model of England and Wales) Maren Schnieder doi: 10.3390/smartcities9070119 Smart Cities 2026-07-12 Smart Cities 2026-07-12 9 7 Article 119 10.3390/smartcities9070119 https://www.mdpi.com/2624-6511/9/7/119 Smart Cities, Vol. 9, Pages 118: AI-Driven Sensing Technologies and Digital Twins for Firefighter Safety: Technologies, Challenges, and Future Directions https://www.mdpi.com/2624-6511/9/7/118 Firefighters operate in high-risk, rapidly evolving environments where exposure to extreme heat, toxic gases, and physiological stress significantly increases the likelihood of injury and fatality. This study systematically maps the emerging research landscape of real-time artificial intelligence (AI)-driven digital twins for environmental and physiological risk prediction in firefighting contexts. A combined bibliometric and qualitative content analysis was conducted using peer-reviewed literature retrieved from the Web of Science database (2010–2025). Bibliometric techniques were used to identify publication trends and thematic clusters, while content analysis examined the integration of sensing technologies, AI models, and digital twin architectures. The results reveal four dominant technological domains shaping the field: AI-enabled fire risk modeling, sensor data acquisition systems, IoT-based digital infrastructures, and predictive analytics for disaster simulation. Sensing technologies such as temperature, gas, particulate matter, thermal imaging, heart rate, and blood oxygen monitoring form the foundational data layer, while machine learning and deep learning models enable real-time hazard prediction and situational awareness. Digital twin architectures serve as the integration layer, fusing multi-source data and supporting simulation-based decision-making. Despite rapid advancements, key gaps persist, including limited integration of environmental and physiological data, insufficient predictive capabilities, a lack of standardized architectures, and minimal development of human-centered decision-support systems. This study provides a structured synthesis of current technologies and identifies future research directions toward integrated, explainable, and real-time digital twin systems to enhance firefighter safety and operational resilience. 2026-07-12 Smart Cities, Vol. 9, Pages 118: AI-Driven Sensing Technologies and Digital Twins for Firefighter Safety: Technologies, Challenges, and Future Directions

Smart Cities doi: 10.3390/smartcities9070118

Authors: Adedeji Afolabi Avdesh Mishra Elaheh Rahbar Noemi Mendoza

Firefighters operate in high-risk, rapidly evolving environments where exposure to extreme heat, toxic gases, and physiological stress significantly increases the likelihood of injury and fatality. This study systematically maps the emerging research landscape of real-time artificial intelligence (AI)-driven digital twins for environmental and physiological risk prediction in firefighting contexts. A combined bibliometric and qualitative content analysis was conducted using peer-reviewed literature retrieved from the Web of Science database (2010–2025). Bibliometric techniques were used to identify publication trends and thematic clusters, while content analysis examined the integration of sensing technologies, AI models, and digital twin architectures. The results reveal four dominant technological domains shaping the field: AI-enabled fire risk modeling, sensor data acquisition systems, IoT-based digital infrastructures, and predictive analytics for disaster simulation. Sensing technologies such as temperature, gas, particulate matter, thermal imaging, heart rate, and blood oxygen monitoring form the foundational data layer, while machine learning and deep learning models enable real-time hazard prediction and situational awareness. Digital twin architectures serve as the integration layer, fusing multi-source data and supporting simulation-based decision-making. Despite rapid advancements, key gaps persist, including limited integration of environmental and physiological data, insufficient predictive capabilities, a lack of standardized architectures, and minimal development of human-centered decision-support systems. This study provides a structured synthesis of current technologies and identifies future research directions toward integrated, explainable, and real-time digital twin systems to enhance firefighter safety and operational resilience.

]]> AI-Driven Sensing Technologies and Digital Twins for Firefighter Safety: Technologies, Challenges, and Future Directions Adedeji Afolabi Avdesh Mishra Elaheh Rahbar Noemi Mendoza doi: 10.3390/smartcities9070118 Smart Cities 2026-07-12 Smart Cities 2026-07-12 9 7 Review 118 10.3390/smartcities9070118 https://www.mdpi.com/2624-6511/9/7/118 Smart Cities, Vol. 9, Pages 117: A Self-Adaptive Framework for Sustainable Smart Cities https://www.mdpi.com/2624-6511/9/7/117 The transition from traditional siloed to intelligent cities allows for the deployment and management of information and communication technologies in the urban context to be driven by holistic sustainability requirements rather than technical ones such as feasibility and fragmented, siloed operational patterns. This work proposes a multi-dimensional decision-making framework to manage a smart city as an urban cognitive Cyber–Physical System (CPS) across environmental, economic, and social sustainability pillars, metrics and their trade-offs. A methodology based on Deep Reinforcement Learning (DRL), specifically adopting Deep Q-Networks (DQNs), is proposed to represent and assess sustainability pillar dependencies and their interplay. A case study on Low-Power Wide-Area Network planning, deployment and management in a Sicilian municipality has been developed to demonstrate the effectiveness of the proposed approach in dealing with the dynamics and non-linear dependencies of the sustainability pillars. 2026-07-10 Smart Cities, Vol. 9, Pages 117: A Self-Adaptive Framework for Sustainable Smart Cities

Smart Cities doi: 10.3390/smartcities9070117

Authors: Maurizio Giacobbe Salvatore Distefano

The transition from traditional siloed to intelligent cities allows for the deployment and management of information and communication technologies in the urban context to be driven by holistic sustainability requirements rather than technical ones such as feasibility and fragmented, siloed operational patterns. This work proposes a multi-dimensional decision-making framework to manage a smart city as an urban cognitive Cyber–Physical System (CPS) across environmental, economic, and social sustainability pillars, metrics and their trade-offs. A methodology based on Deep Reinforcement Learning (DRL), specifically adopting Deep Q-Networks (DQNs), is proposed to represent and assess sustainability pillar dependencies and their interplay. A case study on Low-Power Wide-Area Network planning, deployment and management in a Sicilian municipality has been developed to demonstrate the effectiveness of the proposed approach in dealing with the dynamics and non-linear dependencies of the sustainability pillars.

]]> A Self-Adaptive Framework for Sustainable Smart Cities Maurizio Giacobbe Salvatore Distefano doi: 10.3390/smartcities9070117 Smart Cities 2026-07-10 Smart Cities 2026-07-10 9 7 Article 117 10.3390/smartcities9070117 https://www.mdpi.com/2624-6511/9/7/117 Smart Cities, Vol. 9, Pages 116: Denoising Method for Pipeline Leakage Voiceprint in Utility Tunnel Using an Enhanced StarGAN https://www.mdpi.com/2624-6511/9/7/116 Leakage of water pipelines in urban underground utility tunnels poses a major threat to tunnel safety and operation; therefore, voiceprint recognition is adopted for real-time pipeline monitoring. Although utility tunnels are less affected by outdoor interference, multiple internal noises still degrade voiceprint recognition accuracy. To address this problem, this study proposes an enhanced StarGAN-based denoising method using a single network to handle multiple noise types. Unlike the original StarGAN-VC2 developed for voice conversion, the proposed model is specifically redesigned for leakage voiceprint denoising by integrating MFCC-based representation, a lightweight bottleneck, channel attention, residual feature preservation, and U-Net-style reconstruction. Experimental and engineering application results show that the denoised signals achieve improvements of 3–7 dB in SNR, 3–4 dB in PSNR, and 3–4 in SSR. The model also demonstrates strong generalization capability and plug-and-play applicability, enabling integration with conventional denoising and voiceprint recognition networks. These results indicate that the proposed method can effectively suppress diverse utility tunnel noises while preserving leakage-related voiceprint features. 2026-07-09 Smart Cities, Vol. 9, Pages 116: Denoising Method for Pipeline Leakage Voiceprint in Utility Tunnel Using an Enhanced StarGAN

Smart Cities doi: 10.3390/smartcities9070116

Authors: Qi-Wen Tian Yu-Fei Chen Shi-Wan Zhang Hui-Qing Lan Jie Gao

Leakage of water pipelines in urban underground utility tunnels poses a major threat to tunnel safety and operation; therefore, voiceprint recognition is adopted for real-time pipeline monitoring. Although utility tunnels are less affected by outdoor interference, multiple internal noises still degrade voiceprint recognition accuracy. To address this problem, this study proposes an enhanced StarGAN-based denoising method using a single network to handle multiple noise types. Unlike the original StarGAN-VC2 developed for voice conversion, the proposed model is specifically redesigned for leakage voiceprint denoising by integrating MFCC-based representation, a lightweight bottleneck, channel attention, residual feature preservation, and U-Net-style reconstruction. Experimental and engineering application results show that the denoised signals achieve improvements of 3–7 dB in SNR, 3–4 dB in PSNR, and 3–4 in SSR. The model also demonstrates strong generalization capability and plug-and-play applicability, enabling integration with conventional denoising and voiceprint recognition networks. These results indicate that the proposed method can effectively suppress diverse utility tunnel noises while preserving leakage-related voiceprint features.

]]> Denoising Method for Pipeline Leakage Voiceprint in Utility Tunnel Using an Enhanced StarGAN Qi-Wen Tian Yu-Fei Chen Shi-Wan Zhang Hui-Qing Lan Jie Gao doi: 10.3390/smartcities9070116 Smart Cities 2026-07-09 Smart Cities 2026-07-09 9 7 Article 116 10.3390/smartcities9070116 https://www.mdpi.com/2624-6511/9/7/116 Smart Cities, Vol. 9, Pages 115: When Fairness Backfires: A Chronoceptive Design Approach to Intelligent Transportation Systems https://www.mdpi.com/2624-6511/9/7/115 Intelligent transportation systems (ITSs) and traffic control promise substantial efficiency and safety improvements but frequently face public resistance and driver compliance issues. Many drivers perceive such control measures as unfair or unnecessary, despite measurable system-wide benefits. This study investigates how chronoception—the subjective perception of time—affects user acceptance of ITS control strategies and how signal design can be adapted to reduce perceived delays. We introduce a chronoceptive design framework that integrates insights from cognitive psychology into traffic-control design. Using ramp metering as a case study, we conduct virtual experience stated preference experiments with 101 participants, comparing standard and chronoceptive ramp metering designs featuring shorter signal cycles, three-phase lights, and countdown timers. The results show that chronoceptive signal designs significantly improve user acceptance (by up to 12%) and reduce perceived waiting times, despite identical or slightly longer objective travel times. These findings reveal a systematic bias between factual and perceived benefits and highlight the potential of chronoceptive design to enhance compliance and fairness perception. This study contributes a new human-centred design paradigm for traffic control that aligns objective performance with user perception and outlines how chronoception and perceived fairness can be operationalised in traffic control. The source code and survey data can be found open-source on GitHub. 2026-07-07 Smart Cities, Vol. 9, Pages 115: When Fairness Backfires: A Chronoceptive Design Approach to Intelligent Transportation Systems

Smart Cities doi: 10.3390/smartcities9070115

Authors: Kevin Riehl Linghang Sun Anastasios Kouvelas Michail A. Makridis

Intelligent transportation systems (ITSs) and traffic control promise substantial efficiency and safety improvements but frequently face public resistance and driver compliance issues. Many drivers perceive such control measures as unfair or unnecessary, despite measurable system-wide benefits. This study investigates how chronoception—the subjective perception of time—affects user acceptance of ITS control strategies and how signal design can be adapted to reduce perceived delays. We introduce a chronoceptive design framework that integrates insights from cognitive psychology into traffic-control design. Using ramp metering as a case study, we conduct virtual experience stated preference experiments with 101 participants, comparing standard and chronoceptive ramp metering designs featuring shorter signal cycles, three-phase lights, and countdown timers. The results show that chronoceptive signal designs significantly improve user acceptance (by up to 12%) and reduce perceived waiting times, despite identical or slightly longer objective travel times. These findings reveal a systematic bias between factual and perceived benefits and highlight the potential of chronoceptive design to enhance compliance and fairness perception. This study contributes a new human-centred design paradigm for traffic control that aligns objective performance with user perception and outlines how chronoception and perceived fairness can be operationalised in traffic control. The source code and survey data can be found open-source on GitHub.

]]> When Fairness Backfires: A Chronoceptive Design Approach to Intelligent Transportation Systems Kevin Riehl Linghang Sun Anastasios Kouvelas Michail A. Makridis doi: 10.3390/smartcities9070115 Smart Cities 2026-07-07 Smart Cities 2026-07-07 9 7 Article 115 10.3390/smartcities9070115 https://www.mdpi.com/2624-6511/9/7/115 Smart Cities, Vol. 9, Pages 114: Multimodal Generative AI for Construction-Site Management and Monitoring: A Field-Based Evaluation https://www.mdpi.com/2624-6511/9/7/114 Modern construction sites generate large volumes of visual, spatial, and operational data that can support data-driven project delivery, improved monitoring, and reliable decision-making within the smart-city built environment. However, construction management still relies heavily on human observation and manual interpretation, limiting the transformation of field data into structured information for sustainable urban infrastructure delivery. Multimodal generative artificial intelligence (GenAI) offers a promising approach for interpreting construction-site data, yet its performance under real site conditions remains insufficiently examined, particularly across tasks requiring different levels of visual recognition, contextual reasoning, and professional judgment. This paper presents a field-based evaluation of multimodal GenAI models using 1186 images collected from 17 active construction sites. The evaluation considered three widely available general-purpose multimodal GenAI assistants: Gemini, ChatGPT, and Microsoft Copilot. Four major construction management tasks were assessed: construction activity identification, progress tracking, execution defect detection, and safety hazard identification. The GenAI outputs were compared against ground-truth evaluations established by human experts. The results suggest that GenAI performs more reliably in descriptive and visually explicit tasks than in judgment-intensive tasks requiring engineering interpretation. Activity identification achieved the strongest performance, whereas execution defect detection was the most challenging. The findings indicate that GenAI can support visual site interpretation and improve construction management efficiency, while highlighting the need for human oversight and verification in smart-city infrastructure delivery. 2026-07-02 Smart Cities, Vol. 9, Pages 114: Multimodal Generative AI for Construction-Site Management and Monitoring: A Field-Based Evaluation

Smart Cities doi: 10.3390/smartcities9070114

Authors: Alon Urlainis Eran Haronian Amichai Mitelman

Modern construction sites generate large volumes of visual, spatial, and operational data that can support data-driven project delivery, improved monitoring, and reliable decision-making within the smart-city built environment. However, construction management still relies heavily on human observation and manual interpretation, limiting the transformation of field data into structured information for sustainable urban infrastructure delivery. Multimodal generative artificial intelligence (GenAI) offers a promising approach for interpreting construction-site data, yet its performance under real site conditions remains insufficiently examined, particularly across tasks requiring different levels of visual recognition, contextual reasoning, and professional judgment. This paper presents a field-based evaluation of multimodal GenAI models using 1186 images collected from 17 active construction sites. The evaluation considered three widely available general-purpose multimodal GenAI assistants: Gemini, ChatGPT, and Microsoft Copilot. Four major construction management tasks were assessed: construction activity identification, progress tracking, execution defect detection, and safety hazard identification. The GenAI outputs were compared against ground-truth evaluations established by human experts. The results suggest that GenAI performs more reliably in descriptive and visually explicit tasks than in judgment-intensive tasks requiring engineering interpretation. Activity identification achieved the strongest performance, whereas execution defect detection was the most challenging. The findings indicate that GenAI can support visual site interpretation and improve construction management efficiency, while highlighting the need for human oversight and verification in smart-city infrastructure delivery.

]]> Multimodal Generative AI for Construction-Site Management and Monitoring: A Field-Based Evaluation Alon Urlainis Eran Haronian Amichai Mitelman doi: 10.3390/smartcities9070114 Smart Cities 2026-07-02 Smart Cities 2026-07-02 9 7 Article 114 10.3390/smartcities9070114 https://www.mdpi.com/2624-6511/9/7/114 Smart Cities, Vol. 9, Pages 113: The Use of Graph Neural Networks in Rail Transport Planning https://www.mdpi.com/2624-6511/9/7/113 This work explores how graph theory and graph neural networks can support the strategic planning of rail network expansions using only publicly available city data, applied to the São Paulo Metropolitan Region. The methodology consolidates information from multiple public sources, develops a catchment-area formula to estimate potential passenger demand, applies Random Forest to identify the most relevant demographic features, and implements a GraphSAGE model that derives predictive capability from network topology together with socioeconomic features and origin–destination trips. The demand approximation was checked against observed station boardings, with predicted and observed rankings in agreement. The GraphSAGE model achieved an R2 of 0.874 ± 0.042 when predicting the proxy demand indicator, with minimal overfitting, outperforming the Random Forest baseline and achieving accuracy comparable to an XGBoost baseline while overfitting substantially less; this performance remained stable under spatial cross-validation. The model is computationally efficient and requires no rail-system-specific information beyond topology, making it suitable for the fast, low-cost comparison of expansion proposals rather than as a replacement for detailed transport demand models. It was used to evaluate eleven real projects and proposals for the São Paulo Metropolitan Region. Employment, residences, and destinations where people go to eat together represent about 65% of the model’s predictive capacity. 2026-07-01 Smart Cities, Vol. 9, Pages 113: The Use of Graph Neural Networks in Rail Transport Planning

Smart Cities doi: 10.3390/smartcities9070113

Authors: Rafaela Perrotti Zyngier Ivan Carlos Alcântara de Oliveira

This work explores how graph theory and graph neural networks can support the strategic planning of rail network expansions using only publicly available city data, applied to the São Paulo Metropolitan Region. The methodology consolidates information from multiple public sources, develops a catchment-area formula to estimate potential passenger demand, applies Random Forest to identify the most relevant demographic features, and implements a GraphSAGE model that derives predictive capability from network topology together with socioeconomic features and origin–destination trips. The demand approximation was checked against observed station boardings, with predicted and observed rankings in agreement. The GraphSAGE model achieved an R2 of 0.874 ± 0.042 when predicting the proxy demand indicator, with minimal overfitting, outperforming the Random Forest baseline and achieving accuracy comparable to an XGBoost baseline while overfitting substantially less; this performance remained stable under spatial cross-validation. The model is computationally efficient and requires no rail-system-specific information beyond topology, making it suitable for the fast, low-cost comparison of expansion proposals rather than as a replacement for detailed transport demand models. It was used to evaluate eleven real projects and proposals for the São Paulo Metropolitan Region. Employment, residences, and destinations where people go to eat together represent about 65% of the model’s predictive capacity.

]]> The Use of Graph Neural Networks in Rail Transport Planning Rafaela Perrotti Zyngier Ivan Carlos Alcântara de Oliveira doi: 10.3390/smartcities9070113 Smart Cities 2026-07-01 Smart Cities 2026-07-01 9 7 Article 113 10.3390/smartcities9070113 https://www.mdpi.com/2624-6511/9/7/113 Smart Cities, Vol. 9, Pages 112: Artificial Intelligence and BIM-Enabled Smart Construction Site Management: A Systematic Review of Site-Level Spatial Decision-Making and Site Layout Optimization-Related Applications for Sustainable Building Delivery https://www.mdpi.com/2624-6511/9/7/112 Artificial intelligence (AI), building information modeling (BIM), and digital twins are increasingly transforming construction sites into smart, data-driven environments that support safer, more efficient, and more sustainable building and urban infrastructure delivery. However, site-level spatial decision-making related to site layout optimization (SLO) remains constrained by fragmented data environments, limited interoperability, and weak integration between planning, monitoring, and adaptive decision-making. This study presents a systematic literature review of how AI, BIM, and enabling digital technologies are being applied to support smart construction site management, site-level spatial decision-making, and SLO-related applications. A Scopus-based search conducted in October 2025 identified 169 records, of which 63 studies were retained following PRISMA-guided screening. Because explicit SLO studies remain limited, the review synthesizes both directly relevant SLO studies and contextually relevant enabling studies with clear implications for smart and sustainable construction operations. The review combines bibliometric analysis, thematic content analysis, and cross-functional technology mapping to examine the intellectual structure of the field, the main operational domains addressed, and the dominant technological convergences supporting intelligent site decision-making. The findings show that the field is expanding rapidly but remains unevenly consolidated, with greater evidence concentration and practical readiness in real-time digital twin and spatial data management, automated monitoring, and proactive safety intelligence than in closed-loop logistics coordination and autonomous mobility. Across application domains, the dominant technology convergences combine machine learning and deep learning with multidimensional BIM, frequently extended through digital twins, sensors, cloud platforms, UAVs, simulation tools, and GIS-related infrastructures. The review further shows that the main barriers to deployment are not merely algorithmic, but also relate to interoperability, data quality, implementation complexity, human oversight, and limited field validation. Overall, this study provides a structured synthesis of evidence concentration, practical readiness, dominant patterns, and unresolved gaps of AI-BIM-enabled smart construction site management, and outlines directions for more interoperable, human-centered, and field-validated systems that support sustainable smart building and urban infrastructure delivery. 2026-06-30 Smart Cities, Vol. 9, Pages 112: Artificial Intelligence and BIM-Enabled Smart Construction Site Management: A Systematic Review of Site-Level Spatial Decision-Making and Site Layout Optimization-Related Applications for Sustainable Building Delivery

Smart Cities doi: 10.3390/smartcities9070112

Authors: Zahabiya Fakhruddin Vian Ahmed Zied Bahroun

Artificial intelligence (AI), building information modeling (BIM), and digital twins are increasingly transforming construction sites into smart, data-driven environments that support safer, more efficient, and more sustainable building and urban infrastructure delivery. However, site-level spatial decision-making related to site layout optimization (SLO) remains constrained by fragmented data environments, limited interoperability, and weak integration between planning, monitoring, and adaptive decision-making. This study presents a systematic literature review of how AI, BIM, and enabling digital technologies are being applied to support smart construction site management, site-level spatial decision-making, and SLO-related applications. A Scopus-based search conducted in October 2025 identified 169 records, of which 63 studies were retained following PRISMA-guided screening. Because explicit SLO studies remain limited, the review synthesizes both directly relevant SLO studies and contextually relevant enabling studies with clear implications for smart and sustainable construction operations. The review combines bibliometric analysis, thematic content analysis, and cross-functional technology mapping to examine the intellectual structure of the field, the main operational domains addressed, and the dominant technological convergences supporting intelligent site decision-making. The findings show that the field is expanding rapidly but remains unevenly consolidated, with greater evidence concentration and practical readiness in real-time digital twin and spatial data management, automated monitoring, and proactive safety intelligence than in closed-loop logistics coordination and autonomous mobility. Across application domains, the dominant technology convergences combine machine learning and deep learning with multidimensional BIM, frequently extended through digital twins, sensors, cloud platforms, UAVs, simulation tools, and GIS-related infrastructures. The review further shows that the main barriers to deployment are not merely algorithmic, but also relate to interoperability, data quality, implementation complexity, human oversight, and limited field validation. Overall, this study provides a structured synthesis of evidence concentration, practical readiness, dominant patterns, and unresolved gaps of AI-BIM-enabled smart construction site management, and outlines directions for more interoperable, human-centered, and field-validated systems that support sustainable smart building and urban infrastructure delivery.

]]> Artificial Intelligence and BIM-Enabled Smart Construction Site Management: A Systematic Review of Site-Level Spatial Decision-Making and Site Layout Optimization-Related Applications for Sustainable Building Delivery Zahabiya Fakhruddin Vian Ahmed Zied Bahroun doi: 10.3390/smartcities9070112 Smart Cities 2026-06-30 Smart Cities 2026-06-30 9 7 Review 112 10.3390/smartcities9070112 https://www.mdpi.com/2624-6511/9/7/112 Smart Cities, Vol. 9, Pages 111: A Rolling-Horizon Model Predictive Control Energy Management System for Shaping the Ports of the Future https://www.mdpi.com/2624-6511/9/7/111 Smart-port decarbonisation requires operations-research decision support under day-ahead uncertainty. We present a rolling-horizon Model Predictive Control Energy Management System, formulated as a Mixed-Integer Linear Program with five forecast streams, and benchmark it against a deterministic rule-based controller on an identical configuration. A full-year proof-of-concept at the Port of Ancona (8760 hourly steps over the 2024 Italian Day-Ahead Market, 6.5 MWp PV, 1.0 MWh BESS) combines realised 2024 market, photovoltaic and auxiliary-demand series with a post-AFIR projected cold-ironing demand—the dominant load—and is therefore an operational proof-of-concept rather than a fully metered baseline. The principal MPC outcome is structural: anticipatory dispatch raises the mean BESS state of charge from 13.6% to 46.0% and cuts residence at the minimum SoC from 81% to 6% of hours. The forecasting layer attains sub-7% sMAPE on cold-ironing-loaded demand and 9–18% on the remaining streams (seasonal MASE24 ≤ 0.74 on demand and price streams). At the relay-constrained 0.08 C pilot, the realised savings is 0.44% (€14,463 yr−1; 95% moving-block bootstrap CI [€12,842, €15,742]); benchmarked against an enhanced rule-based controller that is itself permitted price-threshold grid charging, the residual value of predictive optimisation is €5652 yr−1 (0.17%), with the remainder of the gap being the value of enabling grid charging. A C-rate sweep shows the savings doubling to 0.93% at 0.5 C, and a direct 20 MWh/±10 MW simulation yields a €0.57 M yr−1 gross arbitrage savings whose net value, after a realistic battery-degradation penalty, is substantially smaller. Controller-level operational CO2 rises marginally (+6.2 t, +0.13%), an effect distinct from—and dwarfed by—the system-level cold-ironing decarbonisation. The framework is reproducible in open-source Python (PuLP/HiGHS) from the actual data and is portable to other single-node smart city energy hubs. 2026-06-30 Smart Cities, Vol. 9, Pages 111: A Rolling-Horizon Model Predictive Control Energy Management System for Shaping the Ports of the Future

Smart Cities doi: 10.3390/smartcities9070111

Authors: Nikolaos Sifakis Avraam Kartalidis Dimitrios Cholidis Spyridoula Trakaki George Arampatzis

Smart-port decarbonisation requires operations-research decision support under day-ahead uncertainty. We present a rolling-horizon Model Predictive Control Energy Management System, formulated as a Mixed-Integer Linear Program with five forecast streams, and benchmark it against a deterministic rule-based controller on an identical configuration. A full-year proof-of-concept at the Port of Ancona (8760 hourly steps over the 2024 Italian Day-Ahead Market, 6.5 MWp PV, 1.0 MWh BESS) combines realised 2024 market, photovoltaic and auxiliary-demand series with a post-AFIR projected cold-ironing demand—the dominant load—and is therefore an operational proof-of-concept rather than a fully metered baseline. The principal MPC outcome is structural: anticipatory dispatch raises the mean BESS state of charge from 13.6% to 46.0% and cuts residence at the minimum SoC from 81% to 6% of hours. The forecasting layer attains sub-7% sMAPE on cold-ironing-loaded demand and 9–18% on the remaining streams (seasonal MASE24 ≤ 0.74 on demand and price streams). At the relay-constrained 0.08 C pilot, the realised savings is 0.44% (€14,463 yr−1; 95% moving-block bootstrap CI [€12,842, €15,742]); benchmarked against an enhanced rule-based controller that is itself permitted price-threshold grid charging, the residual value of predictive optimisation is €5652 yr−1 (0.17%), with the remainder of the gap being the value of enabling grid charging. A C-rate sweep shows the savings doubling to 0.93% at 0.5 C, and a direct 20 MWh/±10 MW simulation yields a €0.57 M yr−1 gross arbitrage savings whose net value, after a realistic battery-degradation penalty, is substantially smaller. Controller-level operational CO2 rises marginally (+6.2 t, +0.13%), an effect distinct from—and dwarfed by—the system-level cold-ironing decarbonisation. The framework is reproducible in open-source Python (PuLP/HiGHS) from the actual data and is portable to other single-node smart city energy hubs.

]]> A Rolling-Horizon Model Predictive Control Energy Management System for Shaping the Ports of the Future Nikolaos Sifakis Avraam Kartalidis Dimitrios Cholidis Spyridoula Trakaki George Arampatzis doi: 10.3390/smartcities9070111 Smart Cities 2026-06-30 Smart Cities 2026-06-30 9 7 Article 111 10.3390/smartcities9070111 https://www.mdpi.com/2624-6511/9/7/111 Smart Cities, Vol. 9, Pages 110: Physics-Guided Detection of Multiplicative Under-Registration in Smart Meter Time Series Under Smart-City Confounders https://www.mdpi.com/2624-6511/9/7/110 Smart-city advanced metering infrastructure enables utility-scale remote analytics, but some forms of under-registration closely resemble lawful changes in demand and are hard to model as anomalies. We study a narrow, physically motivated event family at the single-meter level, namely multiplicative under-registration with unknown onset (a shunt-like attack), in which recorded active energy is approximately scaled by a factor α<1 after a change-point while the daily-profile structure and spectral shape remain invariant. We formalize the problem and develop a physics-guided detector family based on weighted daily-profile regression (GLS) and its robust variant (RGLS), with quality-control filters, spectral-consistency checks, and an optional reactive-channel gate, designed to stay selective under confounders such as rooftop photovoltaics, electric-vehicle charging, and heat-pump onsets. On a device-disjoint Low Carbon London benchmark (487 households) the preferred GLS detector attains precision 0.915, recall 0.978, and F1=0.945 at α=0.10 while keeping the non-theft suspected rate near 1%; a cross-dataset check on Open Power System Data with real EV/PV/heat-pump overlays yields zero false alarms on all 72 cases, and Mendeley and WPuQ benchmarks add a second large family and a reactive-channel test. We compare against external baselines (classical change-point detection, Isolation Forest, autoencoder, LSTM, gradient boosting, and a supervised statistical pipeline) on the same protocol: generic anomaly detectors fail on this shape-preserving attack, and supervised models match the detector only in-distribution while, unlike it, failing to transfer to real lawful confounders. All metrics carry bootstrap confidence intervals, and a full reproducibility bundle accompanies the submission. 2026-06-30 Smart Cities, Vol. 9, Pages 110: Physics-Guided Detection of Multiplicative Under-Registration in Smart Meter Time Series Under Smart-City Confounders

Smart Cities doi: 10.3390/smartcities9070110

Authors: Sergey I. Nikolenko

Smart-city advanced metering infrastructure enables utility-scale remote analytics, but some forms of under-registration closely resemble lawful changes in demand and are hard to model as anomalies. We study a narrow, physically motivated event family at the single-meter level, namely multiplicative under-registration with unknown onset (a shunt-like attack), in which recorded active energy is approximately scaled by a factor α<1 after a change-point while the daily-profile structure and spectral shape remain invariant. We formalize the problem and develop a physics-guided detector family based on weighted daily-profile regression (GLS) and its robust variant (RGLS), with quality-control filters, spectral-consistency checks, and an optional reactive-channel gate, designed to stay selective under confounders such as rooftop photovoltaics, electric-vehicle charging, and heat-pump onsets. On a device-disjoint Low Carbon London benchmark (487 households) the preferred GLS detector attains precision 0.915, recall 0.978, and F1=0.945 at α=0.10 while keeping the non-theft suspected rate near 1%; a cross-dataset check on Open Power System Data with real EV/PV/heat-pump overlays yields zero false alarms on all 72 cases, and Mendeley and WPuQ benchmarks add a second large family and a reactive-channel test. We compare against external baselines (classical change-point detection, Isolation Forest, autoencoder, LSTM, gradient boosting, and a supervised statistical pipeline) on the same protocol: generic anomaly detectors fail on this shape-preserving attack, and supervised models match the detector only in-distribution while, unlike it, failing to transfer to real lawful confounders. All metrics carry bootstrap confidence intervals, and a full reproducibility bundle accompanies the submission.

]]> Physics-Guided Detection of Multiplicative Under-Registration in Smart Meter Time Series Under Smart-City Confounders Sergey I. Nikolenko doi: 10.3390/smartcities9070110 Smart Cities 2026-06-30 Smart Cities 2026-06-30 9 7 Article 110 10.3390/smartcities9070110 https://www.mdpi.com/2624-6511/9/7/110 Smart Cities, Vol. 9, Pages 109: Generative AI-Driven Digital Twin Architecture for Urban Mobility Simulation and Decision Support https://www.mdpi.com/2624-6511/9/7/109 Urban mobility planning in smart cities requires sophisticated simulation tools, yet their complexity often creates a technical barrier for non-expert stakeholders. This paper presents a novel architecture that integrates generative artificial intelligence with digital twin technology to create an accessible and decision-support prototype. The framework employs a conversational AI agent based on Gemini 2.5 Flash Lite to interpret natural language intentions and translate them into validated simulation parameters. A critical safety layer, built using Pydantic, ensures that the agent’s stochastic outputs adhere to strict technical schemas and predefined logical bounds before execution. The underlying digital twin, developed with SimPy, NetworkX, and OSMnx, features a multi-source data integration strategy that includes demographic density (INE), tourism activity (ISTAC), and high-resolution traffic statistics (TomTom) to calibrate vehicle behavior. The architecture was technically demonstrated through a Technology Readiness Level (TRL) 4 proof-of-concept in Las Palmas de Gran Canaria, simulating multimodal scenarios including buses, the future MetroGuagua (BRT), and pedestrian flows. Results demonstrate a 96% success rate in intent recognition and configuration mapping, with end-to-end execution times under 20 min for a 19 h simulated day. This study demonstrates that LLM-driven orchestration, coupled with automated data pipelines and a decoupled microservice architecture, can lower technical barriers to urban simulation, which could support broader participation in future smart city deployments. 2026-06-30 Smart Cities, Vol. 9, Pages 109: Generative AI-Driven Digital Twin Architecture for Urban Mobility Simulation and Decision Support

Smart Cities doi: 10.3390/smartcities9070109

Authors: Pablo Vicente-Martínez Emilio Soria-Olivas Adrián Chust-Ros María Ángeles García-Escrivà Edu William-Secin Manuel Sánchez-Montañés

Urban mobility planning in smart cities requires sophisticated simulation tools, yet their complexity often creates a technical barrier for non-expert stakeholders. This paper presents a novel architecture that integrates generative artificial intelligence with digital twin technology to create an accessible and decision-support prototype. The framework employs a conversational AI agent based on Gemini 2.5 Flash Lite to interpret natural language intentions and translate them into validated simulation parameters. A critical safety layer, built using Pydantic, ensures that the agent’s stochastic outputs adhere to strict technical schemas and predefined logical bounds before execution. The underlying digital twin, developed with SimPy, NetworkX, and OSMnx, features a multi-source data integration strategy that includes demographic density (INE), tourism activity (ISTAC), and high-resolution traffic statistics (TomTom) to calibrate vehicle behavior. The architecture was technically demonstrated through a Technology Readiness Level (TRL) 4 proof-of-concept in Las Palmas de Gran Canaria, simulating multimodal scenarios including buses, the future MetroGuagua (BRT), and pedestrian flows. Results demonstrate a 96% success rate in intent recognition and configuration mapping, with end-to-end execution times under 20 min for a 19 h simulated day. This study demonstrates that LLM-driven orchestration, coupled with automated data pipelines and a decoupled microservice architecture, can lower technical barriers to urban simulation, which could support broader participation in future smart city deployments.

]]> Generative AI-Driven Digital Twin Architecture for Urban Mobility Simulation and Decision Support Pablo Vicente-Martínez Emilio Soria-Olivas Adrián Chust-Ros María Ángeles García-Escrivà Edu William-Secin Manuel Sánchez-Montañés doi: 10.3390/smartcities9070109 Smart Cities 2026-06-30 Smart Cities 2026-06-30 9 7 Article 109 10.3390/smartcities9070109 https://www.mdpi.com/2624-6511/9/7/109 Smart Cities, Vol. 9, Pages 108: CalmMobility in the Smart City: From Techno-Solutionism to Human-Paced Mobility Transitions https://www.mdpi.com/2624-6511/9/7/108 Smart city mobility is increasingly governed by a techno-solutionist logic that prizes data, automation, and efficiency, often at the expense of public trust, social legitimacy, and lived experience. This article argues that the fate of a mobility transition appears to depend less on the sophistication of the technology than on the pace and posture of change. Building on the CalmMobility framework and on Weiser and Brown’s concept of calm technology, it develops the idea of calm smart mobility—a human-paced, options-first approach in which innovation enters everyday life gradually and with credible alternatives already in place, so that residents are not asked to continuously adapt. The framework’s three pillars (Comprehensiveness; Pacing–Sequencing–Inclusion; Future-Readiness) are mapped onto four recurring challenges of smart mobility (Policy Layering, Affective Mismatch, Governance Silos, and the Future-Readiness Gap) and then used as a descriptive analytical lens to characterize seven documented implementations across economic, spatial, mass-transit, service, and platform interventions and four world regions: the Stockholm congestion charge, the London ULEZ expansion, the Barcelona superblocks, Bogotá’s TransMilenio bus rapid transit and Ciclovía, Seoul’s Cheonggyecheon restoration and bus reform, Helsinki’s Whim Mobility-as-a-Service, and Sidewalk Toronto. Presented through a comparison table, a positioning map, and adoption trajectories rather than rankings, the characterization suggests that the provision of alternatives, the sequencing and pace of change, and the genuineness of co-creation are more closely associated with smooth adoption than the type of instrument deployed. The article is conceptual and framework-building. The cases illustrate and probe the framework instead of validating it, and a testable central hypothesis is specified for future empirical work. Calm smart mobility is offered as a transferable, citizen-centred logic for guiding smart city mobility transitions at a human pace. 2026-06-30 Smart Cities, Vol. 9, Pages 108: CalmMobility in the Smart City: From Techno-Solutionism to Human-Paced Mobility Transitions

Smart Cities doi: 10.3390/smartcities9070108

Authors: Katarzyna Turoń

Smart city mobility is increasingly governed by a techno-solutionist logic that prizes data, automation, and efficiency, often at the expense of public trust, social legitimacy, and lived experience. This article argues that the fate of a mobility transition appears to depend less on the sophistication of the technology than on the pace and posture of change. Building on the CalmMobility framework and on Weiser and Brown’s concept of calm technology, it develops the idea of calm smart mobility—a human-paced, options-first approach in which innovation enters everyday life gradually and with credible alternatives already in place, so that residents are not asked to continuously adapt. The framework’s three pillars (Comprehensiveness; Pacing–Sequencing–Inclusion; Future-Readiness) are mapped onto four recurring challenges of smart mobility (Policy Layering, Affective Mismatch, Governance Silos, and the Future-Readiness Gap) and then used as a descriptive analytical lens to characterize seven documented implementations across economic, spatial, mass-transit, service, and platform interventions and four world regions: the Stockholm congestion charge, the London ULEZ expansion, the Barcelona superblocks, Bogotá’s TransMilenio bus rapid transit and Ciclovía, Seoul’s Cheonggyecheon restoration and bus reform, Helsinki’s Whim Mobility-as-a-Service, and Sidewalk Toronto. Presented through a comparison table, a positioning map, and adoption trajectories rather than rankings, the characterization suggests that the provision of alternatives, the sequencing and pace of change, and the genuineness of co-creation are more closely associated with smooth adoption than the type of instrument deployed. The article is conceptual and framework-building. The cases illustrate and probe the framework instead of validating it, and a testable central hypothesis is specified for future empirical work. Calm smart mobility is offered as a transferable, citizen-centred logic for guiding smart city mobility transitions at a human pace.

]]> CalmMobility in the Smart City: From Techno-Solutionism to Human-Paced Mobility Transitions Katarzyna Turoń doi: 10.3390/smartcities9070108 Smart Cities 2026-06-30 Smart Cities 2026-06-30 9 7 Article 108 10.3390/smartcities9070108 https://www.mdpi.com/2624-6511/9/7/108 Smart Cities, Vol. 9, Pages 107: Monitoring Urban Land Use Intensity with Remote Sensing and Urban Traits: A Review https://www.mdpi.com/2624-6511/9/7/107 Urban land use intensity (U-LUI) is a widely used term for describing urban development processes, yet its conceptualisation and measurement remain inconsistent. Existing approaches focus on isolated dimensions, such as structural density, functional activity, and socio-economic indicators, resulting in limited comparability and weak integration across scales and data sources. This paper reviews and synthesises current approaches to U-LUI with a focus on remote sensing (RS), in situ data and emerging urban data sources. It analyses definitions, related concepts of urban intensity and existing monitoring frameworks at national, European and global levels, and compares methodological approaches for observing U-LUI. Based on this synthesis, U-LUI is defined as a continuous, multidimensional and spatio-temporally dynamic property of urban systems that reflects the intensity of anthropogenic use. To operationalise this concept, the paper develops an integrative, trait-based framework comprising six indicator families: traits, genesis, structure, taxonomy, function and socio-economics. The proposed framework is illustrated and supported through the synthesis of existing RS approaches, urban monitoring concepts and representative examples from the literature, demonstrating its potential for consistent and scalable U-LUI assessment. These dimensions link physically observable characteristics with functional and contextual aspects of urban systems and provide a basis for more consistent quantification and comparison. The results highlight key challenges for U-LUI monitoring, including limited conceptual harmonisation, incomplete integration of dimensions and the need for improved data integration. The proposed framework supports more coherent and scalable assessments of U-LUI in research, monitoring and planning contexts. 2026-06-28 Smart Cities, Vol. 9, Pages 107: Monitoring Urban Land Use Intensity with Remote Sensing and Urban Traits: A Review

Smart Cities doi: 10.3390/smartcities9070107

Authors: Angela Lausch Jan Bumberger Xinyu Dong Dagmar Haase András Jung Marion Pause Peter Selsam Thilo Wellmann Thomas Trabert Ellen Banzhaf

Urban land use intensity (U-LUI) is a widely used term for describing urban development processes, yet its conceptualisation and measurement remain inconsistent. Existing approaches focus on isolated dimensions, such as structural density, functional activity, and socio-economic indicators, resulting in limited comparability and weak integration across scales and data sources. This paper reviews and synthesises current approaches to U-LUI with a focus on remote sensing (RS), in situ data and emerging urban data sources. It analyses definitions, related concepts of urban intensity and existing monitoring frameworks at national, European and global levels, and compares methodological approaches for observing U-LUI. Based on this synthesis, U-LUI is defined as a continuous, multidimensional and spatio-temporally dynamic property of urban systems that reflects the intensity of anthropogenic use. To operationalise this concept, the paper develops an integrative, trait-based framework comprising six indicator families: traits, genesis, structure, taxonomy, function and socio-economics. The proposed framework is illustrated and supported through the synthesis of existing RS approaches, urban monitoring concepts and representative examples from the literature, demonstrating its potential for consistent and scalable U-LUI assessment. These dimensions link physically observable characteristics with functional and contextual aspects of urban systems and provide a basis for more consistent quantification and comparison. The results highlight key challenges for U-LUI monitoring, including limited conceptual harmonisation, incomplete integration of dimensions and the need for improved data integration. The proposed framework supports more coherent and scalable assessments of U-LUI in research, monitoring and planning contexts.

]]> Monitoring Urban Land Use Intensity with Remote Sensing and Urban Traits: A Review Angela Lausch Jan Bumberger Xinyu Dong Dagmar Haase András Jung Marion Pause Peter Selsam Thilo Wellmann Thomas Trabert Ellen Banzhaf doi: 10.3390/smartcities9070107 Smart Cities 2026-06-28 Smart Cities 2026-06-28 9 7 Review 107 10.3390/smartcities9070107 https://www.mdpi.com/2624-6511/9/7/107 Smart Cities, Vol. 9, Pages 106: FedAgent-Chain: A Secure Federated and Agentic AI Framework for Multilingual Disability-Inclusive Employment in AI Cities https://www.mdpi.com/2624-6511/9/7/106 Artificial intelligence is reshaping employment in smart cities, yet centralized hiring platforms can deepen exclusion for persons with disabilities through privacy risk, biased models, weak multilingual support, and limited accommodation awareness. Because disability-related records are highly sensitive, no single institution holds enough representative data to train fair models, and centralizing such data is rarely permissible across borders. We propose FedAgent-Chain, a framework that integrates federated learning, blockchain-based auditability, multilingual processing, rule-based agentic services, and human-in-the-loop governance, extended with an education-to-employment module that builds individualized, accessible job-readiness pathways. Institutions across Saudi Arabia, the United States, China, and Europe train shared models without exchanging raw data. In a prototype evaluation on synthetic records over five seeds, the framework reached a mean F1 of 0.7207 (95% CI: [0.6506, 0.7909]), comparable to a centralized logistic-regression baseline while preserving data locality, with a formal (ε=3.2,δ=10−5) differential-privacy guarantee after 20 rounds. Multi-dimensional fairness regularization lowered disability-category and work-mode disparity by 32.3% and 40.3% relative to local-only training. We report the fairness behavior transparently, including a case where the penalty does not outperform standard FedAvg on disability-category disparity, and we position cross-institutional integration with accountable governance, rather than raw metric superiority, as the central contribution. 2026-06-26 Smart Cities, Vol. 9, Pages 106: FedAgent-Chain: A Secure Federated and Agentic AI Framework for Multilingual Disability-Inclusive Employment in AI Cities

Smart Cities doi: 10.3390/smartcities9070106

Authors: Toqeer Ali Syed Muhammad Shoaib Siddiqui Ali Akarma Antonio Formisano

Artificial intelligence is reshaping employment in smart cities, yet centralized hiring platforms can deepen exclusion for persons with disabilities through privacy risk, biased models, weak multilingual support, and limited accommodation awareness. Because disability-related records are highly sensitive, no single institution holds enough representative data to train fair models, and centralizing such data is rarely permissible across borders. We propose FedAgent-Chain, a framework that integrates federated learning, blockchain-based auditability, multilingual processing, rule-based agentic services, and human-in-the-loop governance, extended with an education-to-employment module that builds individualized, accessible job-readiness pathways. Institutions across Saudi Arabia, the United States, China, and Europe train shared models without exchanging raw data. In a prototype evaluation on synthetic records over five seeds, the framework reached a mean F1 of 0.7207 (95% CI: [0.6506, 0.7909]), comparable to a centralized logistic-regression baseline while preserving data locality, with a formal (ε=3.2,δ=10−5) differential-privacy guarantee after 20 rounds. Multi-dimensional fairness regularization lowered disability-category and work-mode disparity by 32.3% and 40.3% relative to local-only training. We report the fairness behavior transparently, including a case where the penalty does not outperform standard FedAvg on disability-category disparity, and we position cross-institutional integration with accountable governance, rather than raw metric superiority, as the central contribution.

]]> FedAgent-Chain: A Secure Federated and Agentic AI Framework for Multilingual Disability-Inclusive Employment in AI Cities Toqeer Ali Syed Muhammad Shoaib Siddiqui Ali Akarma Antonio Formisano doi: 10.3390/smartcities9070106 Smart Cities 2026-06-26 Smart Cities 2026-06-26 9 7 Article 106 10.3390/smartcities9070106 https://www.mdpi.com/2624-6511/9/7/106 Smart Cities, Vol. 9, Pages 105: Experimental Verification and Implementation Feasibility Analysis of Remote Smart Meter Error Monitoring System in Smart Cities https://www.mdpi.com/2624-6511/9/6/105 Smart energy meters are widely deployed in modern distribution networks, extending their role beyond revenue billing to real-time monitoring and data-driven smart city applications. However, conventional legal metrology frameworks rely on periodic recalibration and are not intended for the detection of accuracy drift or unexpected malfunctions between scheduled inspections. In scientific publications, various techniques for remote smart meters’ error surveillance are presented, but experimental verification on real distribution network data remains limited. The objective of this study is to experimentally verify two previously proposed power event-driven methods for remote estimation of active power measurement error in individual consumer meters, using a feeder-level sum meter as a reference instrument. One-second resolution electrical readings were collected from a real low-voltage distribution branch using ESP32-based local adapters communicating via MQTT over Wi-Fi, with SNTP-based clock synchronization for power event correlation. Under optimized detection parameters, the linear regression method achieved 0.20% RMSE and 0.75% maximum absolute error, and the neural network method 0.09% RMSE and 0.31%, confirming suitability for Class 1 m accuracy surveillance. Feasibility analysis of three MQTT-based deployment scenarios demonstrates that binary encoding limits local adapter buffers to 2.8 kB and worst-case daily channel demand to 2000 kB, confirming the practical viability of the proposed architecture. 2026-06-20 Smart Cities, Vol. 9, Pages 105: Experimental Verification and Implementation Feasibility Analysis of Remote Smart Meter Error Monitoring System in Smart Cities

Smart Cities doi: 10.3390/smartcities9060105

Authors: Julius Šaltanis Marius Saunoris Robertas Lukočius Vytautas Daunoras Kasparas Zulonas Stefano Rinaldi Žilvinas Nakutis

Smart energy meters are widely deployed in modern distribution networks, extending their role beyond revenue billing to real-time monitoring and data-driven smart city applications. However, conventional legal metrology frameworks rely on periodic recalibration and are not intended for the detection of accuracy drift or unexpected malfunctions between scheduled inspections. In scientific publications, various techniques for remote smart meters’ error surveillance are presented, but experimental verification on real distribution network data remains limited. The objective of this study is to experimentally verify two previously proposed power event-driven methods for remote estimation of active power measurement error in individual consumer meters, using a feeder-level sum meter as a reference instrument. One-second resolution electrical readings were collected from a real low-voltage distribution branch using ESP32-based local adapters communicating via MQTT over Wi-Fi, with SNTP-based clock synchronization for power event correlation. Under optimized detection parameters, the linear regression method achieved 0.20% RMSE and 0.75% maximum absolute error, and the neural network method 0.09% RMSE and 0.31%, confirming suitability for Class 1 m accuracy surveillance. Feasibility analysis of three MQTT-based deployment scenarios demonstrates that binary encoding limits local adapter buffers to 2.8 kB and worst-case daily channel demand to 2000 kB, confirming the practical viability of the proposed architecture.

]]> Experimental Verification and Implementation Feasibility Analysis of Remote Smart Meter Error Monitoring System in Smart Cities Julius Šaltanis Marius Saunoris Robertas Lukočius Vytautas Daunoras Kasparas Zulonas Stefano Rinaldi Žilvinas Nakutis doi: 10.3390/smartcities9060105 Smart Cities 2026-06-20 Smart Cities 2026-06-20 9 6 Article 105 10.3390/smartcities9060105 https://www.mdpi.com/2624-6511/9/6/105 Smart Cities, Vol. 9, Pages 104: Feature-Engineered Daytime Hourly Solar Irradiance Forecasting for Smart Urban Energy Systems Across Nine Stations Using Deep Learning and Statistical Models https://www.mdpi.com/2624-6511/9/6/104 Accurate solar irradiance forecasting is important for efficient planning of solar energy systems, renewable energy integration, and data-driven energy management in smart cities. This becomes more essential in regions with limited measured data availability and varying climatic conditions, where reliable forecasting can support urban energy planning and smart grid operation. Pakistan faces a scarcity of available solar data and has varying climatic conditions, which makes it ideal for such a study. This study utilizes nine geographically diverse stations to develop a benchmark framework for direct one-step-ahead hourly solar irradiance forecasting. The dataset was subjected to data preprocessing, feature engineering, and multi-model evaluation. A staged approach was adopted for feature selection, starting from a base model comprising three input variables: extraterrestrial radiation, solar zenith angle, and relative humidity. Features were added in an incremental order, which resulted in an optimized four-variable input set through the addition of a lagged clearness index to the base model. The forecasting models evaluated in this study, using these input variables, were ANN, NAR, NARX, LSTM, GRU, SARIMA, and Prophet. Deep learning models outperformed the other considered approaches, with LSTM showing the best overall benchmark performance with an average RMSE of 92.93 W/m2, MAE of 66.56 W/m2, and R-Squared of 0.872. The performance trends were broadly consistent across the evaluated stations, indicating stable behaviour within the adopted dataset and experimental setup. The study shows that a compact and physically interpretable input feature set, used with recurrent deep learning models, provides an effective solution for hourly solar irradiance forecasting, especially in locations with varying climatic conditions. The proposed benchmark can support smart city applications related to distributed solar generation, energy-aware urban planning, and intelligent operation of renewable-rich power systems. 2026-06-20 Smart Cities, Vol. 9, Pages 104: Feature-Engineered Daytime Hourly Solar Irradiance Forecasting for Smart Urban Energy Systems Across Nine Stations Using Deep Learning and Statistical Models

Smart Cities doi: 10.3390/smartcities9060104

Authors: Ali Hadi Md Fazle Hasan Shiblee Paraskevas Koukaras

Accurate solar irradiance forecasting is important for efficient planning of solar energy systems, renewable energy integration, and data-driven energy management in smart cities. This becomes more essential in regions with limited measured data availability and varying climatic conditions, where reliable forecasting can support urban energy planning and smart grid operation. Pakistan faces a scarcity of available solar data and has varying climatic conditions, which makes it ideal for such a study. This study utilizes nine geographically diverse stations to develop a benchmark framework for direct one-step-ahead hourly solar irradiance forecasting. The dataset was subjected to data preprocessing, feature engineering, and multi-model evaluation. A staged approach was adopted for feature selection, starting from a base model comprising three input variables: extraterrestrial radiation, solar zenith angle, and relative humidity. Features were added in an incremental order, which resulted in an optimized four-variable input set through the addition of a lagged clearness index to the base model. The forecasting models evaluated in this study, using these input variables, were ANN, NAR, NARX, LSTM, GRU, SARIMA, and Prophet. Deep learning models outperformed the other considered approaches, with LSTM showing the best overall benchmark performance with an average RMSE of 92.93 W/m2, MAE of 66.56 W/m2, and R-Squared of 0.872. The performance trends were broadly consistent across the evaluated stations, indicating stable behaviour within the adopted dataset and experimental setup. The study shows that a compact and physically interpretable input feature set, used with recurrent deep learning models, provides an effective solution for hourly solar irradiance forecasting, especially in locations with varying climatic conditions. The proposed benchmark can support smart city applications related to distributed solar generation, energy-aware urban planning, and intelligent operation of renewable-rich power systems.

]]> Feature-Engineered Daytime Hourly Solar Irradiance Forecasting for Smart Urban Energy Systems Across Nine Stations Using Deep Learning and Statistical Models Ali Hadi Md Fazle Hasan Shiblee Paraskevas Koukaras doi: 10.3390/smartcities9060104 Smart Cities 2026-06-20 Smart Cities 2026-06-20 9 6 Article 104 10.3390/smartcities9060104 https://www.mdpi.com/2624-6511/9/6/104 Smart Cities, Vol. 9, Pages 103: Preference-Aware Multimodal Journey Planner: An Optimization Approach for Smart Mobility https://www.mdpi.com/2624-6511/9/6/103 This paper examines the role of Multimodal Journey Planners (MJPs) as a link between user-oriented personalization and the broader societal goals of sustainable urban mobility. In smart cities, MJPs may serve as digital decision-support tools that connect individual mobility choices with broader sustainability objectives. Although contemporary journey planners increasingly display multiple criteria, such as travel time, cost, CO2 emissions, and number of transfers, they still generally rely on predefined and non-personalized criterion weights and rarely infer travellers’ actual preferences from observed choices. The paper therefore proposes a transparent methodological proof-of-concept that combines multicriteria decision-making and inverse optimization to discover individual preference weights and enable personalized, preference-aware planning of multimodal routes. The Weighted Sum Method (WSM) is adopted as the basic ranking framework, and the proposed approach is evaluated within a controlled methodological testbed based on multimodal journey scenarios in Vienna. The results indicate that, within the available methodological testbed, the preference-discovery-based model achieved closer in-sample agreement with user-provided route evaluations than the model based on explicitly rated criteria. This was observed in the ranking-agreement analysis, where a more favourable penalty-point ratio was obtained in 19/21 cases (90.5%) and in the numerical error comparison, where lower in-sample reconstruction errors were obtained for 18/21 users (85.71%) across all scenarios. The paper further considers the tension between individual and system-level goals, as well as a conceptual extension toward system-aware re-ranking of alternatives. Within the broader framework of smart mobility, the importance of interoperability and open data is also recognized, with National Access Points (NAPs) for multimodal travel information potentially representing an important precondition for the development of advanced and transparent MJP solutions. 2026-06-19 Smart Cities, Vol. 9, Pages 103: Preference-Aware Multimodal Journey Planner: An Optimization Approach for Smart Mobility

Smart Cities doi: 10.3390/smartcities9060103

Authors: Bia Mandžuka Krešimir Vidović Marko Ševrović Jasmin Ćelić

This paper examines the role of Multimodal Journey Planners (MJPs) as a link between user-oriented personalization and the broader societal goals of sustainable urban mobility. In smart cities, MJPs may serve as digital decision-support tools that connect individual mobility choices with broader sustainability objectives. Although contemporary journey planners increasingly display multiple criteria, such as travel time, cost, CO2 emissions, and number of transfers, they still generally rely on predefined and non-personalized criterion weights and rarely infer travellers’ actual preferences from observed choices. The paper therefore proposes a transparent methodological proof-of-concept that combines multicriteria decision-making and inverse optimization to discover individual preference weights and enable personalized, preference-aware planning of multimodal routes. The Weighted Sum Method (WSM) is adopted as the basic ranking framework, and the proposed approach is evaluated within a controlled methodological testbed based on multimodal journey scenarios in Vienna. The results indicate that, within the available methodological testbed, the preference-discovery-based model achieved closer in-sample agreement with user-provided route evaluations than the model based on explicitly rated criteria. This was observed in the ranking-agreement analysis, where a more favourable penalty-point ratio was obtained in 19/21 cases (90.5%) and in the numerical error comparison, where lower in-sample reconstruction errors were obtained for 18/21 users (85.71%) across all scenarios. The paper further considers the tension between individual and system-level goals, as well as a conceptual extension toward system-aware re-ranking of alternatives. Within the broader framework of smart mobility, the importance of interoperability and open data is also recognized, with National Access Points (NAPs) for multimodal travel information potentially representing an important precondition for the development of advanced and transparent MJP solutions.

]]> Preference-Aware Multimodal Journey Planner: An Optimization Approach for Smart Mobility Bia Mandžuka Krešimir Vidović Marko Ševrović Jasmin Ćelić doi: 10.3390/smartcities9060103 Smart Cities 2026-06-19 Smart Cities 2026-06-19 9 6 Article 103 10.3390/smartcities9060103 https://www.mdpi.com/2624-6511/9/6/103 Smart Cities, Vol. 9, Pages 102: Federated AI-Driven Urban Energy Resilience Framework for Smart City Critical Infrastructure Restoration https://www.mdpi.com/2624-6511/9/6/102 Modern smart cities increasingly depend on resilient and intelligent energy infrastructures to maintain critical urban services during large-scale disturbances and multi-fault conditions. Conventional restoration approaches are often limited by centralized operation, delayed response, and inadequate coordination of distributed energy resources (DERs) under emergency conditions. To address these challenges, this paper proposes a Federated AI-Driven Urban Energy Resilience Framework for Smart City Critical Infrastructure Restoration using Virtual Power Plant (VPP) coordination, blockchain-enabled peer-to-peer (P2P) energy trading, and intelligent distributed energy management. The proposed framework is validated on the IEEE 118-bus radial distribution system under severe dual-fault outage conditions, representing urban disaster-induced infrastructure interruptions. Critical urban service zones, including healthcare support systems, emergency loads, smart residential sectors, and EV charging corridors, are considered during the restoration process. The Seagull Optimization Algorithm (SOA) is employed to optimize DER dispatch and improve restoration performance under operational constraints. A progressive restoration strategy comprising conventional outage conditions, VPP-assisted restoration, blockchain-enabled decentralized energy trading, and AI-driven coordinated restoration is analyzed. Simulation results demonstrate that the proposed framework significantly enhances urban energy resilience by increasing load restoration from 55.05% to 94.20%, reducing Energy Not Supplied (ENS), improving voltage stability, and lowering interruption-related economic losses. The minimum bus voltage improves to 0.965 p.u. under the proposed coordinated restoration strategy. The results show that coordinated VPP operation and blockchain-based energy sharing can support reliable restoration of critical urban infrastructure during major outage conditions. The results indicate that integrating AI-assisted VPP coordination with secure decentralized energy trading can effectively support smart city critical infrastructure continuity during extreme outage conditions. The proposed framework provides a scalable and resilient solution for future intelligent urban energy systems and disaster-resilient smart city applications. 2026-06-17 Smart Cities, Vol. 9, Pages 102: Federated AI-Driven Urban Energy Resilience Framework for Smart City Critical Infrastructure Restoration

Smart Cities doi: 10.3390/smartcities9060102

Authors: Devabalaji Kaliaperumal Rukmani Joyal Isac S.

Modern smart cities increasingly depend on resilient and intelligent energy infrastructures to maintain critical urban services during large-scale disturbances and multi-fault conditions. Conventional restoration approaches are often limited by centralized operation, delayed response, and inadequate coordination of distributed energy resources (DERs) under emergency conditions. To address these challenges, this paper proposes a Federated AI-Driven Urban Energy Resilience Framework for Smart City Critical Infrastructure Restoration using Virtual Power Plant (VPP) coordination, blockchain-enabled peer-to-peer (P2P) energy trading, and intelligent distributed energy management. The proposed framework is validated on the IEEE 118-bus radial distribution system under severe dual-fault outage conditions, representing urban disaster-induced infrastructure interruptions. Critical urban service zones, including healthcare support systems, emergency loads, smart residential sectors, and EV charging corridors, are considered during the restoration process. The Seagull Optimization Algorithm (SOA) is employed to optimize DER dispatch and improve restoration performance under operational constraints. A progressive restoration strategy comprising conventional outage conditions, VPP-assisted restoration, blockchain-enabled decentralized energy trading, and AI-driven coordinated restoration is analyzed. Simulation results demonstrate that the proposed framework significantly enhances urban energy resilience by increasing load restoration from 55.05% to 94.20%, reducing Energy Not Supplied (ENS), improving voltage stability, and lowering interruption-related economic losses. The minimum bus voltage improves to 0.965 p.u. under the proposed coordinated restoration strategy. The results show that coordinated VPP operation and blockchain-based energy sharing can support reliable restoration of critical urban infrastructure during major outage conditions. The results indicate that integrating AI-assisted VPP coordination with secure decentralized energy trading can effectively support smart city critical infrastructure continuity during extreme outage conditions. The proposed framework provides a scalable and resilient solution for future intelligent urban energy systems and disaster-resilient smart city applications.

]]> Federated AI-Driven Urban Energy Resilience Framework for Smart City Critical Infrastructure Restoration Devabalaji Kaliaperumal Rukmani Joyal Isac S. doi: 10.3390/smartcities9060102 Smart Cities 2026-06-17 Smart Cities 2026-06-17 9 6 Article 102 10.3390/smartcities9060102 https://www.mdpi.com/2624-6511/9/6/102 Smart Cities, Vol. 9, Pages 101: The Mobility Oracle: A Framework for Approximating Human Mobility https://www.mdpi.com/2624-6511/9/6/101 Urban mobility modeling plays a critical role in understanding transport infrastructure and improving its efficiency and sustainability. While existing tools are effective for modeling, they typically require extensive data acquisition, such as surveys, questionnaires, or tracking, as well as domain knowledge for calibration. We propose the Mobility Oracle, a framework that can algorithmically approximate urban mobility by incorporating human preferences in the routing process. The framework relies on open-source data and generates synthetic datasets for further analysis. It can be adapted to different contexts as it is reproducible, modular, and flexible. Both the theoretical components and the practical implementation are presented, along with a case study that illustrates the framework’s potential applications. Validation is carried out for Vienna (Austria) and Munich (Germany), comparing our approach against the official city-wide modal splits and a smaller tracked dataset within one of the cities. The resulting mode shares show an average difference of 4.7% at the city scale and a maximum of 1.9% for the tracked sample. These results demonstrate that the Mobility Oracle can be a useful tool to approximate human mobility. City planners and decision-makers can use it to systematically test and evaluate alternative planning scenarios across different urban contexts. 2026-06-15 Smart Cities, Vol. 9, Pages 101: The Mobility Oracle: A Framework for Approximating Human Mobility

Smart Cities doi: 10.3390/smartcities9060101

Authors: Ioanna Gogousou Manuela Canestrini Negar Alinaghi Dimitrios Michail Ioannis Giannopoulos

Urban mobility modeling plays a critical role in understanding transport infrastructure and improving its efficiency and sustainability. While existing tools are effective for modeling, they typically require extensive data acquisition, such as surveys, questionnaires, or tracking, as well as domain knowledge for calibration. We propose the Mobility Oracle, a framework that can algorithmically approximate urban mobility by incorporating human preferences in the routing process. The framework relies on open-source data and generates synthetic datasets for further analysis. It can be adapted to different contexts as it is reproducible, modular, and flexible. Both the theoretical components and the practical implementation are presented, along with a case study that illustrates the framework’s potential applications. Validation is carried out for Vienna (Austria) and Munich (Germany), comparing our approach against the official city-wide modal splits and a smaller tracked dataset within one of the cities. The resulting mode shares show an average difference of 4.7% at the city scale and a maximum of 1.9% for the tracked sample. These results demonstrate that the Mobility Oracle can be a useful tool to approximate human mobility. City planners and decision-makers can use it to systematically test and evaluate alternative planning scenarios across different urban contexts.

]]> The Mobility Oracle: A Framework for Approximating Human Mobility Ioanna Gogousou Manuela Canestrini Negar Alinaghi Dimitrios Michail Ioannis Giannopoulos doi: 10.3390/smartcities9060101 Smart Cities 2026-06-15 Smart Cities 2026-06-15 9 6 Article 101 10.3390/smartcities9060101 https://www.mdpi.com/2624-6511/9/6/101 Smart Cities, Vol. 9, Pages 100: Machine-Learning-Based Prediction of Gushing-Induced Ground Disturbance Around Shield Tunnels https://www.mdpi.com/2624-6511/9/6/100 Water-soil gushing caused by tunnel leakage can induce severe ground disturbance and threaten the safety of shield tunnels, yet rapid prediction remains difficult because high-fidelity numerical simulations are computationally expensive. This study develops an interpretable machine-learning framework for predicting gushing-induced ground disturbance around shield tunnels based on a validated two-phase Material Point Method database. Six governing variables are considered, including the tunnel depth ratio, gushing location, soil friction angle, Young’s modulus, intrinsic permeability, and soil gushing mass. Three representative response variables were selected, namely the maximum ground settlement, flow-zone width, and flow-zone centroid angle. Five algorithms, including MLP, RF, XGBoost, SVR, and Ridge, were established and compared, with hyperparameters optimised using Optuna. The results show that nonlinear models consistently outperform the linear baseline, among which MLP, RF, and XGBoost achieve the best overall accuracy and robustness. Error-distribution analysis further indicates that MLP and RF yield the highest proportion of low-error predictions. SHAP interpretation shows that SGM is the dominant factor governing maximum settlement and flow-zone width, whereas gushing location primarily controls the flow-zone centroid angle. The proposed framework provides an efficient and physically interpretable surrogate for rapid hazard assessment of gushing-induced ground disturbance in shield tunnelling. 2026-06-13 Smart Cities, Vol. 9, Pages 100: Machine-Learning-Based Prediction of Gushing-Induced Ground Disturbance Around Shield Tunnels

Smart Cities doi: 10.3390/smartcities9060100

Authors: Xiao-Chuang Xie Zhao-Geng Chen Yu-Xin Zhang

Water-soil gushing caused by tunnel leakage can induce severe ground disturbance and threaten the safety of shield tunnels, yet rapid prediction remains difficult because high-fidelity numerical simulations are computationally expensive. This study develops an interpretable machine-learning framework for predicting gushing-induced ground disturbance around shield tunnels based on a validated two-phase Material Point Method database. Six governing variables are considered, including the tunnel depth ratio, gushing location, soil friction angle, Young’s modulus, intrinsic permeability, and soil gushing mass. Three representative response variables were selected, namely the maximum ground settlement, flow-zone width, and flow-zone centroid angle. Five algorithms, including MLP, RF, XGBoost, SVR, and Ridge, were established and compared, with hyperparameters optimised using Optuna. The results show that nonlinear models consistently outperform the linear baseline, among which MLP, RF, and XGBoost achieve the best overall accuracy and robustness. Error-distribution analysis further indicates that MLP and RF yield the highest proportion of low-error predictions. SHAP interpretation shows that SGM is the dominant factor governing maximum settlement and flow-zone width, whereas gushing location primarily controls the flow-zone centroid angle. The proposed framework provides an efficient and physically interpretable surrogate for rapid hazard assessment of gushing-induced ground disturbance in shield tunnelling.

]]> Machine-Learning-Based Prediction of Gushing-Induced Ground Disturbance Around Shield Tunnels Xiao-Chuang Xie Zhao-Geng Chen Yu-Xin Zhang doi: 10.3390/smartcities9060100 Smart Cities 2026-06-13 Smart Cities 2026-06-13 9 6 Article 100 10.3390/smartcities9060100 https://www.mdpi.com/2624-6511/9/6/100 Smart Cities, Vol. 9, Pages 99: Optimizing Public Transport Infrastructure Through AI-Driven Reliability Prediction: A Data-Driven Approach https://www.mdpi.com/2624-6511/9/6/99 Public transport reliability largely determines the performance of smart urban mobility systems, as it directly affects passenger satisfaction and network efficiency. However, the strategic planning of public transport infrastructure is often carried out without dynamic, data-driven insights into operational performance, instead relying solely on static historical records of network operations. This study develops a data-driven framework based on the XGBoost machine learning algorithm to support the prioritization of infrastructure interventions by predicting delay severity and identifying reliability hotspots along an urban bus route. Delay severity is categorized into three classes (minor, moderate, and severe), using a model that incorporates spatial, temporal, operational, and meteorological variables. The XGBoost framework achieves a high predictive performance, with classification accuracies of 91.5% and 89.7% for the outbound and inbound bus route directions, respectively. Feature importance analysis indicates that seasonal and meteorological variables are critical factors influencing delay severity, highlighting the role of broader external environmental conditions on corridor performance. Furthermore, spatial analysis identifies specific bus stops with high delay probabilities, indicating hotspots where infrastructure upgrades should be prioritized at the stop and corridor levels. This study proposes a decision-support tool that enables targeted infrastructure investments at locations where they are most needed, contributing to more efficient and resilient public transport systems in smart cities. 2026-06-11 Smart Cities, Vol. 9, Pages 99: Optimizing Public Transport Infrastructure Through AI-Driven Reliability Prediction: A Data-Driven Approach

Smart Cities doi: 10.3390/smartcities9060099

Authors: Ioannis Marios Andreadis Georgios Georgiadis Ioannis Politis

Public transport reliability largely determines the performance of smart urban mobility systems, as it directly affects passenger satisfaction and network efficiency. However, the strategic planning of public transport infrastructure is often carried out without dynamic, data-driven insights into operational performance, instead relying solely on static historical records of network operations. This study develops a data-driven framework based on the XGBoost machine learning algorithm to support the prioritization of infrastructure interventions by predicting delay severity and identifying reliability hotspots along an urban bus route. Delay severity is categorized into three classes (minor, moderate, and severe), using a model that incorporates spatial, temporal, operational, and meteorological variables. The XGBoost framework achieves a high predictive performance, with classification accuracies of 91.5% and 89.7% for the outbound and inbound bus route directions, respectively. Feature importance analysis indicates that seasonal and meteorological variables are critical factors influencing delay severity, highlighting the role of broader external environmental conditions on corridor performance. Furthermore, spatial analysis identifies specific bus stops with high delay probabilities, indicating hotspots where infrastructure upgrades should be prioritized at the stop and corridor levels. This study proposes a decision-support tool that enables targeted infrastructure investments at locations where they are most needed, contributing to more efficient and resilient public transport systems in smart cities.

]]> Optimizing Public Transport Infrastructure Through AI-Driven Reliability Prediction: A Data-Driven Approach Ioannis Marios Andreadis Georgios Georgiadis Ioannis Politis doi: 10.3390/smartcities9060099 Smart Cities 2026-06-11 Smart Cities 2026-06-11 9 6 Article 99 10.3390/smartcities9060099 https://www.mdpi.com/2624-6511/9/6/99 Smart Cities, Vol. 9, Pages 98: Smart City Mobility Readiness in Thailand: A C.A.S.E. Framework Assessment of Connected, Autonomous, Shared, and Electric Transportation https://www.mdpi.com/2624-6511/9/6/98 Smart city development depends on the readiness of Connected, Autonomous, Shared, and Electric (C.A.S.E.) mobility systems to deliver sustainable, data-driven urban transportation. This paper assesses C.A.S.E. mobility readiness in Thailand—Southeast Asia’s largest automotive manufacturing economy and an active smart city developer—situating each dimension within Thailand’s national seven-pillar smart city framework. A dual-axis supply–demand positioning framework synthesises peer-reviewed evidence, Thailand-specific infrastructure assessments, consumer surveys, and Monte Carlo simulation outputs across all four dimensions. Electric mobility is the most advanced dimension, with Thailand positioned as a regional production hub; Monte Carlo Total Cost of Ownership (TCO) analysis confirms 23–38% savings per route for electric bus adoption and fleet-wide net savings of approximately 236 million THB over ten years. Shared mobility is constrained by absent Mobility-as-a-Service (MaaS) governance, though mode choice evidence confirms a 24–36% car trip reduction potential through congestion pricing and shared taxi deployment. Connected mobility occupies a demand-led position; Autonomous mobility remains nascent on road, with trust identified as the dominant adoption barrier in a Technology Acceptance Model (TAM) survey of 797 Bangkok residents. Thailand’s seven-pillar smart city framework—particularly the Smart Mobility and Smart Governance pillars—provides the institutional architecture for an integrated C.A.S.E. National Mobility Strategy that could resolve governance fragmentation and accelerate sustainable urban mobility transition. 2026-05-29 Smart Cities, Vol. 9, Pages 98: Smart City Mobility Readiness in Thailand: A C.A.S.E. Framework Assessment of Connected, Autonomous, Shared, and Electric Transportation

Smart Cities doi: 10.3390/smartcities9060098

Authors: Sakgasem Ramingwong Salinee Santiteerakul Apichat Sopadang Korrakot Yaibuathet Tippayawong Poti Chaopaisarn Tanyanuparb Anantana Jutamat Jintana

Smart city development depends on the readiness of Connected, Autonomous, Shared, and Electric (C.A.S.E.) mobility systems to deliver sustainable, data-driven urban transportation. This paper assesses C.A.S.E. mobility readiness in Thailand—Southeast Asia’s largest automotive manufacturing economy and an active smart city developer—situating each dimension within Thailand’s national seven-pillar smart city framework. A dual-axis supply–demand positioning framework synthesises peer-reviewed evidence, Thailand-specific infrastructure assessments, consumer surveys, and Monte Carlo simulation outputs across all four dimensions. Electric mobility is the most advanced dimension, with Thailand positioned as a regional production hub; Monte Carlo Total Cost of Ownership (TCO) analysis confirms 23–38% savings per route for electric bus adoption and fleet-wide net savings of approximately 236 million THB over ten years. Shared mobility is constrained by absent Mobility-as-a-Service (MaaS) governance, though mode choice evidence confirms a 24–36% car trip reduction potential through congestion pricing and shared taxi deployment. Connected mobility occupies a demand-led position; Autonomous mobility remains nascent on road, with trust identified as the dominant adoption barrier in a Technology Acceptance Model (TAM) survey of 797 Bangkok residents. Thailand’s seven-pillar smart city framework—particularly the Smart Mobility and Smart Governance pillars—provides the institutional architecture for an integrated C.A.S.E. National Mobility Strategy that could resolve governance fragmentation and accelerate sustainable urban mobility transition.

]]> Smart City Mobility Readiness in Thailand: A C.A.S.E. Framework Assessment of Connected, Autonomous, Shared, and Electric Transportation Sakgasem Ramingwong Salinee Santiteerakul Apichat Sopadang Korrakot Yaibuathet Tippayawong Poti Chaopaisarn Tanyanuparb Anantana Jutamat Jintana doi: 10.3390/smartcities9060098 Smart Cities 2026-05-29 Smart Cities 2026-05-29 9 6 Article 98 10.3390/smartcities9060098 https://www.mdpi.com/2624-6511/9/6/98 Smart Cities, Vol. 9, Pages 97: Equitable Access to Urban Green Spaces Under Heat Stress: An Agent-Based Simulation (ABS) of Age-Differentiated Walkability Through a Behavioral Perspective https://www.mdpi.com/2624-6511/9/6/97 Urban green spaces play a critical role in mitigating heat stress and enhancing urban livability, in line with the objectives and expectations of the United Nations Sustainable Development Goals 10 (Reduced Inequalities) and 11 (Sustainable Cities and Communities). This study employs Physarealm (Grasshopper), a lightweight agent-based simulation (ABS) model, to dynamically simulate pedestrian behaviors for different mobility groups. Together with Space Syntax, the results—time-extended movement and interaction patterns—are conceptualized as a relational configuration of green space provision (supply), pedestrian activity intensity (demand), and thermal exposure (environmental resistance). Three contrasting urban areas in northern Italy (Lambrate, Bolognina, and Ispra) are selected as case studies. The results demonstrate that urban inequality cannot be sufficiently explained by the inadequacy of single components, but emerges from imbalanced relational configurations of supply, demand, and environmental resistance. In May, 100% and 95% of traversed cells in Lambrate and Bolognina fall within the high-heat-stress range (>32 °C), compared with 59% in Ispra. Correspondingly, average green provision within the 5 min walking range is 5.4% in Lambrate, 7.2% in Bolognina, and 37% in Ispra. By uncovering relational mismatch patterns that are often overlooked in conventional urban analyses, this study enables a multi-dimensional diagnosis of imbalances. By positioning ABS as a front-end process generator and Space Syntax as a structural interpretation step, it demonstrates how dynamic behavioral processes can be reorganized into network-scale diagnostic representations. The study supports a climate-sensitive and human-centered diagnosis of walkability and green space accessibility, while contributing a transferable analytical approach for identifying relational inequality patterns within open urban data science contexts. 2026-05-28 Smart Cities, Vol. 9, Pages 97: Equitable Access to Urban Green Spaces Under Heat Stress: An Agent-Based Simulation (ABS) of Age-Differentiated Walkability Through a Behavioral Perspective

Smart Cities doi: 10.3390/smartcities9060097

Authors: Tao Dong Massimo Tadi

Urban green spaces play a critical role in mitigating heat stress and enhancing urban livability, in line with the objectives and expectations of the United Nations Sustainable Development Goals 10 (Reduced Inequalities) and 11 (Sustainable Cities and Communities). This study employs Physarealm (Grasshopper), a lightweight agent-based simulation (ABS) model, to dynamically simulate pedestrian behaviors for different mobility groups. Together with Space Syntax, the results—time-extended movement and interaction patterns—are conceptualized as a relational configuration of green space provision (supply), pedestrian activity intensity (demand), and thermal exposure (environmental resistance). Three contrasting urban areas in northern Italy (Lambrate, Bolognina, and Ispra) are selected as case studies. The results demonstrate that urban inequality cannot be sufficiently explained by the inadequacy of single components, but emerges from imbalanced relational configurations of supply, demand, and environmental resistance. In May, 100% and 95% of traversed cells in Lambrate and Bolognina fall within the high-heat-stress range (>32 °C), compared with 59% in Ispra. Correspondingly, average green provision within the 5 min walking range is 5.4% in Lambrate, 7.2% in Bolognina, and 37% in Ispra. By uncovering relational mismatch patterns that are often overlooked in conventional urban analyses, this study enables a multi-dimensional diagnosis of imbalances. By positioning ABS as a front-end process generator and Space Syntax as a structural interpretation step, it demonstrates how dynamic behavioral processes can be reorganized into network-scale diagnostic representations. The study supports a climate-sensitive and human-centered diagnosis of walkability and green space accessibility, while contributing a transferable analytical approach for identifying relational inequality patterns within open urban data science contexts.

]]> Equitable Access to Urban Green Spaces Under Heat Stress: An Agent-Based Simulation (ABS) of Age-Differentiated Walkability Through a Behavioral Perspective Tao Dong Massimo Tadi doi: 10.3390/smartcities9060097 Smart Cities 2026-05-28 Smart Cities 2026-05-28 9 6 Article 97 10.3390/smartcities9060097 https://www.mdpi.com/2624-6511/9/6/97 Smart Cities, Vol. 9, Pages 95: MobiCugat: City-Scale Traffic Assessment Using Low-Emission Zone Camera Data https://www.mdpi.com/2624-6511/9/6/95 While Low Emission Zone (LEZ) enforcement cameras provide a constant stream of traffic data, such resources remain significantly underexploited for urban mobility planning, as their current application is restricted to enforcing vehicle access regulations and issuing fines. This paper presents MobiCugat, a framework demonstrating that Automatic Number Plate Recognition (ANPR) camera data from a municipal LEZ network can serve as the calibration backbone for high-fidelity, city-scale traffic simulations for a policy-testing Digital Twin. The case study is Sant Cugat del Vallès (Barcelona), where the local council sought to evaluate new scenarios for the area using an evidence-based, data-driven approach. Vehicle detection records from 102 LEZ ANPR cameras were processed into 15-min traffic intensity time series through a General Data Protection Regulation (GDPR)-compliant pipeline. The Realistic Urban Traffic Generator (RUTGe), a Deep Reinforcement Learning-based tool, was used to generate SUMO-compatible traffic demand whose simulated detector counts reproduce the observed camera-based intensities. The resulting simulations reproduced the observed detector-level traffic intensities with MARE% values between 2.29% and 2.90% across representative morning peak, midday off-peak, and evening peak traffic conditions. Additionally, camera analysis of over 470,000 vehicle records revealed that resident traffic (37.4%) dominates over through-traffic (3.8%), significantly refining prior survey-based estimates. Our high-fidelity simulation tool based on SUMO, features realistic traffic patterns calibrated through AI-driven techniques, enabling the evaluation of diverse ’what-if’ scenarios—such as road closures, pedestrianization, changes in traffic direction, or relocation of bus stops. By quantifying the impact of these interventions, our tool facilitates informed decision-making prior to physical implementation. The proposed pipeline is cost-effective, privacy-preserving, and directly replicable for any municipality operating an LEZ camera network, offering a scalable template for evidence-based urban mobility planning, aligned with the European Strategy for Data and the EU Green Deal goals for sustainable mobility. 2026-05-27 Smart Cities, Vol. 9, Pages 95: MobiCugat: City-Scale Traffic Assessment Using Low-Emission Zone Camera Data

Smart Cities doi: 10.3390/smartcities9060095

Authors: Alberto Bazán-Guillén Víctor Rubio-Jornet Mónica Aguilar Igartua Joaquim Montal Marta Vives i Pinyol Albert Muratet i Casadevall

While Low Emission Zone (LEZ) enforcement cameras provide a constant stream of traffic data, such resources remain significantly underexploited for urban mobility planning, as their current application is restricted to enforcing vehicle access regulations and issuing fines. This paper presents MobiCugat, a framework demonstrating that Automatic Number Plate Recognition (ANPR) camera data from a municipal LEZ network can serve as the calibration backbone for high-fidelity, city-scale traffic simulations for a policy-testing Digital Twin. The case study is Sant Cugat del Vallès (Barcelona), where the local council sought to evaluate new scenarios for the area using an evidence-based, data-driven approach. Vehicle detection records from 102 LEZ ANPR cameras were processed into 15-min traffic intensity time series through a General Data Protection Regulation (GDPR)-compliant pipeline. The Realistic Urban Traffic Generator (RUTGe), a Deep Reinforcement Learning-based tool, was used to generate SUMO-compatible traffic demand whose simulated detector counts reproduce the observed camera-based intensities. The resulting simulations reproduced the observed detector-level traffic intensities with MARE% values between 2.29% and 2.90% across representative morning peak, midday off-peak, and evening peak traffic conditions. Additionally, camera analysis of over 470,000 vehicle records revealed that resident traffic (37.4%) dominates over through-traffic (3.8%), significantly refining prior survey-based estimates. Our high-fidelity simulation tool based on SUMO, features realistic traffic patterns calibrated through AI-driven techniques, enabling the evaluation of diverse ’what-if’ scenarios—such as road closures, pedestrianization, changes in traffic direction, or relocation of bus stops. By quantifying the impact of these interventions, our tool facilitates informed decision-making prior to physical implementation. The proposed pipeline is cost-effective, privacy-preserving, and directly replicable for any municipality operating an LEZ camera network, offering a scalable template for evidence-based urban mobility planning, aligned with the European Strategy for Data and the EU Green Deal goals for sustainable mobility.

]]> MobiCugat: City-Scale Traffic Assessment Using Low-Emission Zone Camera Data Alberto Bazán-Guillén Víctor Rubio-Jornet Mónica Aguilar Igartua Joaquim Montal Marta Vives i Pinyol Albert Muratet i Casadevall doi: 10.3390/smartcities9060095 Smart Cities 2026-05-27 Smart Cities 2026-05-27 9 6 Article 95 10.3390/smartcities9060095 https://www.mdpi.com/2624-6511/9/6/95 Smart Cities, Vol. 9, Pages 96: Electrical Grid Architectures for Smart Cities from Digitalized Power Systems to AI-Enabled Urban Energy Ecosystems https://www.mdpi.com/2624-6511/9/6/96 Smart cities increasingly depend on electrical grid infrastructures capable of operating under high levels of digitalization, decentralization, and intelligence while maintaining reliability, security, and governance at the city scale. However, conventional power systems, historically designed for centralized generation and passive operation, are poorly aligned with the operational complexity, multi-actor coordination, and cross-sector integration characteristic of urban energy systems. This review develops an architecture-first perspective on smart-city electrical grids, tracing their evolution from digitalized power networks to decentralized and AI-enabled urban energy ecosystems. Rather than focusing on individual technologies, the study evaluates grid architectures using a multi-layer framework that integrates physical grid infrastructure, distributed energy resources and microgrids, communication and data platforms, intelligence placement, cybersecurity exposure, and governance accountability. Smart-city grid architectures are assessed using deployability beyond pilot projects, auditability, and regulatory alignment as primary evaluation criteria alongside conventional technical considerations. Through this perspective, the review explains a recurring pattern observed in the literature: many technically mature smart-grid solutions fail to scale in real urban deployments due to architectural fragmentation and governance constraints. By synthesizing insights from power systems engineering, information and communication technologies, and smart-city research, the paper highlights architectural trade-offs related to decentralization, interoperability, resilience under compound threats, and assisted autonomy. The resulting framework supports researchers, system designers, and policymakers in the coordinated development of resilient, secure, and governable electrical grids for future smart-city energy systems. 2026-05-27 Smart Cities, Vol. 9, Pages 96: Electrical Grid Architectures for Smart Cities from Digitalized Power Systems to AI-Enabled Urban Energy Ecosystems

Smart Cities doi: 10.3390/smartcities9060096

Authors: Hilmy Awad Ehab H. E. Bayoumi

Smart cities increasingly depend on electrical grid infrastructures capable of operating under high levels of digitalization, decentralization, and intelligence while maintaining reliability, security, and governance at the city scale. However, conventional power systems, historically designed for centralized generation and passive operation, are poorly aligned with the operational complexity, multi-actor coordination, and cross-sector integration characteristic of urban energy systems. This review develops an architecture-first perspective on smart-city electrical grids, tracing their evolution from digitalized power networks to decentralized and AI-enabled urban energy ecosystems. Rather than focusing on individual technologies, the study evaluates grid architectures using a multi-layer framework that integrates physical grid infrastructure, distributed energy resources and microgrids, communication and data platforms, intelligence placement, cybersecurity exposure, and governance accountability. Smart-city grid architectures are assessed using deployability beyond pilot projects, auditability, and regulatory alignment as primary evaluation criteria alongside conventional technical considerations. Through this perspective, the review explains a recurring pattern observed in the literature: many technically mature smart-grid solutions fail to scale in real urban deployments due to architectural fragmentation and governance constraints. By synthesizing insights from power systems engineering, information and communication technologies, and smart-city research, the paper highlights architectural trade-offs related to decentralization, interoperability, resilience under compound threats, and assisted autonomy. The resulting framework supports researchers, system designers, and policymakers in the coordinated development of resilient, secure, and governable electrical grids for future smart-city energy systems.

]]> Electrical Grid Architectures for Smart Cities from Digitalized Power Systems to AI-Enabled Urban Energy Ecosystems Hilmy Awad Ehab H. E. Bayoumi doi: 10.3390/smartcities9060096 Smart Cities 2026-05-27 Smart Cities 2026-05-27 9 6 Review 96 10.3390/smartcities9060096 https://www.mdpi.com/2624-6511/9/6/96 Smart Cities, Vol. 9, Pages 94: What Is Worse than a Back-Seat Driver? A Remote One: Rethinking Teleoperation in Automated Vehicles https://www.mdpi.com/2624-6511/9/6/94 Much of the research and proposed industrial deployment of Remote Operations (ROs) in support of automated vehicles is founded on the optimistic premise that in-vehicle standby drivers and Safety Officers (SOs) can easily be replaced with ROs, with some commercial models proposing that a single RO supervise over 30 vehicles. However, emerging evidence suggests that the RO task is fundamentally different from the in-vehicle driving task. Furthermore, communications latency and reliability constraints, coupled with fragmented attention and altered task demands, introduce distinctive human factor challenges. These include degraded situational awareness, increased cognitive workload, and reduced capacity for timely intervention. The result is a widening gap between what is commercially desirable and what may be operationally appropriate. This paper argues that the central question for remote operation in support of automated vehicles is not one of technical feasibility but of human-centred appropriateness, and debates which RO roles should continue to be developed and which should be constrained or avoided. We present a synthesis of research on remote vehicle operations, identifying recurring human-factor limitations and mapping them to proposed remote tasks. The paper concludes with targeted recommendations for designers, operators, and regulators intended to question the scaling of teleoperation models and to reframe the debate from “Can we teleoperate?” to “Under what conditions should we?” 2026-05-27 Smart Cities, Vol. 9, Pages 94: What Is Worse than a Back-Seat Driver? A Remote One: Rethinking Teleoperation in Automated Vehicles

Smart Cities doi: 10.3390/smartcities9060094

Authors: Adam Bogg Stewart Birrell Marko Medojevic Kevin Vincent

Much of the research and proposed industrial deployment of Remote Operations (ROs) in support of automated vehicles is founded on the optimistic premise that in-vehicle standby drivers and Safety Officers (SOs) can easily be replaced with ROs, with some commercial models proposing that a single RO supervise over 30 vehicles. However, emerging evidence suggests that the RO task is fundamentally different from the in-vehicle driving task. Furthermore, communications latency and reliability constraints, coupled with fragmented attention and altered task demands, introduce distinctive human factor challenges. These include degraded situational awareness, increased cognitive workload, and reduced capacity for timely intervention. The result is a widening gap between what is commercially desirable and what may be operationally appropriate. This paper argues that the central question for remote operation in support of automated vehicles is not one of technical feasibility but of human-centred appropriateness, and debates which RO roles should continue to be developed and which should be constrained or avoided. We present a synthesis of research on remote vehicle operations, identifying recurring human-factor limitations and mapping them to proposed remote tasks. The paper concludes with targeted recommendations for designers, operators, and regulators intended to question the scaling of teleoperation models and to reframe the debate from “Can we teleoperate?” to “Under what conditions should we?”

]]> What Is Worse than a Back-Seat Driver? A Remote One: Rethinking Teleoperation in Automated Vehicles Adam Bogg Stewart Birrell Marko Medojevic Kevin Vincent doi: 10.3390/smartcities9060094 Smart Cities 2026-05-27 Smart Cities 2026-05-27 9 6 Review 94 10.3390/smartcities9060094 https://www.mdpi.com/2624-6511/9/6/94 Smart Cities, Vol. 9, Pages 93: Pareto Optimization of Power Consumption and Transmission Power for IoT and Wireless Sensor Networks in Dynamic Temperature Environments https://www.mdpi.com/2624-6511/9/6/93 Temperature has a significant impact on the operation and performance of electronic systems. Conventional approaches focus on stabilizing electronic systems to maintain functionality under unfavorable thermal conditions, typically at the expense of increased consumption. This paper adopts a multi-objective approach to identify the Pareto-optimal (PO) trade-off across varying temperatures between functionality and consumption of low-power radio transceivers used in the Internet of Things (IoT) and wireless sensor networks. Building upon the established two-segment PO trade-off controlled by supply voltage and output power settings, between engaged and achieved transmission power, parameters directly associated with energy consumption and transmission quality, we analyze the influence of temperature on the Pareto front. We find that decreasing the temperature improves both engaged power and achieved transmission power simultaneously. Therefore, we propose a novel Pareto-optimal temperature-opportunistic wireless communication approach that exploits temperature variability by selecting favorable temperature conditions for transmission. We also identify the spatio-temporal potential of temperature variations across a four-dimensional network deployment space, particularly in temperature-dynamic urban environments of smart city infrastructure supporting massive IoT. Experiments on a modern Texas Instruments CC1200 transceiver confirm that the power savings of approx 30% and nearly 450 times increase in achieved transmission power are attainable for a temperature difference of 60 °C, corresponding to realistic conditions between the ambient air and a black-painted surface. 2026-05-26 Smart Cities, Vol. 9, Pages 93: Pareto Optimization of Power Consumption and Transmission Power for IoT and Wireless Sensor Networks in Dynamic Temperature Environments

Smart Cities doi: 10.3390/smartcities9060093

Authors: Nikola Zogović Miloš D. Jevtić Dragana Bajić Goran Dimić

Temperature has a significant impact on the operation and performance of electronic systems. Conventional approaches focus on stabilizing electronic systems to maintain functionality under unfavorable thermal conditions, typically at the expense of increased consumption. This paper adopts a multi-objective approach to identify the Pareto-optimal (PO) trade-off across varying temperatures between functionality and consumption of low-power radio transceivers used in the Internet of Things (IoT) and wireless sensor networks. Building upon the established two-segment PO trade-off controlled by supply voltage and output power settings, between engaged and achieved transmission power, parameters directly associated with energy consumption and transmission quality, we analyze the influence of temperature on the Pareto front. We find that decreasing the temperature improves both engaged power and achieved transmission power simultaneously. Therefore, we propose a novel Pareto-optimal temperature-opportunistic wireless communication approach that exploits temperature variability by selecting favorable temperature conditions for transmission. We also identify the spatio-temporal potential of temperature variations across a four-dimensional network deployment space, particularly in temperature-dynamic urban environments of smart city infrastructure supporting massive IoT. Experiments on a modern Texas Instruments CC1200 transceiver confirm that the power savings of approx 30% and nearly 450 times increase in achieved transmission power are attainable for a temperature difference of 60 °C, corresponding to realistic conditions between the ambient air and a black-painted surface.

]]> Pareto Optimization of Power Consumption and Transmission Power for IoT and Wireless Sensor Networks in Dynamic Temperature Environments Nikola Zogović Miloš D. Jevtić Dragana Bajić Goran Dimić doi: 10.3390/smartcities9060093 Smart Cities 2026-05-26 Smart Cities 2026-05-26 9 6 Article 93 10.3390/smartcities9060093 https://www.mdpi.com/2624-6511/9/6/93 Smart Cities, Vol. 9, Pages 92: A Systematic Review of IoT and Edge Computing Applications for the Monitoring and Control of Renewable Energy Systems in Smart Grid and Smart City Environments https://www.mdpi.com/2624-6511/9/6/92 The growing environmental crisis and rapid urbanization have made the shift to renewable energy systems even more important for smart city development. In today’s cities, such renewable energy sources as solar photovoltaics, wind energy, hybrid systems, and battery energy storage are no longer just separate assets. They are now important parts of smart grids, intelligent buildings, and urban infrastructure that work together. However, putting these systems in cities on a large scale makes it harder to monitor, control, integrate, scale, and work with them in real time. In this setting, the Internet of Things (IoT) and edge computing are technologies that make it possible to turn traditional renewable energy systems into smart, responsive, and self-sufficient urban energy systems. IoT-based monitoring and control systems let city operators, utilities, and policymakers gather real-time data, improve grid stability, optimize energy flows, and better integrate distributed renewable energy sources into smart city ecosystems. Edge computing makes these features even better by allowing for low-latency processing, more localized decision-making, and less reliance on centralized cloud infrastructures. This paper offers a thorough and methodical examination of contemporary IoT- and edge-enabled technologies used to monitor, control, and integrate renewable energy systems; specifically highlighting their significance in smart city and smart grid applications. The review combines the most recent research on hardware platforms, communication protocols, data processing architectures, and edge–cloud coordination mechanisms used in solar, wind, and hybrid energy systems. Additionally, this review synthesizes architectural design principles extracted from analyzed studies to guide the development of scalable, resilient, and cost-efficient renewable energy monitoring systems. This study offers a structured foundation for the design of scalable, resilient, and cost-effective renewable energy management systems that align with the sustainability, efficiency, and intelligence goals of future smart cities by analyzing cutting-edge solutions and pinpointing significant technological trends, challenges, and research deficiencies. This review also highlights its contribution vis-à-vis previous surveys by stressing the inter-domain comparison across solar, wind, and hybrid systems. It focuses, in particular, on edge–cloud coordination and architecture-level trade-offs pertinent to smart grid and smart city deployments. 2026-05-25 Smart Cities, Vol. 9, Pages 92: A Systematic Review of IoT and Edge Computing Applications for the Monitoring and Control of Renewable Energy Systems in Smart Grid and Smart City Environments

Smart Cities doi: 10.3390/smartcities9060092

Authors: Jafar AlQaryouti Mustafa J. M. Alhamdi Javad Rahebi Jose Antonio Ramos-Hernanz Jose Manuel Lopez-Guede

The growing environmental crisis and rapid urbanization have made the shift to renewable energy systems even more important for smart city development. In today’s cities, such renewable energy sources as solar photovoltaics, wind energy, hybrid systems, and battery energy storage are no longer just separate assets. They are now important parts of smart grids, intelligent buildings, and urban infrastructure that work together. However, putting these systems in cities on a large scale makes it harder to monitor, control, integrate, scale, and work with them in real time. In this setting, the Internet of Things (IoT) and edge computing are technologies that make it possible to turn traditional renewable energy systems into smart, responsive, and self-sufficient urban energy systems. IoT-based monitoring and control systems let city operators, utilities, and policymakers gather real-time data, improve grid stability, optimize energy flows, and better integrate distributed renewable energy sources into smart city ecosystems. Edge computing makes these features even better by allowing for low-latency processing, more localized decision-making, and less reliance on centralized cloud infrastructures. This paper offers a thorough and methodical examination of contemporary IoT- and edge-enabled technologies used to monitor, control, and integrate renewable energy systems; specifically highlighting their significance in smart city and smart grid applications. The review combines the most recent research on hardware platforms, communication protocols, data processing architectures, and edge–cloud coordination mechanisms used in solar, wind, and hybrid energy systems. Additionally, this review synthesizes architectural design principles extracted from analyzed studies to guide the development of scalable, resilient, and cost-efficient renewable energy monitoring systems. This study offers a structured foundation for the design of scalable, resilient, and cost-effective renewable energy management systems that align with the sustainability, efficiency, and intelligence goals of future smart cities by analyzing cutting-edge solutions and pinpointing significant technological trends, challenges, and research deficiencies. This review also highlights its contribution vis-à-vis previous surveys by stressing the inter-domain comparison across solar, wind, and hybrid systems. It focuses, in particular, on edge–cloud coordination and architecture-level trade-offs pertinent to smart grid and smart city deployments.

]]> A Systematic Review of IoT and Edge Computing Applications for the Monitoring and Control of Renewable Energy Systems in Smart Grid and Smart City Environments Jafar AlQaryouti Mustafa J. M. Alhamdi Javad Rahebi Jose Antonio Ramos-Hernanz Jose Manuel Lopez-Guede doi: 10.3390/smartcities9060092 Smart Cities 2026-05-25 Smart Cities 2026-05-25 9 6 Systematic Review 92 10.3390/smartcities9060092 https://www.mdpi.com/2624-6511/9/6/92 Smart Cities, Vol. 9, Pages 91: Closed-Loop CPU-Aware Traffic Control for SDN-Enabled 5G/6G Networks in Open vSwitch Dataplanes https://www.mdpi.com/2624-6511/9/6/91 This paper presents a closed-loop, CPU-aware traffic-control framework for SDN in 5G/6G multi-tenant edge environments based on commodity KVM/OVS infrastructures. It couples fine-grained data-plane telemetry via eBPF with adaptive XDP rate limiting, coordinated by a PID controller in the OVS datapath. Unlike control-plane polling, it provides real-time feedback between CPU utilization and traffic regulation. Experiments in a virtualized multi-tenant OVS testbed (KVM/virtio-net) keep CPU below per-slice CPU targets (e.g., 1.02% for a 3% setpoint), with an under-target bias that avoids overshoot while preserving stable forwarding. We attribute this bias, at light load, to a supply-limited regime, conservative per-slice CPU accounting, and stability-oriented PID tuning, and introduce a low-latency profile that mitigates this bias for latency-sensitive slices. The XDP datapath achieves 1–3 μs per-packet processing with 5–10% additional CPU overhead relative to an uninstrumented baseline, while using less CPU than OVS policing at comparable throughput. A 3% per-slice CPU target balances isolation and throughput, while 2% yields stricter isolation at the cost of higher packet loss. Software-based rate limiting can induce cross-slice interference; effective isolation holds below 1 Gbps aggregate load. Above this, shared Linux kernel overhead degrades isolation, causing significant loss; thus, XDP alone cannot ensure line-rate isolation, motivating SmartNICs. The design improves efficiency, predictability, and isolation, laying a foundation for intelligent traffic management in future resource-intensive applications. 2026-05-25 Smart Cities, Vol. 9, Pages 91: Closed-Loop CPU-Aware Traffic Control for SDN-Enabled 5G/6G Networks in Open vSwitch Dataplanes

Smart Cities doi: 10.3390/smartcities9060091

Authors: Stefan Biševac Živko Bojović Petar D. Bojović Ilija Doknić

This paper presents a closed-loop, CPU-aware traffic-control framework for SDN in 5G/6G multi-tenant edge environments based on commodity KVM/OVS infrastructures. It couples fine-grained data-plane telemetry via eBPF with adaptive XDP rate limiting, coordinated by a PID controller in the OVS datapath. Unlike control-plane polling, it provides real-time feedback between CPU utilization and traffic regulation. Experiments in a virtualized multi-tenant OVS testbed (KVM/virtio-net) keep CPU below per-slice CPU targets (e.g., 1.02% for a 3% setpoint), with an under-target bias that avoids overshoot while preserving stable forwarding. We attribute this bias, at light load, to a supply-limited regime, conservative per-slice CPU accounting, and stability-oriented PID tuning, and introduce a low-latency profile that mitigates this bias for latency-sensitive slices. The XDP datapath achieves 1–3 μs per-packet processing with 5–10% additional CPU overhead relative to an uninstrumented baseline, while using less CPU than OVS policing at comparable throughput. A 3% per-slice CPU target balances isolation and throughput, while 2% yields stricter isolation at the cost of higher packet loss. Software-based rate limiting can induce cross-slice interference; effective isolation holds below 1 Gbps aggregate load. Above this, shared Linux kernel overhead degrades isolation, causing significant loss; thus, XDP alone cannot ensure line-rate isolation, motivating SmartNICs. The design improves efficiency, predictability, and isolation, laying a foundation for intelligent traffic management in future resource-intensive applications.

]]> Closed-Loop CPU-Aware Traffic Control for SDN-Enabled 5G/6G Networks in Open vSwitch Dataplanes Stefan Biševac Živko Bojović Petar D. Bojović Ilija Doknić doi: 10.3390/smartcities9060091 Smart Cities 2026-05-25 Smart Cities 2026-05-25 9 6 Article 91 10.3390/smartcities9060091 https://www.mdpi.com/2624-6511/9/6/91 Smart Cities, Vol. 9, Pages 90: Nonlinear Scaling of Medical Resources with Population Size in Chinese Cities https://www.mdpi.com/2624-6511/9/6/90 Medical resources are primary public goods, but the nature of their distribution across different-sized cities is unclear. Here, we examined the nonlinear scaling relationship between urban populations and medical resources in China, moving beyond the limitations of traditional linear evaluation metrics. Taking 296 Chinese cities as samples, we constructed scaling law models between population size and three medical resource indicators: the numbers of hospital beds, doctors, and hospitals. The results show that the number of doctors maintained a linear scaling relationship on the whole (scaling exponent β: 0.98–1.06), while the numbers of hospitals (β: 0.79–0.91) and hospital beds (β: 0.91–0.99) both exhibited sublinear scaling (2000–2022), confirming the existence of economies of scale in basic medical facilities. The Scale-Adjusted Metropolitan Indicator (SAMI) further reveals spatial agglomeration characteristics: the northern and southwestern regions of China perform notably better than expected in hospital availability, while provincial cites show advantages in terms of the numbers of beds and doctors. This study quantifies the nonlinear allocation of medical resources across Chinese cities and advocates for a reasonable allocation mechanism to promote medical equity. 2026-05-25 Smart Cities, Vol. 9, Pages 90: Nonlinear Scaling of Medical Resources with Population Size in Chinese Cities

Smart Cities doi: 10.3390/smartcities9060090

Authors: Ruimin Cai Mengqin Wu Ting Dong Gang Xu

Medical resources are primary public goods, but the nature of their distribution across different-sized cities is unclear. Here, we examined the nonlinear scaling relationship between urban populations and medical resources in China, moving beyond the limitations of traditional linear evaluation metrics. Taking 296 Chinese cities as samples, we constructed scaling law models between population size and three medical resource indicators: the numbers of hospital beds, doctors, and hospitals. The results show that the number of doctors maintained a linear scaling relationship on the whole (scaling exponent β: 0.98–1.06), while the numbers of hospitals (β: 0.79–0.91) and hospital beds (β: 0.91–0.99) both exhibited sublinear scaling (2000–2022), confirming the existence of economies of scale in basic medical facilities. The Scale-Adjusted Metropolitan Indicator (SAMI) further reveals spatial agglomeration characteristics: the northern and southwestern regions of China perform notably better than expected in hospital availability, while provincial cites show advantages in terms of the numbers of beds and doctors. This study quantifies the nonlinear allocation of medical resources across Chinese cities and advocates for a reasonable allocation mechanism to promote medical equity.

]]> Nonlinear Scaling of Medical Resources with Population Size in Chinese Cities Ruimin Cai Mengqin Wu Ting Dong Gang Xu doi: 10.3390/smartcities9060090 Smart Cities 2026-05-25 Smart Cities 2026-05-25 9 6 Article 90 10.3390/smartcities9060090 https://www.mdpi.com/2624-6511/9/6/90 Smart Cities, Vol. 9, Pages 89: Traffic-Management Screening with Urban Buses as Probe Vehicles: MRV, Mixed-Effects Evidence and EF 3.1 Scenarios from a 2024 Metropolitan Fleet https://www.mdpi.com/2624-6511/9/6/89 Background: Smart-city road and intersection management increasingly aims to smooth bus operations and reduce stop-and-go driving, but cities often lack auditable indicators linking routine fleet data with comparable energy and environmental KPIs. Methods: This study develops a Monitoring–Reporting–Verification (MRV) workflow for daily bus records from a 2024 Polish metropolitan fleet (diesel, compressed natural gas (CNG), hybrid, and battery-electric buses). Records were quality checked, harmonized to MJ/km, aggregated to bus-month observations, and analyzed using a linear mixed-effects model with propulsion technology, season, and activity level as fixed effects and vehicle-level random intercepts. Environmental impacts were then calculated under well-to-wheel (WTW) boundaries using Environmental Footprint 3.1 (EF 3.1) impact categories, Poland’s 2024 electricity mix, and illustrative electricity-mix scenarios through 2050. Results: Relative to diesel, BEV and HEV were associated with lower adjusted energy intensity (ratios 0.272 and 0.681, respectively), whereas the CNG–diesel contrast was directionally higher but statistically inconclusive under the available CNG sample. BEV energy intensity more than doubled in winter in descriptive terms, and vehicle-specific heterogeneity remained high (ICC ≈ 0.61). The BEV climate profile improved under electricity decarbonization, while some EF categories showed mix-dependent trade-offs. The 3–10% traffic-management variants are interpreted as screening assumptions rather than measured ITS effects. Conclusions: Routine bus records can support auditable MRV and preliminary screening of fleet and corridor interventions, but causal traffic-management evaluation requires route-level trajectory, congestion, and before–after data. 2026-05-24 Smart Cities, Vol. 9, Pages 89: Traffic-Management Screening with Urban Buses as Probe Vehicles: MRV, Mixed-Effects Evidence and EF 3.1 Scenarios from a 2024 Metropolitan Fleet

Smart Cities doi: 10.3390/smartcities9060089

Authors: Marcin Staniek

Background: Smart-city road and intersection management increasingly aims to smooth bus operations and reduce stop-and-go driving, but cities often lack auditable indicators linking routine fleet data with comparable energy and environmental KPIs. Methods: This study develops a Monitoring–Reporting–Verification (MRV) workflow for daily bus records from a 2024 Polish metropolitan fleet (diesel, compressed natural gas (CNG), hybrid, and battery-electric buses). Records were quality checked, harmonized to MJ/km, aggregated to bus-month observations, and analyzed using a linear mixed-effects model with propulsion technology, season, and activity level as fixed effects and vehicle-level random intercepts. Environmental impacts were then calculated under well-to-wheel (WTW) boundaries using Environmental Footprint 3.1 (EF 3.1) impact categories, Poland’s 2024 electricity mix, and illustrative electricity-mix scenarios through 2050. Results: Relative to diesel, BEV and HEV were associated with lower adjusted energy intensity (ratios 0.272 and 0.681, respectively), whereas the CNG–diesel contrast was directionally higher but statistically inconclusive under the available CNG sample. BEV energy intensity more than doubled in winter in descriptive terms, and vehicle-specific heterogeneity remained high (ICC ≈ 0.61). The BEV climate profile improved under electricity decarbonization, while some EF categories showed mix-dependent trade-offs. The 3–10% traffic-management variants are interpreted as screening assumptions rather than measured ITS effects. Conclusions: Routine bus records can support auditable MRV and preliminary screening of fleet and corridor interventions, but causal traffic-management evaluation requires route-level trajectory, congestion, and before–after data.

]]> Traffic-Management Screening with Urban Buses as Probe Vehicles: MRV, Mixed-Effects Evidence and EF 3.1 Scenarios from a 2024 Metropolitan Fleet Marcin Staniek doi: 10.3390/smartcities9060089 Smart Cities 2026-05-24 Smart Cities 2026-05-24 9 6 Article 89 10.3390/smartcities9060089 https://www.mdpi.com/2624-6511/9/6/89 Smart Cities, Vol. 9, Pages 88: Intelligent Load Frequency Control Strategy for Multi-Microgrids with Vehicle-to-Grid Considering Charging Diversity and Extreme Weather https://www.mdpi.com/2624-6511/9/5/88 With the rapid electrification of urban transportation and increasing penetration of renewable energy, maintaining frequency stability in smart-city multi-microgrids (MMG) systems increasingly depends on coordinated vehicle-to-grid (V2G) flexibility. However, existing load frequency control strategies typically treat electric vehicles (EVs) as homogeneous resources and overlook the impacts of charging-infrastructure diversity, user mobility constraints, and extreme weather conditions on regulation availability. To address these challenges, this study proposes a weather-adaptive intelligent load frequency control strategy for smart-city MMG considering heterogeneous charging stations and energy requirements of EV users. Fast and slow charging infrastructures are modeled separately to reflect their distinct regulation characteristics, while time-varying charging and discharging margins are derived from travel demand, parking duration, and state-of-charge preferences and further adjusted under extreme weather scenarios. Based on these dynamic constraints, an enhanced multi-agent soft actor–critic (MA-SAC) controller coordinates micro gas turbines and charging stations for distributed frequency regulation. Simulations demonstrate MA-SAC outperforms PID, Fuzzy, and MA-DDPG methods, achieving a 98.51% frequency excellent rate normally and 91.47% during extreme weather. It reduces maximum deviations by up to 80% versus PID, while preserving user travel requirements. The proposed framework provides a practical pathway for integrating electrified mobility into resilient smart-city MMG frequency regulation. 2026-05-21 Smart Cities, Vol. 9, Pages 88: Intelligent Load Frequency Control Strategy for Multi-Microgrids with Vehicle-to-Grid Considering Charging Diversity and Extreme Weather

Smart Cities doi: 10.3390/smartcities9050088

Authors: Chenxuan Zhang Peixiao Fan Siqi Bu

With the rapid electrification of urban transportation and increasing penetration of renewable energy, maintaining frequency stability in smart-city multi-microgrids (MMG) systems increasingly depends on coordinated vehicle-to-grid (V2G) flexibility. However, existing load frequency control strategies typically treat electric vehicles (EVs) as homogeneous resources and overlook the impacts of charging-infrastructure diversity, user mobility constraints, and extreme weather conditions on regulation availability. To address these challenges, this study proposes a weather-adaptive intelligent load frequency control strategy for smart-city MMG considering heterogeneous charging stations and energy requirements of EV users. Fast and slow charging infrastructures are modeled separately to reflect their distinct regulation characteristics, while time-varying charging and discharging margins are derived from travel demand, parking duration, and state-of-charge preferences and further adjusted under extreme weather scenarios. Based on these dynamic constraints, an enhanced multi-agent soft actor–critic (MA-SAC) controller coordinates micro gas turbines and charging stations for distributed frequency regulation. Simulations demonstrate MA-SAC outperforms PID, Fuzzy, and MA-DDPG methods, achieving a 98.51% frequency excellent rate normally and 91.47% during extreme weather. It reduces maximum deviations by up to 80% versus PID, while preserving user travel requirements. The proposed framework provides a practical pathway for integrating electrified mobility into resilient smart-city MMG frequency regulation.

]]> Intelligent Load Frequency Control Strategy for Multi-Microgrids with Vehicle-to-Grid Considering Charging Diversity and Extreme Weather Chenxuan Zhang Peixiao Fan Siqi Bu doi: 10.3390/smartcities9050088 Smart Cities 2026-05-21 Smart Cities 2026-05-21 9 5 Article 88 10.3390/smartcities9050088 https://www.mdpi.com/2624-6511/9/5/88 Smart Cities, Vol. 9, Pages 87: Feeder-Aware Coordination of Buildings, EVs, and DERs in Smart Cities: A Systematic Review of AI-, Digital-Twin-, and Interoperability-Enabled Approaches https://www.mdpi.com/2624-6511/9/5/87 Urban flexibility research is expanding across buildings, electric vehicles (EVs), distributed energy resources (DERs), storage, positive energy districts (PEDs), digital twins, and interoperability platforms. These strands are often reviewed separately, although urban distribution operators must manage their combined impacts on the same feeders. This paper presents a PRISMA 2020-aligned systematic review with evidence mapping and narrative synthesis of feeder-aware coordination in smart-city electricity systems. Searches of Scopus, Web of Science, IEEE Xplore, ScienceDirect, and citation chasing identified 312 records; 127 studies were included after screening and eligibility assessment, 101 entered the quantitative mapping sample, and 31 formed the deep-synthesis anchor core. Sparse contingency tables were analyzed with Monte-Carlo permutation chi-square tests and bootstrap confidence intervals for Cramér’s V, while ordinal variables were summarized with medians and interquartile ranges. Explicit feeder grounding was concentrated in grid-oriented and EV-oriented studies, whereas many AI/digital-twin and interoperability studies were less often validated against distribution-network operation. Economic and peak-flexibility indicators were reported far more often than interoperability, cybersecurity, or validation-maturity indicators in the anchor core. The synthesis also showed that deployment-oriented work depends on clearer treatment of standards, co-simulation workflows, regulatory instruments, and stakeholder roles. The evidence base is heterogeneous, English-only, and single-coded, so the quantitative results are descriptive rather than population-level. The review contributes a transparent three-layer corpus design (127 included/101 mapped/31 anchor), a domain-specific specialization of SGAM/IEEE 2030 for urban feeder orchestration, an operational digital-twin definition and validation ladder, a retrofittable benchmarking framework, and a practical roadmap for DSOs, municipalities, aggregators, EV operators, building managers, and ICT providers. 2026-05-20 Smart Cities, Vol. 9, Pages 87: Feeder-Aware Coordination of Buildings, EVs, and DERs in Smart Cities: A Systematic Review of AI-, Digital-Twin-, and Interoperability-Enabled Approaches

Smart Cities doi: 10.3390/smartcities9050087

Authors: Manuel Dario Jaramillo Diego Carrión Alexander Aguila Téllez

Urban flexibility research is expanding across buildings, electric vehicles (EVs), distributed energy resources (DERs), storage, positive energy districts (PEDs), digital twins, and interoperability platforms. These strands are often reviewed separately, although urban distribution operators must manage their combined impacts on the same feeders. This paper presents a PRISMA 2020-aligned systematic review with evidence mapping and narrative synthesis of feeder-aware coordination in smart-city electricity systems. Searches of Scopus, Web of Science, IEEE Xplore, ScienceDirect, and citation chasing identified 312 records; 127 studies were included after screening and eligibility assessment, 101 entered the quantitative mapping sample, and 31 formed the deep-synthesis anchor core. Sparse contingency tables were analyzed with Monte-Carlo permutation chi-square tests and bootstrap confidence intervals for Cramér’s V, while ordinal variables were summarized with medians and interquartile ranges. Explicit feeder grounding was concentrated in grid-oriented and EV-oriented studies, whereas many AI/digital-twin and interoperability studies were less often validated against distribution-network operation. Economic and peak-flexibility indicators were reported far more often than interoperability, cybersecurity, or validation-maturity indicators in the anchor core. The synthesis also showed that deployment-oriented work depends on clearer treatment of standards, co-simulation workflows, regulatory instruments, and stakeholder roles. The evidence base is heterogeneous, English-only, and single-coded, so the quantitative results are descriptive rather than population-level. The review contributes a transparent three-layer corpus design (127 included/101 mapped/31 anchor), a domain-specific specialization of SGAM/IEEE 2030 for urban feeder orchestration, an operational digital-twin definition and validation ladder, a retrofittable benchmarking framework, and a practical roadmap for DSOs, municipalities, aggregators, EV operators, building managers, and ICT providers.

]]> Feeder-Aware Coordination of Buildings, EVs, and DERs in Smart Cities: A Systematic Review of AI-, Digital-Twin-, and Interoperability-Enabled Approaches Manuel Dario Jaramillo Diego Carrión Alexander Aguila Téllez doi: 10.3390/smartcities9050087 Smart Cities 2026-05-20 Smart Cities 2026-05-20 9 5 Review 87 10.3390/smartcities9050087 https://www.mdpi.com/2624-6511/9/5/87 Smart Cities, Vol. 9, Pages 86: Acoustic Intelligence with Multi-Stage Model Optimization for Environmental Sound Classification https://www.mdpi.com/2624-6511/9/5/86 Environmental sound classification is an important component of smart city sensing systems, supporting applications such as urban noise analysis, public safety monitoring, and real-time situational awareness. However, high-accuracy models are often difficult to deploy on low-power edge devices because of memory, computational, and latency constraints. This study aims to address this deployment gap by developing a lightweight compression pipeline for a hybrid convolutional and Kolmogorov–Arnold Network-based model. The proposed pipeline consists of three stages. First, structured channel pruning is applied to remove redundant convolutional filters while preserving hardware-efficient dense operations. Second, selective quantization-aware training is applied to the most computation-dominant layers, namely the third convolutional layer and the fully connected layer. Third, knowledge distillation is used to recover accuracy by training the compressed model under the guidance of the baseline model. Experiments were conducted on ESC-10, ESC-50, FSC22, and UrbanSound8K. The proposed pipeline reduced the average parameter count from 511,033 to 50,774 and reduced the model size while maintaining competitive accuracy across all benchmarks. The final model preserved the baseline accuracy of 96.75% on ESC-10, while accuracy decreased only from 88.25% to 86.50% on ESC-50, from 87.92% to 86.38% on FSC22, and from 85.13% to 84.52% on UrbanSound8K. These results show that the proposed compression pipeline provides an effective accuracy–efficiency trade-off for real-time audio classification on resource-constrained devices. Therefore, the resulting compressed model supports the scalable deployment of distributed acoustic sensing systems for real-time smart city monitoring and decision-making. 2026-05-16 Smart Cities, Vol. 9, Pages 86: Acoustic Intelligence with Multi-Stage Model Optimization for Environmental Sound Classification

Smart Cities doi: 10.3390/smartcities9050086

Authors: Pasan Sarathchandra Senuri Mallikarachchi Dimalsha Madushani Dulani Meedeniya

Environmental sound classification is an important component of smart city sensing systems, supporting applications such as urban noise analysis, public safety monitoring, and real-time situational awareness. However, high-accuracy models are often difficult to deploy on low-power edge devices because of memory, computational, and latency constraints. This study aims to address this deployment gap by developing a lightweight compression pipeline for a hybrid convolutional and Kolmogorov–Arnold Network-based model. The proposed pipeline consists of three stages. First, structured channel pruning is applied to remove redundant convolutional filters while preserving hardware-efficient dense operations. Second, selective quantization-aware training is applied to the most computation-dominant layers, namely the third convolutional layer and the fully connected layer. Third, knowledge distillation is used to recover accuracy by training the compressed model under the guidance of the baseline model. Experiments were conducted on ESC-10, ESC-50, FSC22, and UrbanSound8K. The proposed pipeline reduced the average parameter count from 511,033 to 50,774 and reduced the model size while maintaining competitive accuracy across all benchmarks. The final model preserved the baseline accuracy of 96.75% on ESC-10, while accuracy decreased only from 88.25% to 86.50% on ESC-50, from 87.92% to 86.38% on FSC22, and from 85.13% to 84.52% on UrbanSound8K. These results show that the proposed compression pipeline provides an effective accuracy–efficiency trade-off for real-time audio classification on resource-constrained devices. Therefore, the resulting compressed model supports the scalable deployment of distributed acoustic sensing systems for real-time smart city monitoring and decision-making.

]]> Acoustic Intelligence with Multi-Stage Model Optimization for Environmental Sound Classification Pasan Sarathchandra Senuri Mallikarachchi Dimalsha Madushani Dulani Meedeniya doi: 10.3390/smartcities9050086 Smart Cities 2026-05-16 Smart Cities 2026-05-16 9 5 Article 86 10.3390/smartcities9050086 https://www.mdpi.com/2624-6511/9/5/86 Smart Cities, Vol. 9, Pages 85: Universal Robust Vehicle Identification System for Monitoring Using YOLOv12 and DeepSORT https://www.mdpi.com/2624-6511/9/5/85 Persistent traffic congestion and the need for efficient traffic monitoring have increased the demand for automated vehicle-analysis systems based on CCTV footage. This study presents a CCTV-based vehicle monitoring system that integrates vehicle detection, tracking, counting, public/private vehicle class prediction, seven-category vehicle-type prediction, vehicle-color recognition, and traffic-state estimation using YOLOv12 and DeepSORT. To reduce manual annotation effort during the initial training stage, a semi-automated method for generating synthetic composite road scenes was developed by combining cropped vehicle images and road-background images. The detector was first trained on 10,000 synthetic images and then sequentially fine-tuned on real CCTV data. Four real-world traffic video clips from Metro Manila were used in the study. Three 5 min clips were used within the staged refinement workflow: the first two for iterative refinement and the third for final post-refinement evaluation of the adapted model. A separate fourth CCTV clip was reserved exclusively for blind evaluation without on-the-fly retraining. The final system achieved average accuracies of 97% for public/private vehicle class prediction, 90% for seven-category vehicle-type prediction, 82% for vehicle-color recognition, and 96.67% for vehicle counting on the final evaluation video. The results show that synthetic pretraining combined with limited real-world fine-tuning can improve performance in CCTV-based vehicle monitoring while reducing the amount of manually labeled real-world data required. The study also discusses the limitations of the current evaluation protocol and the need for broader multi-location testing. 2026-05-15 Smart Cities, Vol. 9, Pages 85: Universal Robust Vehicle Identification System for Monitoring Using YOLOv12 and DeepSORT

Smart Cities doi: 10.3390/smartcities9050085

Authors: Leonard Ambata Elmer Jose Dadios

Persistent traffic congestion and the need for efficient traffic monitoring have increased the demand for automated vehicle-analysis systems based on CCTV footage. This study presents a CCTV-based vehicle monitoring system that integrates vehicle detection, tracking, counting, public/private vehicle class prediction, seven-category vehicle-type prediction, vehicle-color recognition, and traffic-state estimation using YOLOv12 and DeepSORT. To reduce manual annotation effort during the initial training stage, a semi-automated method for generating synthetic composite road scenes was developed by combining cropped vehicle images and road-background images. The detector was first trained on 10,000 synthetic images and then sequentially fine-tuned on real CCTV data. Four real-world traffic video clips from Metro Manila were used in the study. Three 5 min clips were used within the staged refinement workflow: the first two for iterative refinement and the third for final post-refinement evaluation of the adapted model. A separate fourth CCTV clip was reserved exclusively for blind evaluation without on-the-fly retraining. The final system achieved average accuracies of 97% for public/private vehicle class prediction, 90% for seven-category vehicle-type prediction, 82% for vehicle-color recognition, and 96.67% for vehicle counting on the final evaluation video. The results show that synthetic pretraining combined with limited real-world fine-tuning can improve performance in CCTV-based vehicle monitoring while reducing the amount of manually labeled real-world data required. The study also discusses the limitations of the current evaluation protocol and the need for broader multi-location testing.

]]> Universal Robust Vehicle Identification System for Monitoring Using YOLOv12 and DeepSORT Leonard Ambata Elmer Jose Dadios doi: 10.3390/smartcities9050085 Smart Cities 2026-05-15 Smart Cities 2026-05-15 9 5 Article 85 10.3390/smartcities9050085 https://www.mdpi.com/2624-6511/9/5/85 Smart Cities, Vol. 9, Pages 84: Resident Behavior-Driven Zonation and Optimization of Commercial Service Facilities at the Community Scale https://www.mdpi.com/2624-6511/9/5/84 Precise assessment of commercial service facilities (CSFs) is a vital pillar for megacity governance. However, existing evaluations rely on static population and 2D metrics, overlooking behavioral heterogeneity and 3D spatial supply at the micro scale. This study constructs a “3D Supply–Group Demand–Matching” framework at the community level. On the supply side, a Building Coupling Entropy (BCE) model integrates 3D volume and morphology to characterize service capacity. On the demand side, a dynamic behavioral model measures multi-group needs. Mismatch patterns are identified using the Entropy-modified Spatial Disparity Ratio (ESDR). Using Guangzhou as a case, the results reveal three paradigms: (1) Core districts exhibit rigid path dependency, where first-tier sub-districts rose from 48 to 51, and elderly service shortages in old areas plummeted by nearly 80% via micro-regeneration; (2) Growth poles show spatial fragmentation, with core labor demand spilling over but infrastructure lagging, creating a fast production–slow urbanism mismatch; (3) Far-suburban areas reduced extreme-shortage sub-districts from 38 to 34, identifying resource islands besieged by residential demand. Overall, the framework elucidates the shape–flow mismatch mechanism and provides a transferable basis for precision zonation governance, supporting a shift from static quantity-based allocation to dynamic quality-oriented provision in high-density megacities. 2026-05-15 Smart Cities, Vol. 9, Pages 84: Resident Behavior-Driven Zonation and Optimization of Commercial Service Facilities at the Community Scale

Smart Cities doi: 10.3390/smartcities9050084

Authors: Zeying Lan Beixi Lu Yuyi Bian Yang Liu Xiaohui Chen Jianhua He

Precise assessment of commercial service facilities (CSFs) is a vital pillar for megacity governance. However, existing evaluations rely on static population and 2D metrics, overlooking behavioral heterogeneity and 3D spatial supply at the micro scale. This study constructs a “3D Supply–Group Demand–Matching” framework at the community level. On the supply side, a Building Coupling Entropy (BCE) model integrates 3D volume and morphology to characterize service capacity. On the demand side, a dynamic behavioral model measures multi-group needs. Mismatch patterns are identified using the Entropy-modified Spatial Disparity Ratio (ESDR). Using Guangzhou as a case, the results reveal three paradigms: (1) Core districts exhibit rigid path dependency, where first-tier sub-districts rose from 48 to 51, and elderly service shortages in old areas plummeted by nearly 80% via micro-regeneration; (2) Growth poles show spatial fragmentation, with core labor demand spilling over but infrastructure lagging, creating a fast production–slow urbanism mismatch; (3) Far-suburban areas reduced extreme-shortage sub-districts from 38 to 34, identifying resource islands besieged by residential demand. Overall, the framework elucidates the shape–flow mismatch mechanism and provides a transferable basis for precision zonation governance, supporting a shift from static quantity-based allocation to dynamic quality-oriented provision in high-density megacities.

]]> Resident Behavior-Driven Zonation and Optimization of Commercial Service Facilities at the Community Scale Zeying Lan Beixi Lu Yuyi Bian Yang Liu Xiaohui Chen Jianhua He doi: 10.3390/smartcities9050084 Smart Cities 2026-05-15 Smart Cities 2026-05-15 9 5 Article 84 10.3390/smartcities9050084 https://www.mdpi.com/2624-6511/9/5/84 Smart Cities, Vol. 9, Pages 83: The Design and Evaluation of Nanogrid-Based Solar Photovoltaic Light-Emitting Diode Street Lighting Systems: A Techno-Economic and Voltage Drop Analysis for Secondary Roads in Thailand https://www.mdpi.com/2624-6511/9/5/83 Street lighting systems are essential for ensuring nighttime road safety and visibility. The integration of solar photovoltaic (PV) systems into street lighting infrastructure improves energy efficiency and sustainability; however, the mismatch between daytime energy generation and nighttime lighting demand requires effective energy management solutions. In addition, long-distance electrical connections introduce voltage drop constraints, which are often overlooked in conventional design approaches. This study addresses the integration of lighting design, electrical constraints, and techno-economic performance in nanogrid-based LED street lighting systems for secondary roads. A unified framework is developed to evaluate lighting performance, PV–battery sizing, voltage drop behavior, and lifecycle cost under different system architectures. Optimal pole spacing and luminaire ratings are determined using DIALux, while PV–battery configurations are optimized using HOMER Pro based on site-specific solar irradiance. The analysis focuses on voltage drop as the key electrical constraint and examines its impact under decentralized and centralized nanogrid configurations (25%, 50%, and 100%) in both stand-alone and grid-connected modes. The results show that increasing centralization reduces component redundancy but significantly increases cable length, conductor sizing, and infrastructure cost. A techno-economic assessment with lifecycle cost and sensitivity analysis indicates that a 25% centralized configuration reduces total system cost by approximately 23% compared to fully decentralized systems while avoiding excessive cabling costs. These findings demonstrate that voltage drop and electrical infrastructure constraints play a decisive role in determining optimal system design, highlighting the importance of system-level integration rather than isolated optimization of lighting or energy components. 2026-05-14 Smart Cities, Vol. 9, Pages 83: The Design and Evaluation of Nanogrid-Based Solar Photovoltaic Light-Emitting Diode Street Lighting Systems: A Techno-Economic and Voltage Drop Analysis for Secondary Roads in Thailand

Smart Cities doi: 10.3390/smartcities9050083

Authors: Sulee Bunjongjit Hongyan Wang Yansheng Huang Panapong Songsukthawan Suntiti Yoomak Santipont Ananwattanaporn

Street lighting systems are essential for ensuring nighttime road safety and visibility. The integration of solar photovoltaic (PV) systems into street lighting infrastructure improves energy efficiency and sustainability; however, the mismatch between daytime energy generation and nighttime lighting demand requires effective energy management solutions. In addition, long-distance electrical connections introduce voltage drop constraints, which are often overlooked in conventional design approaches. This study addresses the integration of lighting design, electrical constraints, and techno-economic performance in nanogrid-based LED street lighting systems for secondary roads. A unified framework is developed to evaluate lighting performance, PV–battery sizing, voltage drop behavior, and lifecycle cost under different system architectures. Optimal pole spacing and luminaire ratings are determined using DIALux, while PV–battery configurations are optimized using HOMER Pro based on site-specific solar irradiance. The analysis focuses on voltage drop as the key electrical constraint and examines its impact under decentralized and centralized nanogrid configurations (25%, 50%, and 100%) in both stand-alone and grid-connected modes. The results show that increasing centralization reduces component redundancy but significantly increases cable length, conductor sizing, and infrastructure cost. A techno-economic assessment with lifecycle cost and sensitivity analysis indicates that a 25% centralized configuration reduces total system cost by approximately 23% compared to fully decentralized systems while avoiding excessive cabling costs. These findings demonstrate that voltage drop and electrical infrastructure constraints play a decisive role in determining optimal system design, highlighting the importance of system-level integration rather than isolated optimization of lighting or energy components.

]]> The Design and Evaluation of Nanogrid-Based Solar Photovoltaic Light-Emitting Diode Street Lighting Systems: A Techno-Economic and Voltage Drop Analysis for Secondary Roads in Thailand Sulee Bunjongjit Hongyan Wang Yansheng Huang Panapong Songsukthawan Suntiti Yoomak Santipont Ananwattanaporn doi: 10.3390/smartcities9050083 Smart Cities 2026-05-14 Smart Cities 2026-05-14 9 5 Article 83 10.3390/smartcities9050083 https://www.mdpi.com/2624-6511/9/5/83 Smart Cities, Vol. 9, Pages 82: From Smart City Pilots to Institutionalised Urban Resilience: The Smart Urban Resilience Framework (SURF) https://www.mdpi.com/2624-6511/9/5/82 Australian local governments are increasingly deploying smart city technologies to manage climate-related shocks and chronic stresses, yet implementation often remains fragmented and difficult to embed in routine practice. Many initiatives stall in “pilot-forever” cycles because decision rights, equity safeguards, operational integration, and learning systems are applied inconsistently. This paper introduces the Smart Urban Resilience Framework (SURF), a phase-gated, tier-aware governance framework designed to support the institutionalisation of smart urban resilience through more transparent and evidence-based decision-making. The SURF is grounded in an integrated evidence-to-design synthesis drawing on a systematic review, a comparative analysis of Tier 1 and Tier 2 Australian local government strategies, an in-depth Sydney case study, and stakeholder interviews. Although empirically grounded in Australian local government, the SURF is designed as a governance architecture that may be adapted in comparable municipal settings elsewhere. The framework comprises a staged pathway, two evidence gates, and four concurrent action tracks, supported by enabling layers and traceable evidence tools. The SURF is presented as a practical implementation architecture intended to support more transparent and defensible decisions about funding, scaling, refining, or retiring smart resilience initiatives. In this paper, resilience is operationalised through a service continuity lens, focusing on how digital initiatives can be embedded in governance and delivery systems to support the continuity of essential local government services under stress. 2026-05-09 Smart Cities, Vol. 9, Pages 82: From Smart City Pilots to Institutionalised Urban Resilience: The Smart Urban Resilience Framework (SURF)

Smart Cities doi: 10.3390/smartcities9050082

Authors: Shabnam Varzeshi John Fien Leila Irajifar Anthony Kent

Australian local governments are increasingly deploying smart city technologies to manage climate-related shocks and chronic stresses, yet implementation often remains fragmented and difficult to embed in routine practice. Many initiatives stall in “pilot-forever” cycles because decision rights, equity safeguards, operational integration, and learning systems are applied inconsistently. This paper introduces the Smart Urban Resilience Framework (SURF), a phase-gated, tier-aware governance framework designed to support the institutionalisation of smart urban resilience through more transparent and evidence-based decision-making. The SURF is grounded in an integrated evidence-to-design synthesis drawing on a systematic review, a comparative analysis of Tier 1 and Tier 2 Australian local government strategies, an in-depth Sydney case study, and stakeholder interviews. Although empirically grounded in Australian local government, the SURF is designed as a governance architecture that may be adapted in comparable municipal settings elsewhere. The framework comprises a staged pathway, two evidence gates, and four concurrent action tracks, supported by enabling layers and traceable evidence tools. The SURF is presented as a practical implementation architecture intended to support more transparent and defensible decisions about funding, scaling, refining, or retiring smart resilience initiatives. In this paper, resilience is operationalised through a service continuity lens, focusing on how digital initiatives can be embedded in governance and delivery systems to support the continuity of essential local government services under stress.

]]> From Smart City Pilots to Institutionalised Urban Resilience: The Smart Urban Resilience Framework (SURF) Shabnam Varzeshi John Fien Leila Irajifar Anthony Kent doi: 10.3390/smartcities9050082 Smart Cities 2026-05-09 Smart Cities 2026-05-09 9 5 Article 82 10.3390/smartcities9050082 https://www.mdpi.com/2624-6511/9/5/82 Smart Cities, Vol. 9, Pages 81: Governing Urban AI from the Frontline: A Stage-Gate Framework for Municipal Algorithmic Decision-Making https://www.mdpi.com/2624-6511/9/5/81 Artificial intelligence (AI) is increasingly embedded in how cities are governed, shaping decisions on mobility, land use, public services, and environmental management. Yet urban AI is predominantly governed through fragmented frameworks designed at national or corporate scales, offering limited guidance for municipal decision-making and overlooking place-specific social and ecological consequences. As the level of government closest to everyday urban life, cities are uniquely positioned to steer AI toward public value, but face persistent tensions between efficiency, equity, accountability, and sustainability. This paper argues that responsible urban AI cannot be governed through top-down or one-size-fits-all approaches. To address this, the study aims to conceptualise and advance a ground-up model of responsible urban AI governance that places cities and local governments at the centre of decision-making. It addresses the following research question: How can municipal authorities translate high-level ethical principles into practical, context-sensitive governance arrangements that respond to local capacities, risks, and public values? Drawing on global governance principles and illustrative city experiences, we propose a locally grounded, stage-based framework for municipal AI governance. The framework addresses institutional capacity gaps, fragmented responsibilities, and algorithmic externalities, advancing a participatory, place-sensitive, and adaptive model that aligns urban AI innovation with democratic legitimacy, social justice, and sustainable urban futures. 2026-05-08 Smart Cities, Vol. 9, Pages 81: Governing Urban AI from the Frontline: A Stage-Gate Framework for Municipal Algorithmic Decision-Making

Smart Cities doi: 10.3390/smartcities9050081

Authors: Tan Yigitcanlar Anne David Raveena Marasinghe Sajani Senadheera Tahsin Hossain Xinyue Ye Araz Taeihagh

Artificial intelligence (AI) is increasingly embedded in how cities are governed, shaping decisions on mobility, land use, public services, and environmental management. Yet urban AI is predominantly governed through fragmented frameworks designed at national or corporate scales, offering limited guidance for municipal decision-making and overlooking place-specific social and ecological consequences. As the level of government closest to everyday urban life, cities are uniquely positioned to steer AI toward public value, but face persistent tensions between efficiency, equity, accountability, and sustainability. This paper argues that responsible urban AI cannot be governed through top-down or one-size-fits-all approaches. To address this, the study aims to conceptualise and advance a ground-up model of responsible urban AI governance that places cities and local governments at the centre of decision-making. It addresses the following research question: How can municipal authorities translate high-level ethical principles into practical, context-sensitive governance arrangements that respond to local capacities, risks, and public values? Drawing on global governance principles and illustrative city experiences, we propose a locally grounded, stage-based framework for municipal AI governance. The framework addresses institutional capacity gaps, fragmented responsibilities, and algorithmic externalities, advancing a participatory, place-sensitive, and adaptive model that aligns urban AI innovation with democratic legitimacy, social justice, and sustainable urban futures.

]]> Governing Urban AI from the Frontline: A Stage-Gate Framework for Municipal Algorithmic Decision-Making Tan Yigitcanlar Anne David Raveena Marasinghe Sajani Senadheera Tahsin Hossain Xinyue Ye Araz Taeihagh doi: 10.3390/smartcities9050081 Smart Cities 2026-05-08 Smart Cities 2026-05-08 9 5 Article 81 10.3390/smartcities9050081 https://www.mdpi.com/2624-6511/9/5/81 Smart Cities, Vol. 9, Pages 80: Experimental Evaluation of Serverless Data Layer Architectures for Smart City Internet of Things Applications https://www.mdpi.com/2624-6511/9/5/80 Comparative, experimentally grounded evidence for selecting smart city IoT data-layer architectures remains limited, complicating practical design decisions. This study provides an applied architecture decision-making guide by evaluating seven serverless data-layer architectures within a clearly defined service boundary (The Things Network, Azure-managed ingestion services, and Delta Lake persistence on object storage). Using a 21-day pilot deployment with nine LoRaWAN sensors, we compare ingestion completeness, median ingestion latency (estimated from TTN receive timestamps to Delta Lake commit times), cloud costs within an explicit boundary (ingestion, compute, and storage), and implementation/operational complexity proxies. Under the observed workload, TTN Storage Integration offers the lowest-cost archival ingestion via batching, Event Grid provides the most cost-effective near-real-time option among reliable pipelines, and Event Hubs demonstrates the highest ingestion completeness. The results are synthesized into practical guidance that maps common smart city application requirements to appropriate serverless ingestion patterns. 2026-05-01 Smart Cities, Vol. 9, Pages 80: Experimental Evaluation of Serverless Data Layer Architectures for Smart City Internet of Things Applications

Smart Cities doi: 10.3390/smartcities9050080

Authors: Victor Ariel Leal Sobral Jonathan L. Goodall

Comparative, experimentally grounded evidence for selecting smart city IoT data-layer architectures remains limited, complicating practical design decisions. This study provides an applied architecture decision-making guide by evaluating seven serverless data-layer architectures within a clearly defined service boundary (The Things Network, Azure-managed ingestion services, and Delta Lake persistence on object storage). Using a 21-day pilot deployment with nine LoRaWAN sensors, we compare ingestion completeness, median ingestion latency (estimated from TTN receive timestamps to Delta Lake commit times), cloud costs within an explicit boundary (ingestion, compute, and storage), and implementation/operational complexity proxies. Under the observed workload, TTN Storage Integration offers the lowest-cost archival ingestion via batching, Event Grid provides the most cost-effective near-real-time option among reliable pipelines, and Event Hubs demonstrates the highest ingestion completeness. The results are synthesized into practical guidance that maps common smart city application requirements to appropriate serverless ingestion patterns.

]]> Experimental Evaluation of Serverless Data Layer Architectures for Smart City Internet of Things Applications Victor Ariel Leal Sobral Jonathan L. Goodall doi: 10.3390/smartcities9050080 Smart Cities 2026-05-01 Smart Cities 2026-05-01 9 5 Article 80 10.3390/smartcities9050080 https://www.mdpi.com/2624-6511/9/5/80 Smart Cities, Vol. 9, Pages 79: Energy Consumption Forecasting in Public Nursing Homes Using Multivariable Regression Models https://www.mdpi.com/2624-6511/9/5/79 Buildings represent 40% of the European Union’s energy consumption and 36% of its greenhouse gas emissions. Nursing homes are among the buildings that consume the most energy. The objective of this study was to make predictive models of Energy Consumption, Energy Costs, and CO2 Emissions in nursing homes using different variables. To do this, data from 20 public nursing homes located in Extremadura (Spain) during the 2019–2023 period were analyzed. All the buildings were built or renovated between 1995 and 2009; the useful area and the number of residents were in the range of 1332–10,880 m2 and 24–254 residents. A statistical analysis was performed using multivariable linear regression. During the research, equations that allow for the estimation of the annual Energy Consumption, Energy Costs and CO2 Emissions of nursing homes, according to the useful area and number of residents, were found. The Radj2 was 0.9710, 0.9744 and 0.9742, respectively. The quality of the models obtained was contrasted using the mean absolute error (MAE), the relative error (RE) and the root mean square error (RMSE), together with the assessment of multicollinearity through the Variance Inflation Factor (VIF). The findings of this study may prove beneficial for stakeholders within the elder care sector. 2026-04-30 Smart Cities, Vol. 9, Pages 79: Energy Consumption Forecasting in Public Nursing Homes Using Multivariable Regression Models

Smart Cities doi: 10.3390/smartcities9050079

Authors: Miguel Gómez-Chaparro Alejandro Prieto-Fernández Manuel Botejara-Antúnez Justo García-Sanz-Calcedo

Buildings represent 40% of the European Union’s energy consumption and 36% of its greenhouse gas emissions. Nursing homes are among the buildings that consume the most energy. The objective of this study was to make predictive models of Energy Consumption, Energy Costs, and CO2 Emissions in nursing homes using different variables. To do this, data from 20 public nursing homes located in Extremadura (Spain) during the 2019–2023 period were analyzed. All the buildings were built or renovated between 1995 and 2009; the useful area and the number of residents were in the range of 1332–10,880 m2 and 24–254 residents. A statistical analysis was performed using multivariable linear regression. During the research, equations that allow for the estimation of the annual Energy Consumption, Energy Costs and CO2 Emissions of nursing homes, according to the useful area and number of residents, were found. The Radj2 was 0.9710, 0.9744 and 0.9742, respectively. The quality of the models obtained was contrasted using the mean absolute error (MAE), the relative error (RE) and the root mean square error (RMSE), together with the assessment of multicollinearity through the Variance Inflation Factor (VIF). The findings of this study may prove beneficial for stakeholders within the elder care sector.

]]> Energy Consumption Forecasting in Public Nursing Homes Using Multivariable Regression Models Miguel Gómez-Chaparro Alejandro Prieto-Fernández Manuel Botejara-Antúnez Justo García-Sanz-Calcedo doi: 10.3390/smartcities9050079 Smart Cities 2026-04-30 Smart Cities 2026-04-30 9 5 Article 79 10.3390/smartcities9050079 https://www.mdpi.com/2624-6511/9/5/79 Smart Cities, Vol. 9, Pages 78: A Recommendation Engine for Multimodal Transport Route Planning Using Shared Vehicles of Different Types https://www.mdpi.com/2624-6511/9/5/78 Vehicle-sharing platforms are constantly gaining ground in smart cities around the world, reducing the number of traditional fuel-based vehicles on the roads in busy areas and thus contributing to the development of a sustainable environment. On the other hand, the availability of a plethora of shared vehicles of different types across a city increases the need for their seamless combination, so that they are considered part of a unified transportation system within a smart city rather than independent solutions. In this work, we present a system that enables authorized users to gain access to shared vehicles of different transport modalities, allowing them to reach their destination without relying on a private car or public transport. For this purpose, we have used existing systems and techniques from different fields, such as recommendation systems, machine learning, and route planning, which provide appropriate multimodal routes while taking into consideration several parameters, including user demographics, vehicle status, environmental conditions, and road traffic congestion. The evaluation of the system using simulated data showed that it enables users to identify suitable multimodal routes, either through explicit preferences or by inferring them from historical data, and revealed limitations to be addressed in future work. 2026-04-29 Smart Cities, Vol. 9, Pages 78: A Recommendation Engine for Multimodal Transport Route Planning Using Shared Vehicles of Different Types

Smart Cities doi: 10.3390/smartcities9050078

Authors: Efthymios Chondrogiannis Leonidas Avdelas Antonis Litke Theodora Varvarigou

Vehicle-sharing platforms are constantly gaining ground in smart cities around the world, reducing the number of traditional fuel-based vehicles on the roads in busy areas and thus contributing to the development of a sustainable environment. On the other hand, the availability of a plethora of shared vehicles of different types across a city increases the need for their seamless combination, so that they are considered part of a unified transportation system within a smart city rather than independent solutions. In this work, we present a system that enables authorized users to gain access to shared vehicles of different transport modalities, allowing them to reach their destination without relying on a private car or public transport. For this purpose, we have used existing systems and techniques from different fields, such as recommendation systems, machine learning, and route planning, which provide appropriate multimodal routes while taking into consideration several parameters, including user demographics, vehicle status, environmental conditions, and road traffic congestion. The evaluation of the system using simulated data showed that it enables users to identify suitable multimodal routes, either through explicit preferences or by inferring them from historical data, and revealed limitations to be addressed in future work.

]]> A Recommendation Engine for Multimodal Transport Route Planning Using Shared Vehicles of Different Types Efthymios Chondrogiannis Leonidas Avdelas Antonis Litke Theodora Varvarigou doi: 10.3390/smartcities9050078 Smart Cities 2026-04-29 Smart Cities 2026-04-29 9 5 Article 78 10.3390/smartcities9050078 https://www.mdpi.com/2624-6511/9/5/78 Smart Cities, Vol. 9, Pages 77: Semantic Core for Sensor Telemetry Ingestion for Digital Twins https://www.mdpi.com/2624-6511/9/5/77 Digital twin platforms for smart cities must continuously receive different types of data from sensors, gateways, and services, but in real situations these data are heterogeneous in terms of indicator names, measurement units, time rules, and object identification, which makes integrations expensive and fragile, while second verification becomes complicated. In this paper, a minimal semantic core for “first-stage” telemetry receiving of the DTwin platform, where semantics are used as operational rules during data ingestion. The core includes a machine-readable model of entities and relationships, dictionaries of metrics and measurement units, a unified event format with separation into a stable envelope and payload, formal validation against data schemas, a mapping table for transforming raw fields into standardized measurements [name, value, unit], as well as an ingestion service with canonicalization of the event record and integrity control through the SHA-256 cryptographic hash. The implementation ensures ingestion of correct events, rejection of incorrect ones without recording, and reproducible verification through control examples, a testing protocol, and evidence snapshots. In smart city settings, such a telemetry ingestion foundation can support reliable monitoring of municipal buildings and infrastructure, including energy efficiency, indoor environmental quality, and data-driven operational decision-making. The proposed approach establishes a core for the stable integration of different sensor data into digital twins and further scaling of the platform. 2026-04-28 Smart Cities, Vol. 9, Pages 77: Semantic Core for Sensor Telemetry Ingestion for Digital Twins

Smart Cities doi: 10.3390/smartcities9050077

Authors: Oleksandr Osolinskyi Khrystyna Lipianina-Honcharenko Myroslav Komar

Digital twin platforms for smart cities must continuously receive different types of data from sensors, gateways, and services, but in real situations these data are heterogeneous in terms of indicator names, measurement units, time rules, and object identification, which makes integrations expensive and fragile, while second verification becomes complicated. In this paper, a minimal semantic core for “first-stage” telemetry receiving of the DTwin platform, where semantics are used as operational rules during data ingestion. The core includes a machine-readable model of entities and relationships, dictionaries of metrics and measurement units, a unified event format with separation into a stable envelope and payload, formal validation against data schemas, a mapping table for transforming raw fields into standardized measurements [name, value, unit], as well as an ingestion service with canonicalization of the event record and integrity control through the SHA-256 cryptographic hash. The implementation ensures ingestion of correct events, rejection of incorrect ones without recording, and reproducible verification through control examples, a testing protocol, and evidence snapshots. In smart city settings, such a telemetry ingestion foundation can support reliable monitoring of municipal buildings and infrastructure, including energy efficiency, indoor environmental quality, and data-driven operational decision-making. The proposed approach establishes a core for the stable integration of different sensor data into digital twins and further scaling of the platform.

]]> Semantic Core for Sensor Telemetry Ingestion for Digital Twins Oleksandr Osolinskyi Khrystyna Lipianina-Honcharenko Myroslav Komar doi: 10.3390/smartcities9050077 Smart Cities 2026-04-28 Smart Cities 2026-04-28 9 5 Article 77 10.3390/smartcities9050077 https://www.mdpi.com/2624-6511/9/5/77 Smart Cities, Vol. 9, Pages 76: Cybersecurity and Regulatory Compliance in Smart Cities: A Comprehensive Review https://www.mdpi.com/2624-6511/9/5/76 Smart cities increasingly rely on urban digital systems deployed across domains such as mobility, public safety, surveillance, and governance, involving large-scale collection and processing of sensitive data. These systems raise significant cybersecurity and privacy challenges, shaped by European regulatory frameworks that influence how data are collected, secured, shared, and governed within urban environments. While existing research has examined legal and regulatory aspects alongside technical cybersecurity solutions, these areas are often addressed in isolation, limiting insight into how regulatory requirements translate into concrete implementations. This paper presents a comprehensive review of regulatory-driven cybersecurity approaches for smart cities. It maps the literature across major application domains and analyses how regulatory objectives are reflected in technical, organisational, and operational measures, as well as in implemented solutions. By jointly examining legal and technical perspectives, the review links regulatory compliance requirements with concrete security practices and system-level design choices. Based on this analysis, the paper proposes a structured classification of regulatory-driven smart city approaches and identifies key trends, gaps, and challenges in the literature. The findings provide a foundation for future research on regulatory-driven cybersecurity and privacy protection in smart systems. 2026-04-28 Smart Cities, Vol. 9, Pages 76: Cybersecurity and Regulatory Compliance in Smart Cities: A Comprehensive Review

Smart Cities doi: 10.3390/smartcities9050076

Authors: Maria Papaioannou Mila Georgieva Valcheva Metehan Gelgi Lejla Islami Lars Sommer

Smart cities increasingly rely on urban digital systems deployed across domains such as mobility, public safety, surveillance, and governance, involving large-scale collection and processing of sensitive data. These systems raise significant cybersecurity and privacy challenges, shaped by European regulatory frameworks that influence how data are collected, secured, shared, and governed within urban environments. While existing research has examined legal and regulatory aspects alongside technical cybersecurity solutions, these areas are often addressed in isolation, limiting insight into how regulatory requirements translate into concrete implementations. This paper presents a comprehensive review of regulatory-driven cybersecurity approaches for smart cities. It maps the literature across major application domains and analyses how regulatory objectives are reflected in technical, organisational, and operational measures, as well as in implemented solutions. By jointly examining legal and technical perspectives, the review links regulatory compliance requirements with concrete security practices and system-level design choices. Based on this analysis, the paper proposes a structured classification of regulatory-driven smart city approaches and identifies key trends, gaps, and challenges in the literature. The findings provide a foundation for future research on regulatory-driven cybersecurity and privacy protection in smart systems.

]]> Cybersecurity and Regulatory Compliance in Smart Cities: A Comprehensive Review Maria Papaioannou Mila Georgieva Valcheva Metehan Gelgi Lejla Islami Lars Sommer doi: 10.3390/smartcities9050076 Smart Cities 2026-04-28 Smart Cities 2026-04-28 9 5 Review 76 10.3390/smartcities9050076 https://www.mdpi.com/2624-6511/9/5/76 Smart Cities, Vol. 9, Pages 75: Stress-Aware Stackelberg Pricing for Probabilistic Grid Impact Mitigation of Bidirectional EVs https://www.mdpi.com/2624-6511/9/5/75 This paper presents an integrated techno–economic framework for coordinated grid-to-vehicle and vehicle-to-grid (G2V–V2G) operation in unbalanced distribution networks. A hardware-compatible bidirectional charger with nested AC/DC and DC/DC control loops, together with a rule-based energy management system (EMS), enables seamless mode transitions while enforcing state-of-charge (SoC) and network constraints. A probabilistic Monte Carlo study on the IEEE 13-bus feeder shows that uncoordinated G2V charging induces adverse grid impacts such as voltage stress, line-ampacity violations, and transformer overloading, whereas EMS-driven V2G support improves voltage by 2–4%, reduces line loading by 15–25%, and lowers transformer stress by up to 10%. To align these technical benefits with economic incentives, a bi-level Stackelberg model is formulated where the utility updates locational energy prices based on combined voltage, line ampacity, transformer loading stress indices and EVs choose profit-maximizing nodes, modes and power levels. The interaction converges to a Stackelberg equilibrium with a clear win–win situation; the feeder’s average locational energy price falls entirely within the win–win region, yielding positive per-session profits for both the EV (≈$0.80) and the utility (≈$0.48) while reducing feeder stress. These results demonstrate that stress-aware locational pricing, combined with detailed converter-level control provides a technically robust and economically sustainable pathway for large-scale EV integration. 2026-04-22 Smart Cities, Vol. 9, Pages 75: Stress-Aware Stackelberg Pricing for Probabilistic Grid Impact Mitigation of Bidirectional EVs

Smart Cities doi: 10.3390/smartcities9050075

Authors: Amit Hasan Abir Kazi N. Hasan Asif Islam Mohammad AlMuhaini

This paper presents an integrated techno–economic framework for coordinated grid-to-vehicle and vehicle-to-grid (G2V–V2G) operation in unbalanced distribution networks. A hardware-compatible bidirectional charger with nested AC/DC and DC/DC control loops, together with a rule-based energy management system (EMS), enables seamless mode transitions while enforcing state-of-charge (SoC) and network constraints. A probabilistic Monte Carlo study on the IEEE 13-bus feeder shows that uncoordinated G2V charging induces adverse grid impacts such as voltage stress, line-ampacity violations, and transformer overloading, whereas EMS-driven V2G support improves voltage by 2–4%, reduces line loading by 15–25%, and lowers transformer stress by up to 10%. To align these technical benefits with economic incentives, a bi-level Stackelberg model is formulated where the utility updates locational energy prices based on combined voltage, line ampacity, transformer loading stress indices and EVs choose profit-maximizing nodes, modes and power levels. The interaction converges to a Stackelberg equilibrium with a clear win–win situation; the feeder’s average locational energy price falls entirely within the win–win region, yielding positive per-session profits for both the EV (≈$0.80) and the utility (≈$0.48) while reducing feeder stress. These results demonstrate that stress-aware locational pricing, combined with detailed converter-level control provides a technically robust and economically sustainable pathway for large-scale EV integration.

]]> Stress-Aware Stackelberg Pricing for Probabilistic Grid Impact Mitigation of Bidirectional EVs Amit Hasan Abir Kazi N. Hasan Asif Islam Mohammad AlMuhaini doi: 10.3390/smartcities9050075 Smart Cities 2026-04-22 Smart Cities 2026-04-22 9 5 Article 75 10.3390/smartcities9050075 https://www.mdpi.com/2624-6511/9/5/75 Smart Cities, Vol. 9, Pages 74: A Review of Machine Learning Modeling Approaches of Spatiotemporal Urbanization and Land Use Land Cover https://www.mdpi.com/2624-6511/9/5/74 Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), is transforming the modeling of complex spatiotemporal urban processes such as urban growth, sprawl, shrinkage, redevelopment, and Land Use/Land Cover Change (LULCC). However, despite rapid methodological innovation, applications remain fragmented, and there is limited synthesis of how AI-based models complement, extend, or supersede conventional approaches. This study addresses this gap through a systematic review of 6356 records, from which 120 articles were selected for detailed analysis. It investigates: (i) how ML/DL techniques are embedded within spatiotemporal modeling frameworks; (ii) their use in simulating urbanization dynamics and land-use (LU) transitions; (iii) methodological and performance gains relative to traditional statistical and rule-based models; and (iv) emerging research frontiers and limitations. The review shows that LULCC dominates current applications, with Artificial Neural Networks (ANNs) as the most prevalent ML method, increasingly complemented by DL architectures. Across cases, AI is primarily used to learn non-linear transition dynamics, represent spatial and temporal dependencies, identify influential drivers, and improve classification performance and computational efficiency. Building on these insights, the paper synthesizes the roles of AI in spatiotemporal urban modeling and outlines forward-looking research directions to support more robust, transparent, and policy-relevant applications for urban sustainability. 2026-04-22 Smart Cities, Vol. 9, Pages 74: A Review of Machine Learning Modeling Approaches of Spatiotemporal Urbanization and Land Use Land Cover

Smart Cities doi: 10.3390/smartcities9050074

Authors: Farasath Hasan Jian Liu Xintao Liu

Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), is transforming the modeling of complex spatiotemporal urban processes such as urban growth, sprawl, shrinkage, redevelopment, and Land Use/Land Cover Change (LULCC). However, despite rapid methodological innovation, applications remain fragmented, and there is limited synthesis of how AI-based models complement, extend, or supersede conventional approaches. This study addresses this gap through a systematic review of 6356 records, from which 120 articles were selected for detailed analysis. It investigates: (i) how ML/DL techniques are embedded within spatiotemporal modeling frameworks; (ii) their use in simulating urbanization dynamics and land-use (LU) transitions; (iii) methodological and performance gains relative to traditional statistical and rule-based models; and (iv) emerging research frontiers and limitations. The review shows that LULCC dominates current applications, with Artificial Neural Networks (ANNs) as the most prevalent ML method, increasingly complemented by DL architectures. Across cases, AI is primarily used to learn non-linear transition dynamics, represent spatial and temporal dependencies, identify influential drivers, and improve classification performance and computational efficiency. Building on these insights, the paper synthesizes the roles of AI in spatiotemporal urban modeling and outlines forward-looking research directions to support more robust, transparent, and policy-relevant applications for urban sustainability.

]]> A Review of Machine Learning Modeling Approaches of Spatiotemporal Urbanization and Land Use Land Cover Farasath Hasan Jian Liu Xintao Liu doi: 10.3390/smartcities9050074 Smart Cities 2026-04-22 Smart Cities 2026-04-22 9 5 Review 74 10.3390/smartcities9050074 https://www.mdpi.com/2624-6511/9/5/74 Smart Cities, Vol. 9, Pages 73: AICEBERG: A Novel Agentic AI Framework for Autonomous Radio Monitoring, Compliance and Governance Based on LLM, MCP, and SCPI in Smart Cities https://www.mdpi.com/2624-6511/9/5/73 Urban radio spectrum monitoring is becoming increasingly complex due to the rapid growth of wireless devices, unauthorized emissions, and dynamic electromagnetic environments in smart cities. Traditional spectrum analysis approaches, based on manual operation or static detection techniques, are no longer sufficient to ensure scalable, autonomous, and secure monitoring. The convergence of two emergent technologies—Large Language Models (LLMs) and the Model Context Protocol (MCP)—facilitates a fundamental shift in radio monitoring. We define this as the AICEBERG paradigm: a novel, stratified architecture where a high-level, intelligent agentic interface (the peak) abstracts the underlying complexity of SCPI-driven hardware integration and radio governance protocols (the foundational base). This autonomous framework provides the necessary objective rigor to audit the stochastic ‘ocean of electromagnetic waves’ characteristic of modern smart cities, ensuring a stable platform for regulatory enforcement amidst high-density signal interference. The proposed system implements a three-layer processing flow, enabling high-level natural language commands to be translated into validated and secure hardware actions on RF spectrum analyzers. A dual-server design separates operational execution from safety validation, ensuring controlled SCPI command handling, parameter verification, and instrument health monitoring. Experimental validation demonstrates the feasibility of autonomous measurement execution. The results show that the proposed architecture reduces human dependency, enhances reproducibility and lowers the expertise barrier required for RF spectrum surveillance. To the best of our knowledge, AICEBERG represents one of the first integrated frameworks to bridge LLMs with SCPI-compliant hardware through the MCP for autonomous radio governance. 2026-04-22 Smart Cities, Vol. 9, Pages 73: AICEBERG: A Novel Agentic AI Framework for Autonomous Radio Monitoring, Compliance and Governance Based on LLM, MCP, and SCPI in Smart Cities

Smart Cities doi: 10.3390/smartcities9050073

Authors: Florin Popescu Denis Stanescu

Urban radio spectrum monitoring is becoming increasingly complex due to the rapid growth of wireless devices, unauthorized emissions, and dynamic electromagnetic environments in smart cities. Traditional spectrum analysis approaches, based on manual operation or static detection techniques, are no longer sufficient to ensure scalable, autonomous, and secure monitoring. The convergence of two emergent technologies—Large Language Models (LLMs) and the Model Context Protocol (MCP)—facilitates a fundamental shift in radio monitoring. We define this as the AICEBERG paradigm: a novel, stratified architecture where a high-level, intelligent agentic interface (the peak) abstracts the underlying complexity of SCPI-driven hardware integration and radio governance protocols (the foundational base). This autonomous framework provides the necessary objective rigor to audit the stochastic ‘ocean of electromagnetic waves’ characteristic of modern smart cities, ensuring a stable platform for regulatory enforcement amidst high-density signal interference. The proposed system implements a three-layer processing flow, enabling high-level natural language commands to be translated into validated and secure hardware actions on RF spectrum analyzers. A dual-server design separates operational execution from safety validation, ensuring controlled SCPI command handling, parameter verification, and instrument health monitoring. Experimental validation demonstrates the feasibility of autonomous measurement execution. The results show that the proposed architecture reduces human dependency, enhances reproducibility and lowers the expertise barrier required for RF spectrum surveillance. To the best of our knowledge, AICEBERG represents one of the first integrated frameworks to bridge LLMs with SCPI-compliant hardware through the MCP for autonomous radio governance.

]]> AICEBERG: A Novel Agentic AI Framework for Autonomous Radio Monitoring, Compliance and Governance Based on LLM, MCP, and SCPI in Smart Cities Florin Popescu Denis Stanescu doi: 10.3390/smartcities9050073 Smart Cities 2026-04-22 Smart Cities 2026-04-22 9 5 Article 73 10.3390/smartcities9050073 https://www.mdpi.com/2624-6511/9/5/73 Smart Cities, Vol. 9, Pages 72: An Intelligent Arterial Traffic Control Framework for Visible Light-Connected Vehicles https://www.mdpi.com/2624-6511/9/4/72 Inefficient urban traffic management remains a critical challenge, as conventional signal controllers—built on fixed timing plans—cannot cope with the dynamic nature of modern city traffic. This study addresses this limitation by developing a decentralized MARL-based framework capable of coordinating five interconnected intersections as a unified traffic cell. Central to the proposed solution is the Strategic Anti-Blocking Phase Adjustment (SAPA) module, which enables intersections to autonomously modify phase durations in response to real-time traffic conditions. The framework is designed to handle heterogeneous demand patterns, with particular emphasis on arterial corridors connecting urban centers to peripheral zones. Integration of a Visible Light Communication (VLC) network allows continuous monitoring of key variables, including vehicle kinematics and pedestrian activity, feeding the agents with rich environmental feedback. Experimental evaluation confirms the effectiveness of the approach: the SAPA-augmented DQN achieves roughly 33% shorter vehicle queues and a ~70% reduction in pedestrian waiting counts relative to a standard DQN baseline. Remarkably, these gains bring the value-based method to a performance level comparable to MAPPO, a considerably more complex multi-agent policy optimization algorithm, establishing SAPA as an efficient and scalable enhancement for intelligent urban traffic control. 2026-04-20 Smart Cities, Vol. 9, Pages 72: An Intelligent Arterial Traffic Control Framework for Visible Light-Connected Vehicles

Smart Cities doi: 10.3390/smartcities9040072

Authors: Gonçalo Galvão Manuela Vieira Manuel Augusto Vieira Mário Véstias Paula Louro

Inefficient urban traffic management remains a critical challenge, as conventional signal controllers—built on fixed timing plans—cannot cope with the dynamic nature of modern city traffic. This study addresses this limitation by developing a decentralized MARL-based framework capable of coordinating five interconnected intersections as a unified traffic cell. Central to the proposed solution is the Strategic Anti-Blocking Phase Adjustment (SAPA) module, which enables intersections to autonomously modify phase durations in response to real-time traffic conditions. The framework is designed to handle heterogeneous demand patterns, with particular emphasis on arterial corridors connecting urban centers to peripheral zones. Integration of a Visible Light Communication (VLC) network allows continuous monitoring of key variables, including vehicle kinematics and pedestrian activity, feeding the agents with rich environmental feedback. Experimental evaluation confirms the effectiveness of the approach: the SAPA-augmented DQN achieves roughly 33% shorter vehicle queues and a ~70% reduction in pedestrian waiting counts relative to a standard DQN baseline. Remarkably, these gains bring the value-based method to a performance level comparable to MAPPO, a considerably more complex multi-agent policy optimization algorithm, establishing SAPA as an efficient and scalable enhancement for intelligent urban traffic control.

]]> An Intelligent Arterial Traffic Control Framework for Visible Light-Connected Vehicles Gonçalo Galvão Manuela Vieira Manuel Augusto Vieira Mário Véstias Paula Louro doi: 10.3390/smartcities9040072 Smart Cities 2026-04-20 Smart Cities 2026-04-20 9 4 Article 72 10.3390/smartcities9040072 https://www.mdpi.com/2624-6511/9/4/72 Smart Cities, Vol. 9, Pages 71: Reframing BIM and Digital Twins for Intelligent Built Environments https://www.mdpi.com/2624-6511/9/4/71 The integration of Building Information Modeling [BIM] and Digital Twins [DT] has emerged as a central driver of digital transformation in the architecture, engineering, and construction sector. Yet, its systemic impact remains constrained by conceptual fragmentation and uneven institutional adoption. This study synthesizes contemporary BIM–DT scalability and each to identify dominant technological and application dimensions, examine the governance conditions shaping scalability, and develop an analytical framework that advances understanding beyond technology-centered syntheses. A two-stage analytical design was employed, combining bibliometric keyword co-occurrence analysis of 1295 Scopus-indexed records with systematic qualitative synthesis of 56 peer-reviewed journal articles published between 2020 and 2025, following PRISMA guidelines. Six interrelated analytical dimensions characterize the current BIM–DT research landscape: BIM–DT integration advancements and applications; interoperability and visualization; safety enhancement; energy efficiency; data-driven decision making; and stakeholder collaboration. Across these dimensions, a persistent misalignment emerges between technological capability and organizational readiness, with deficiencies in standards, governance, and sociotechnical coordination constituting the principal barriers to large-scale deployment. The findings reframe BIM–DT convergence not as a discrete technological upgrade but as the emergence of a coordinated socio-technical information ecosystem spanning the full building lifecycle. By foregrounding governance conditions, data stewardship, and institutional coordination, this study extends understanding of how digital twins expand BIM from design coordination to operational governance and establishes a foundation for more systematic implementation of intelligent, resilient, and sustainable built-environment systems. 2026-04-17 Smart Cities, Vol. 9, Pages 71: Reframing BIM and Digital Twins for Intelligent Built Environments

Smart Cities doi: 10.3390/smartcities9040071

Authors: Abdullahi Abdulrahman Muhudin Md Shafiullah Baqer Al-Ramadan Mohammad Sharif Zami Mohammad Tahir Zamani Lazhari Herzallah

The integration of Building Information Modeling [BIM] and Digital Twins [DT] has emerged as a central driver of digital transformation in the architecture, engineering, and construction sector. Yet, its systemic impact remains constrained by conceptual fragmentation and uneven institutional adoption. This study synthesizes contemporary BIM–DT scalability and each to identify dominant technological and application dimensions, examine the governance conditions shaping scalability, and develop an analytical framework that advances understanding beyond technology-centered syntheses. A two-stage analytical design was employed, combining bibliometric keyword co-occurrence analysis of 1295 Scopus-indexed records with systematic qualitative synthesis of 56 peer-reviewed journal articles published between 2020 and 2025, following PRISMA guidelines. Six interrelated analytical dimensions characterize the current BIM–DT research landscape: BIM–DT integration advancements and applications; interoperability and visualization; safety enhancement; energy efficiency; data-driven decision making; and stakeholder collaboration. Across these dimensions, a persistent misalignment emerges between technological capability and organizational readiness, with deficiencies in standards, governance, and sociotechnical coordination constituting the principal barriers to large-scale deployment. The findings reframe BIM–DT convergence not as a discrete technological upgrade but as the emergence of a coordinated socio-technical information ecosystem spanning the full building lifecycle. By foregrounding governance conditions, data stewardship, and institutional coordination, this study extends understanding of how digital twins expand BIM from design coordination to operational governance and establishes a foundation for more systematic implementation of intelligent, resilient, and sustainable built-environment systems.

]]> Reframing BIM and Digital Twins for Intelligent Built Environments Abdullahi Abdulrahman Muhudin Md Shafiullah Baqer Al-Ramadan Mohammad Sharif Zami Mohammad Tahir Zamani Lazhari Herzallah doi: 10.3390/smartcities9040071 Smart Cities 2026-04-17 Smart Cities 2026-04-17 9 4 Systematic Review 71 10.3390/smartcities9040071 https://www.mdpi.com/2624-6511/9/4/71 Smart Cities, Vol. 9, Pages 70: Wavelet–Deep Learning Framework for High-Resolution Fault Detection, Classification, and Localization in WMU-Enabled Distribution Systems https://www.mdpi.com/2624-6511/9/4/70 Timely fault detection, classification, and localization are fundamental to enabling fast service restoration in modern distribution networks, and are especially vital for maintaining the reliability and resilience of smart city electricity infrastructures. A new AI-based method for classifying and localizing fault types is presented in this paper, which enhances situational awareness in smart distribution grids that supply dense urban loads and critical smart city services. The proposed approach targets various fault conditions, which include three-phase-to-ground, three-phase, two-phase-to-ground, two-phase, and single-phase-to-ground faults. The proposed method utilizes a wavelet-based signal processing technique to analyze the feeder’s current data captured by waveform measurement units (WMUs) and extracts features for fault analysis. As a result of these features, a multi-stage machine learning architecture incorporating deep learning components is developed to accurately determine the occurrence, type, and location of faults. To evaluate the performance of the proposed approach, simulations were conducted on a 16-bus distribution network. Results show a high level of accuracy in fault detection, classification, and localization. This indicates that the method can be a valuable tool for enhancing the resilience and intelligence of future power grids, as well as supporting self-healing and fast service restoration in smart city services. 2026-04-16 Smart Cities, Vol. 9, Pages 70: Wavelet–Deep Learning Framework for High-Resolution Fault Detection, Classification, and Localization in WMU-Enabled Distribution Systems

Smart Cities doi: 10.3390/smartcities9040070

Authors: Dariush Salehi Navid Vafamand Shayan Soltani Innocent Kamwa Abbas Rabiee

Timely fault detection, classification, and localization are fundamental to enabling fast service restoration in modern distribution networks, and are especially vital for maintaining the reliability and resilience of smart city electricity infrastructures. A new AI-based method for classifying and localizing fault types is presented in this paper, which enhances situational awareness in smart distribution grids that supply dense urban loads and critical smart city services. The proposed approach targets various fault conditions, which include three-phase-to-ground, three-phase, two-phase-to-ground, two-phase, and single-phase-to-ground faults. The proposed method utilizes a wavelet-based signal processing technique to analyze the feeder’s current data captured by waveform measurement units (WMUs) and extracts features for fault analysis. As a result of these features, a multi-stage machine learning architecture incorporating deep learning components is developed to accurately determine the occurrence, type, and location of faults. To evaluate the performance of the proposed approach, simulations were conducted on a 16-bus distribution network. Results show a high level of accuracy in fault detection, classification, and localization. This indicates that the method can be a valuable tool for enhancing the resilience and intelligence of future power grids, as well as supporting self-healing and fast service restoration in smart city services.

]]> Wavelet–Deep Learning Framework for High-Resolution Fault Detection, Classification, and Localization in WMU-Enabled Distribution Systems Dariush Salehi Navid Vafamand Shayan Soltani Innocent Kamwa Abbas Rabiee doi: 10.3390/smartcities9040070 Smart Cities 2026-04-16 Smart Cities 2026-04-16 9 4 Article 70 10.3390/smartcities9040070 https://www.mdpi.com/2624-6511/9/4/70 Smart Cities, Vol. 9, Pages 69: Co-Optimized Scheduling of a Multi-Microgrid System Based on a Reputation Point Trading Mechanism https://www.mdpi.com/2624-6511/9/4/69 With the rapid integration of distributed energy resources, achieving a balance between economic efficiency and environmental sustainability in multi-microgrid (MMG) systems is critical. However, existing studies typically treat microgrid operators as fully compliant entities. They often neglect the “trust-risk” dimension along with potential default behaviors in decentralized markets. This paper proposes a novel co-optimized scheduling model for urban MMG systems, centered on a unified “Social–Economic–Physical” coupling framework. To ensure transaction integrity, a robust reputation evaluation framework is developed using Root Mean Square Error (RMSE), mean absolute error (MAE), plus Dynamic Time Warping (DTW). This framework effectively identifies fraudulent data or contractual breaches. Furthermore, to enhance fairness while promoting decarbonization, the model integrates a dynamic network pricing strategy based on the Shapley value. It works alongside a reputation-weighted reward–penalty step-type carbon trading scheme. The proposed model is formulated as a mixed-integer linear programming (MILP) problem and solved using MATLAB R2025b with CPLEX 12.10. Simulation results demonstrate that the integrated approach significantly optimizes system performance. Total carbon emissions are reduced by 49.6 tons. Meanwhile, revenues for the MMG Alliance, individual microgrids, and shared energy storage operators increase by 4.08% to 33.00%. The proposed framework provides a practical governance solution for Smart City multi-microgrid systems, effectively addressing the “trust-risk” challenge in decentralized urban energy markets. The findings validate that the proposed mechanism effectively fosters a trustworthy trading environment, achieving a “win-win” outcome for economic profitability and urban energy resilience. 2026-04-15 Smart Cities, Vol. 9, Pages 69: Co-Optimized Scheduling of a Multi-Microgrid System Based on a Reputation Point Trading Mechanism

Smart Cities doi: 10.3390/smartcities9040069

Authors: Jiankai Fang Dongmei Yan Hongkun Wang Hui Deng Xinyu Meng Hong Zhang

With the rapid integration of distributed energy resources, achieving a balance between economic efficiency and environmental sustainability in multi-microgrid (MMG) systems is critical. However, existing studies typically treat microgrid operators as fully compliant entities. They often neglect the “trust-risk” dimension along with potential default behaviors in decentralized markets. This paper proposes a novel co-optimized scheduling model for urban MMG systems, centered on a unified “Social–Economic–Physical” coupling framework. To ensure transaction integrity, a robust reputation evaluation framework is developed using Root Mean Square Error (RMSE), mean absolute error (MAE), plus Dynamic Time Warping (DTW). This framework effectively identifies fraudulent data or contractual breaches. Furthermore, to enhance fairness while promoting decarbonization, the model integrates a dynamic network pricing strategy based on the Shapley value. It works alongside a reputation-weighted reward–penalty step-type carbon trading scheme. The proposed model is formulated as a mixed-integer linear programming (MILP) problem and solved using MATLAB R2025b with CPLEX 12.10. Simulation results demonstrate that the integrated approach significantly optimizes system performance. Total carbon emissions are reduced by 49.6 tons. Meanwhile, revenues for the MMG Alliance, individual microgrids, and shared energy storage operators increase by 4.08% to 33.00%. The proposed framework provides a practical governance solution for Smart City multi-microgrid systems, effectively addressing the “trust-risk” challenge in decentralized urban energy markets. The findings validate that the proposed mechanism effectively fosters a trustworthy trading environment, achieving a “win-win” outcome for economic profitability and urban energy resilience.

]]> Co-Optimized Scheduling of a Multi-Microgrid System Based on a Reputation Point Trading Mechanism Jiankai Fang Dongmei Yan Hongkun Wang Hui Deng Xinyu Meng Hong Zhang doi: 10.3390/smartcities9040069 Smart Cities 2026-04-15 Smart Cities 2026-04-15 9 4 Article 69 10.3390/smartcities9040069 https://www.mdpi.com/2624-6511/9/4/69 Smart Cities, Vol. 9, Pages 68: Enhancing Smart Building Energy Resilience: A Novel Parallel-Series PV Architecture for Urban Partial Shading Mitigation https://www.mdpi.com/2624-6511/9/4/68 Building-integrated photovoltaic systems are essential components of smart buildings and sustainable urban infrastructure, contributing to energy efficiency and carbon footprint reduction in smart cities. Mismatch loss, particularly under partial shading, is one of the concerns in photovoltaic (PV) systems, especially in urban environments where buildings, trees, and other structures create complex shading patterns. It leads to significant power loss and poor efficiency. Several methods, such as string converters, multi-string converters, central converters, and micro-inverters/power optimizers, have been widely employed to address this issue. These methods suffer from hardware complexity and are good in certain shading patterns only; they remain ineffective otherwise. Power optimizers lead in efficiency under all the shading patterns, whereas string converters lead in hardware simplicity. We propose a novel parallel-series converter to mitigate mismatch losses in smart building applications that is as efficient as power optimizers and as simple as converters. In the proposed parallel-series converter design, multiple PV modules are connected in parallel to a very simple converter, and many such converters are then connected in series to get the final output. The proposed converter is rigorously evaluated for various shading patterns using MATLAB/SIMULINK. A prototype system of 3×2 PV panels is also developed for hardware evaluation. The simulation and hardware results show that the proposed parallel-series converter dominantly competes with power optimizers with much simpler hardware and outperforms the other converters, making it particularly suitable for smart building energy systems where cost-effectiveness and reliability are critical. 2026-04-13 Smart Cities, Vol. 9, Pages 68: Enhancing Smart Building Energy Resilience: A Novel Parallel-Series PV Architecture for Urban Partial Shading Mitigation

Smart Cities doi: 10.3390/smartcities9040068

Authors: Tanveer Abbas Syed Talha Safeer Gardezi Noman Khan Adnan Khan Shakeel Ahmed Kambiz Tehrani

Building-integrated photovoltaic systems are essential components of smart buildings and sustainable urban infrastructure, contributing to energy efficiency and carbon footprint reduction in smart cities. Mismatch loss, particularly under partial shading, is one of the concerns in photovoltaic (PV) systems, especially in urban environments where buildings, trees, and other structures create complex shading patterns. It leads to significant power loss and poor efficiency. Several methods, such as string converters, multi-string converters, central converters, and micro-inverters/power optimizers, have been widely employed to address this issue. These methods suffer from hardware complexity and are good in certain shading patterns only; they remain ineffective otherwise. Power optimizers lead in efficiency under all the shading patterns, whereas string converters lead in hardware simplicity. We propose a novel parallel-series converter to mitigate mismatch losses in smart building applications that is as efficient as power optimizers and as simple as converters. In the proposed parallel-series converter design, multiple PV modules are connected in parallel to a very simple converter, and many such converters are then connected in series to get the final output. The proposed converter is rigorously evaluated for various shading patterns using MATLAB/SIMULINK. A prototype system of 3×2 PV panels is also developed for hardware evaluation. The simulation and hardware results show that the proposed parallel-series converter dominantly competes with power optimizers with much simpler hardware and outperforms the other converters, making it particularly suitable for smart building energy systems where cost-effectiveness and reliability are critical.

]]> Enhancing Smart Building Energy Resilience: A Novel Parallel-Series PV Architecture for Urban Partial Shading Mitigation Tanveer Abbas Syed Talha Safeer Gardezi Noman Khan Adnan Khan Shakeel Ahmed Kambiz Tehrani doi: 10.3390/smartcities9040068 Smart Cities 2026-04-13 Smart Cities 2026-04-13 9 4 Article 68 10.3390/smartcities9040068 https://www.mdpi.com/2624-6511/9/4/68 Smart Cities, Vol. 9, Pages 67: Towards a Temporal City: Time of Day as a Structural Dimension of Urban Accessibility https://www.mdpi.com/2624-6511/9/4/67 Urban accessibility is commonly evaluated using static spatial indicators, which assume stable travel conditions throughout the day. Road congestion, network saturation, and service variability change the function and experience of the built environment (BE). This study tests the Temporal City Framework (TCF) by examining how time of day (TOD) reshapes urban accessibility and travel behaviour with varying levels of congestion. Using 30,288 trip records from the 2022 US National Household Travel Survey (NHTS), duration is operationalised as a sixth dimension of the BE. A time-normalised impedance metric, measured in minutes per mile (MPM), is used that captures realised congestion independently of distance. Temporal impedance (TI) varies strongly with TOD, with substantially higher MPM during peak and midday periods than at night. Compared with nighttime conditions, midday travel requires approximately 19% more time per mile. This indicates a measurable contraction in functional accessibility under identical BE conditions. The TI model outperforms duration-only models, with impedance remaining dominant when both measures are included. These results support interpreting duration as a structural dimension of urban accessibility. TI significantly increases the relative likelihood of active and public transport compared to private cars, even after accounting for absolute trip duration. Hired transport modes (taxi and ride-hailing services) are most prevalent at night, reflecting a greater reliance on on-demand services outside regular daytime schedules. This study tests duration as a structural dimension of the BE by operationalising time-normalised TI. Associations are interpreted as trip-level behavioural constraints rather than causal effects. Planning frameworks based on static travel times systematically misrepresent exposure, equity, and travel mode feasibility. Time-stratified accessibility metrics should therefore be integrated into transport and land-use evaluation and associated policies. 2026-04-10 Smart Cities, Vol. 9, Pages 67: Towards a Temporal City: Time of Day as a Structural Dimension of Urban Accessibility

Smart Cities doi: 10.3390/smartcities9040067

Authors: Irfan Arif Fahim Ullah Siddra Qayyum Mahboobeh Jafari

Urban accessibility is commonly evaluated using static spatial indicators, which assume stable travel conditions throughout the day. Road congestion, network saturation, and service variability change the function and experience of the built environment (BE). This study tests the Temporal City Framework (TCF) by examining how time of day (TOD) reshapes urban accessibility and travel behaviour with varying levels of congestion. Using 30,288 trip records from the 2022 US National Household Travel Survey (NHTS), duration is operationalised as a sixth dimension of the BE. A time-normalised impedance metric, measured in minutes per mile (MPM), is used that captures realised congestion independently of distance. Temporal impedance (TI) varies strongly with TOD, with substantially higher MPM during peak and midday periods than at night. Compared with nighttime conditions, midday travel requires approximately 19% more time per mile. This indicates a measurable contraction in functional accessibility under identical BE conditions. The TI model outperforms duration-only models, with impedance remaining dominant when both measures are included. These results support interpreting duration as a structural dimension of urban accessibility. TI significantly increases the relative likelihood of active and public transport compared to private cars, even after accounting for absolute trip duration. Hired transport modes (taxi and ride-hailing services) are most prevalent at night, reflecting a greater reliance on on-demand services outside regular daytime schedules. This study tests duration as a structural dimension of the BE by operationalising time-normalised TI. Associations are interpreted as trip-level behavioural constraints rather than causal effects. Planning frameworks based on static travel times systematically misrepresent exposure, equity, and travel mode feasibility. Time-stratified accessibility metrics should therefore be integrated into transport and land-use evaluation and associated policies.

]]> Towards a Temporal City: Time of Day as a Structural Dimension of Urban Accessibility Irfan Arif Fahim Ullah Siddra Qayyum Mahboobeh Jafari doi: 10.3390/smartcities9040067 Smart Cities 2026-04-10 Smart Cities 2026-04-10 9 4 Article 67 10.3390/smartcities9040067 https://www.mdpi.com/2624-6511/9/4/67 Smart Cities, Vol. 9, Pages 66: A Timed Petri Net-Based Dynamic Visitor Guidance Model for Mountain Scenic Areas During Peak Periods https://www.mdpi.com/2624-6511/9/4/66 Tourist congestion and load imbalance during peak periods pose critical challenges to the safe operation and experience assurance of large scenic areas. To address the limitations of traditional management approaches in capturing the dynamic and stochastic nature of tourist flows, this study develops a dynamic visitor guidance modeling and analysis framework based on a Timed Petri Net. The proposed model provides a formal representation of tourist movements, scenic spot load evolution, and guidance decision mechanisms within a scenic area. Under unified parameter settings and controlled random conditions, multiple visitor guidance strategies with different information coverage scopes are designed, and minute-level simulation experiments are conducted using the Huangshan Scenic Area as a case study. The simulation results show that, compared with unguided tourist flows, the proposed strategies significantly reduce average load levels, alleviate spatial load imbalance, and enhance TS. Using mean–standard deviation analysis, distributional analysis, and dynamic evolution analysis, differences among guidance strategies in terms of load control, visitor experience, and operational stability are systematically evaluated. Furthermore, a quantitative relationship model between tourist satisfaction and scenic area load is constructed, revealing a consistent inverted-U pattern. Robustness tests under multiple random seeds indicate that the main conclusions are not sensitive to specific stochastic realizations. Overall, the simulation results suggest that dynamic visitor guidance may improve load control, visitor experience, and system stability by optimizing the spatiotemporal distribution of tourist flows, thereby providing simulation-based quantitative insights for peak-period management in large scenic areas. 2026-04-10 Smart Cities, Vol. 9, Pages 66: A Timed Petri Net-Based Dynamic Visitor Guidance Model for Mountain Scenic Areas During Peak Periods

Smart Cities doi: 10.3390/smartcities9040066

Authors: Binyou Wang Liyan Lu Changyong Liang Xiaohan Yan Shuping Zhao Wenxing Lu

Tourist congestion and load imbalance during peak periods pose critical challenges to the safe operation and experience assurance of large scenic areas. To address the limitations of traditional management approaches in capturing the dynamic and stochastic nature of tourist flows, this study develops a dynamic visitor guidance modeling and analysis framework based on a Timed Petri Net. The proposed model provides a formal representation of tourist movements, scenic spot load evolution, and guidance decision mechanisms within a scenic area. Under unified parameter settings and controlled random conditions, multiple visitor guidance strategies with different information coverage scopes are designed, and minute-level simulation experiments are conducted using the Huangshan Scenic Area as a case study. The simulation results show that, compared with unguided tourist flows, the proposed strategies significantly reduce average load levels, alleviate spatial load imbalance, and enhance TS. Using mean–standard deviation analysis, distributional analysis, and dynamic evolution analysis, differences among guidance strategies in terms of load control, visitor experience, and operational stability are systematically evaluated. Furthermore, a quantitative relationship model between tourist satisfaction and scenic area load is constructed, revealing a consistent inverted-U pattern. Robustness tests under multiple random seeds indicate that the main conclusions are not sensitive to specific stochastic realizations. Overall, the simulation results suggest that dynamic visitor guidance may improve load control, visitor experience, and system stability by optimizing the spatiotemporal distribution of tourist flows, thereby providing simulation-based quantitative insights for peak-period management in large scenic areas.

]]> A Timed Petri Net-Based Dynamic Visitor Guidance Model for Mountain Scenic Areas During Peak Periods Binyou Wang Liyan Lu Changyong Liang Xiaohan Yan Shuping Zhao Wenxing Lu doi: 10.3390/smartcities9040066 Smart Cities 2026-04-10 Smart Cities 2026-04-10 9 4 Article 66 10.3390/smartcities9040066 https://www.mdpi.com/2624-6511/9/4/66 Smart Cities, Vol. 9, Pages 64: The Role and Significance of Rail Transport in the Decarbonisation of the EU Transport Sector https://www.mdpi.com/2624-6511/9/4/64 Globally, the transport sector accounts for almost a quarter of CO2 emissions from fuel combustion and generates large amounts of pollutants, placing significant pressure on the environment and human health. By 2050, the European Green Deal requires a 90% reduction in transport-related emissions, making sustainability necessary across all modes of transport. Based on the relevant literature, this study examines the role and potential of railways in decarbonising the EU transport sector. Railway is highly efficient, consuming just 1.9% of transport sector energy while handling 16.9% of freight and 5.1% of passenger transport in the EU, yet is responsible for only 0.4% of total emissions. According to studies, greenhouse gas emissions can be reduced by improving energy efficiency, using low-carbon or renewable energy, and expanding train electrification. The greatest potential for decarbonisation lies in a modal shift to rail. However, this requires significant infrastructure investment: raising line speeds to at least 160 km/h, expanding networks, building terminals, digitalisation, and alignment with TEN-T standards. Although the EU supports the modal shift with funding programmes, the transition is not progressing as expected—the share of road freight transport increased from 74% in 2013 to 78% in 2023. Stronger investment is needed in Member States’ national policies for the development and modernisation of railways. The authors developed a Path Evaluation Matrix (PEM), a quantitative decision framework integrating the fields of energy, transport, politics, and economics. The PEM results indicate that BEMU (battery electric multiple units) is optimal for 68% of secondary lines in south-eastern Europe. 2026-04-07 Smart Cities, Vol. 9, Pages 64: The Role and Significance of Rail Transport in the Decarbonisation of the EU Transport Sector

Smart Cities doi: 10.3390/smartcities9040064

Authors: Mladen Bošnjaković Robert Santa Maja Čuletić Čondrić

Globally, the transport sector accounts for almost a quarter of CO2 emissions from fuel combustion and generates large amounts of pollutants, placing significant pressure on the environment and human health. By 2050, the European Green Deal requires a 90% reduction in transport-related emissions, making sustainability necessary across all modes of transport. Based on the relevant literature, this study examines the role and potential of railways in decarbonising the EU transport sector. Railway is highly efficient, consuming just 1.9% of transport sector energy while handling 16.9% of freight and 5.1% of passenger transport in the EU, yet is responsible for only 0.4% of total emissions. According to studies, greenhouse gas emissions can be reduced by improving energy efficiency, using low-carbon or renewable energy, and expanding train electrification. The greatest potential for decarbonisation lies in a modal shift to rail. However, this requires significant infrastructure investment: raising line speeds to at least 160 km/h, expanding networks, building terminals, digitalisation, and alignment with TEN-T standards. Although the EU supports the modal shift with funding programmes, the transition is not progressing as expected—the share of road freight transport increased from 74% in 2013 to 78% in 2023. Stronger investment is needed in Member States’ national policies for the development and modernisation of railways. The authors developed a Path Evaluation Matrix (PEM), a quantitative decision framework integrating the fields of energy, transport, politics, and economics. The PEM results indicate that BEMU (battery electric multiple units) is optimal for 68% of secondary lines in south-eastern Europe.

]]> The Role and Significance of Rail Transport in the Decarbonisation of the EU Transport Sector Mladen Bošnjaković Robert Santa Maja Čuletić Čondrić doi: 10.3390/smartcities9040064 Smart Cities 2026-04-07 Smart Cities 2026-04-07 9 4 Review 64 10.3390/smartcities9040064 https://www.mdpi.com/2624-6511/9/4/64 Smart Cities, Vol. 9, Pages 65: BiLSTM Guided LPA Planning, Re-Planning, and Backtracking for Effective and Efficient Emergency Evacuation https://www.mdpi.com/2624-6511/9/4/65 Emergency evacuation in complex and dynamic building environments requires robust and adaptive routing strategies capable of responding to evolving hazards, blocked passages, and changing crowd behaviour. Most existing evacuation planners rely on static geometric representations and lack semantic awareness of the environment, limiting their ability to perform informed re-planning and backtracking when routes become unsafe. This paper proposes a neuro-symbolic evacuation planning framework that integrates Lifelong Planning A* (LPA*) with ontology-driven semantic reasoning and a Bidirectional Long Short-Term Memory (BiLSTM) prediction model. The building’s spatial and semantic knowledge is represented using the Web Ontology Language (OWL) and Resource Description Framework (RDF), enabling automated inference of implicit connections and enforcement of safety policies. The BiLSTM model learns temporal patterns from ontology-consistent evacuation trajectories and provides guidance for remaining-cost estimation and early prediction of routes likely to require backtracking, which is combined with a bounded semantic heuristic to preserve admissibility and optimality guarantees. Simulation results in a multi-floor academic building show that the proposed BiLSTM-guided semantic LPA* framework reduces average evacuation time by up to 9.6%, decreases node expansions by up to 32%, and increases evacuation success rates to 96.2% compared with a purely semantic baseline. The BiLSTM model also achieves strong predictive performance, with a test AUC of 0.92 for backtracking prediction and a next-state accuracy of 87.1%. The proposed framework is designed to support explainable, policy-compliant, and incrementally adaptable evacuation guidance under rapidly evolving emergency conditions. 2026-04-07 Smart Cities, Vol. 9, Pages 65: BiLSTM Guided LPA Planning, Re-Planning, and Backtracking for Effective and Efficient Emergency Evacuation

Smart Cities doi: 10.3390/smartcities9040065

Authors: Ramzi Djemai Hamza Kheddar Mohamed Chahine Ghanem Karim Ouazzane Erivelton Nepomuceno

Emergency evacuation in complex and dynamic building environments requires robust and adaptive routing strategies capable of responding to evolving hazards, blocked passages, and changing crowd behaviour. Most existing evacuation planners rely on static geometric representations and lack semantic awareness of the environment, limiting their ability to perform informed re-planning and backtracking when routes become unsafe. This paper proposes a neuro-symbolic evacuation planning framework that integrates Lifelong Planning A* (LPA*) with ontology-driven semantic reasoning and a Bidirectional Long Short-Term Memory (BiLSTM) prediction model. The building’s spatial and semantic knowledge is represented using the Web Ontology Language (OWL) and Resource Description Framework (RDF), enabling automated inference of implicit connections and enforcement of safety policies. The BiLSTM model learns temporal patterns from ontology-consistent evacuation trajectories and provides guidance for remaining-cost estimation and early prediction of routes likely to require backtracking, which is combined with a bounded semantic heuristic to preserve admissibility and optimality guarantees. Simulation results in a multi-floor academic building show that the proposed BiLSTM-guided semantic LPA* framework reduces average evacuation time by up to 9.6%, decreases node expansions by up to 32%, and increases evacuation success rates to 96.2% compared with a purely semantic baseline. The BiLSTM model also achieves strong predictive performance, with a test AUC of 0.92 for backtracking prediction and a next-state accuracy of 87.1%. The proposed framework is designed to support explainable, policy-compliant, and incrementally adaptable evacuation guidance under rapidly evolving emergency conditions.

]]> BiLSTM Guided LPA Planning, Re-Planning, and Backtracking for Effective and Efficient Emergency Evacuation Ramzi Djemai Hamza Kheddar Mohamed Chahine Ghanem Karim Ouazzane Erivelton Nepomuceno doi: 10.3390/smartcities9040065 Smart Cities 2026-04-07 Smart Cities 2026-04-07 9 4 Article 65 10.3390/smartcities9040065 https://www.mdpi.com/2624-6511/9/4/65 Smart Cities, Vol. 9, Pages 63: Next Generation of Smart Grid Technologies https://www.mdpi.com/2624-6511/9/4/63 The emergence of smart cities demands a fundamental transformation in how energy is managed, positioning smart grid technologies as a key driver in urban progress [...] 2026-04-05 Smart Cities, Vol. 9, Pages 63: Next Generation of Smart Grid Technologies

Smart Cities doi: 10.3390/smartcities9040063

Authors: Luis M. Fernández-Ramírez Chun Sing Lai Payman Dehghanian

The emergence of smart cities demands a fundamental transformation in how energy is managed, positioning smart grid technologies as a key driver in urban progress [...]

]]> Next Generation of Smart Grid Technologies Luis M. Fernández-Ramírez Chun Sing Lai Payman Dehghanian doi: 10.3390/smartcities9040063 Smart Cities 2026-04-05 Smart Cities 2026-04-05 9 4 Editorial 63 10.3390/smartcities9040063 https://www.mdpi.com/2624-6511/9/4/63 Smart Cities, Vol. 9, Pages 62: Rethinking Pooled Ride-Hailing as Large-Scale Simulations Reveal System Limits https://www.mdpi.com/2624-6511/9/4/62 Over nearly two decades, ride-hailing has become a major component of urban travel, and its tendency to increase vehicle miles traveled (VMT) and worsen congestion is now well established. What remains poorly understood is why pooling, the most frequently proposed remedy, consistently falls short of theoretical expectations. With access to proprietary platform data still limited, high-fidelity simulation offers a promising path to untangle these dynamics. Here, we implement three pooling algorithms alongside a demand-following repositioning algorithm, within Berkeley Lab’s BEAM (Behavior, Energy, Autonomy, and Mobility), an open-source, agent-based regional transportation model. In a high ride-hailing adoption scenario for the San Francisco Bay Area, we find a counterintuitive result: the more stringently point-to-point pooling is promoted, the more detour burdens erode matching feasibility and reduce vehicle occupancy rather than increase it, thereby compounding rather than offsetting VMT and congestion impacts. Sensitivity analysis further identifies inflection points in pooling match rates and repositioning sensitivity beyond which deadheading and negative network feedbacks begin to dominate. These results show that pooled ride-hailing has a constrained ability to reduce network-wide impacts and that effective shared mobility requires treating pooling, repositioning, and fleet sizing as interdependent levers. 2026-04-01 Smart Cities, Vol. 9, Pages 62: Rethinking Pooled Ride-Hailing as Large-Scale Simulations Reveal System Limits

Smart Cities doi: 10.3390/smartcities9040062

Authors: Haitam Laarabi Zachary A. Needell Rashid A. Waraich C. Anna Spurlock

Over nearly two decades, ride-hailing has become a major component of urban travel, and its tendency to increase vehicle miles traveled (VMT) and worsen congestion is now well established. What remains poorly understood is why pooling, the most frequently proposed remedy, consistently falls short of theoretical expectations. With access to proprietary platform data still limited, high-fidelity simulation offers a promising path to untangle these dynamics. Here, we implement three pooling algorithms alongside a demand-following repositioning algorithm, within Berkeley Lab’s BEAM (Behavior, Energy, Autonomy, and Mobility), an open-source, agent-based regional transportation model. In a high ride-hailing adoption scenario for the San Francisco Bay Area, we find a counterintuitive result: the more stringently point-to-point pooling is promoted, the more detour burdens erode matching feasibility and reduce vehicle occupancy rather than increase it, thereby compounding rather than offsetting VMT and congestion impacts. Sensitivity analysis further identifies inflection points in pooling match rates and repositioning sensitivity beyond which deadheading and negative network feedbacks begin to dominate. These results show that pooled ride-hailing has a constrained ability to reduce network-wide impacts and that effective shared mobility requires treating pooling, repositioning, and fleet sizing as interdependent levers.

]]> Rethinking Pooled Ride-Hailing as Large-Scale Simulations Reveal System Limits Haitam Laarabi Zachary A. Needell Rashid A. Waraich C. Anna Spurlock doi: 10.3390/smartcities9040062 Smart Cities 2026-04-01 Smart Cities 2026-04-01 9 4 Article 62 10.3390/smartcities9040062 https://www.mdpi.com/2624-6511/9/4/62 Smart Cities, Vol. 9, Pages 61: Intelligence Collision Detection Using a Combination of Tuning Base Methods and Convolutional Long Short Term Memory Models https://www.mdpi.com/2624-6511/9/4/61 Effective traffic control using Artificial Intelligence (AI) is essential to ensure safe passage for all road users. AI-based collision detection systems offer advanced mechanisms to prevent accidents and improve highway safety. This research investigates two distinct collision scenarios: vehicle–pedestrian and vehicle–motorcyclist interactions. The proposed method in this research involves the bidirectional Long Short Term Memory (LSTM), Convolutional Neural Network with LSTM (CNN–LSTM), and transformer models. The model is furthermore tuned using random or grid search. For the pedestrian–vehicle scenario, the CNN–LSTM model achieved 99.76% accuracy, 99.77% precision, and 99.76% recall, highlighting its strong classification performance. In the vehicle–motorcyclist scenario, the bidirectional LSTM reached 99.73% accuracy with precision and recall of 99.15%, demonstrating its effectiveness in detecting imminent crashes. The optimized CNN-LSTM by random search has focused on decreasing the false-positive rate and increasing the positive rate. It has achieved superior results compared to previous research. These results suggest that the system could be effectively implemented as an early collision warning solution on edge devices. 2026-03-31 Smart Cities, Vol. 9, Pages 61: Intelligence Collision Detection Using a Combination of Tuning Base Methods and Convolutional Long Short Term Memory Models

Smart Cities doi: 10.3390/smartcities9040061

Authors: Mohammed Hilfi Lubna Alazzawi

Effective traffic control using Artificial Intelligence (AI) is essential to ensure safe passage for all road users. AI-based collision detection systems offer advanced mechanisms to prevent accidents and improve highway safety. This research investigates two distinct collision scenarios: vehicle–pedestrian and vehicle–motorcyclist interactions. The proposed method in this research involves the bidirectional Long Short Term Memory (LSTM), Convolutional Neural Network with LSTM (CNN–LSTM), and transformer models. The model is furthermore tuned using random or grid search. For the pedestrian–vehicle scenario, the CNN–LSTM model achieved 99.76% accuracy, 99.77% precision, and 99.76% recall, highlighting its strong classification performance. In the vehicle–motorcyclist scenario, the bidirectional LSTM reached 99.73% accuracy with precision and recall of 99.15%, demonstrating its effectiveness in detecting imminent crashes. The optimized CNN-LSTM by random search has focused on decreasing the false-positive rate and increasing the positive rate. It has achieved superior results compared to previous research. These results suggest that the system could be effectively implemented as an early collision warning solution on edge devices.

]]> Intelligence Collision Detection Using a Combination of Tuning Base Methods and Convolutional Long Short Term Memory Models Mohammed Hilfi Lubna Alazzawi doi: 10.3390/smartcities9040061 Smart Cities 2026-03-31 Smart Cities 2026-03-31 9 4 Article 61 10.3390/smartcities9040061 https://www.mdpi.com/2624-6511/9/4/61 Smart Cities, Vol. 9, Pages 60: Cost-Effective Planning of Station-Based Car-Sharing Systems: Increasing Efficiency While Emphasizing User Comfort https://www.mdpi.com/2624-6511/9/4/60 Station-based car-sharing has been shown to reduce resource-intensive private car ownership. However, only a small proportion of the population uses station-based car-sharing, which could be improved by redesigning the service to reduce walking distances and increase availability. We developed a method for designing an efficient and cost-effective station-based car-sharing network for smart cities that emphasizes user comfort and convenience, while reducing the number of needed cars. To quantify the placements, we created a high-resolution synthetic population for Munich, Germany as a case study. The population was based on census and OpenStreetMap data, and each person was assigned to a suitable mobility plan derived from two mobility surveys. Since car ownership and station-based car-sharing are particularly associated with trips for vacations, we supplemented the mobility plans with long-distance travel data from a one-year tracking dataset. This allowed us to perform a spatial and temporal analysis of the theoretical potential of various station placements for station-based car-sharing. The tested station networks varied in user comfort, especially in the distance to the nearest station and the group size of car-sharing users. Our findings indicate that the best trade-off between convenience and efficiency is a station design with a group size of 217–949 people. We further found that the car-sharing fleet size is strongly influenced by long-distance trips, and that a substitution rate of 1:1.25 to 3.3 with private cars is possible. 2026-03-28 Smart Cities, Vol. 9, Pages 60: Cost-Effective Planning of Station-Based Car-Sharing Systems: Increasing Efficiency While Emphasizing User Comfort

Smart Cities doi: 10.3390/smartcities9040060

Authors: Nico Nachtigall Markus Lienkamp

Station-based car-sharing has been shown to reduce resource-intensive private car ownership. However, only a small proportion of the population uses station-based car-sharing, which could be improved by redesigning the service to reduce walking distances and increase availability. We developed a method for designing an efficient and cost-effective station-based car-sharing network for smart cities that emphasizes user comfort and convenience, while reducing the number of needed cars. To quantify the placements, we created a high-resolution synthetic population for Munich, Germany as a case study. The population was based on census and OpenStreetMap data, and each person was assigned to a suitable mobility plan derived from two mobility surveys. Since car ownership and station-based car-sharing are particularly associated with trips for vacations, we supplemented the mobility plans with long-distance travel data from a one-year tracking dataset. This allowed us to perform a spatial and temporal analysis of the theoretical potential of various station placements for station-based car-sharing. The tested station networks varied in user comfort, especially in the distance to the nearest station and the group size of car-sharing users. Our findings indicate that the best trade-off between convenience and efficiency is a station design with a group size of 217–949 people. We further found that the car-sharing fleet size is strongly influenced by long-distance trips, and that a substitution rate of 1:1.25 to 3.3 with private cars is possible.

]]> Cost-Effective Planning of Station-Based Car-Sharing Systems: Increasing Efficiency While Emphasizing User Comfort Nico Nachtigall Markus Lienkamp doi: 10.3390/smartcities9040060 Smart Cities 2026-03-28 Smart Cities 2026-03-28 9 4 Article 60 10.3390/smartcities9040060 https://www.mdpi.com/2624-6511/9/4/60 Smart Cities, Vol. 9, Pages 59: Advanced Multivariate Deep Learning Methodology for Forecasting Wind Speed and Solar Irradiation https://www.mdpi.com/2624-6511/9/4/59 The transition to smart cities is accelerating distributed wind and solar deployment. However, their intermittency challenges grid operation, thereby making accurate machine-learning-based prediction of wind speed and global horizontal irradiance (GHI) crucial. This study presents a cost-effective approach that enhances prediction accuracy by extracting additional features from timestamp records for deep learning models used to forecast GHI and wind speed. Unlike conventional methods that require onsite meteorological measurements, the proposed approach uses only date and time information as inputs to multivariate deep neural networks, including recurrent neural networks, gated recurrent units, long short-term memory (LSTM), bidirectional LSTM, and convolutional neural networks. For wind speed prediction, the proposed configuration achieves R2 up to 0.9987, with RMSE as low as 0.067 m/s for 3 d ahead forecasting, outperforming univariate baselines and matching models. For GHI forecasting, the time-based configuration attains R2 values above 0.9994 in 12 h ahead predictions, with the RMSE reduced to approximately 4.47 W/m2, representing a substantial improvement over univariate models. The proposed framework maintains strong performance, particularly under clear and sunny conditions. These results demonstrate that timestamp-engineered features can deliver forecasting accuracy comparable to conventional multivariate meteorological models while significantly reducing infrastructure requirements, making the approach well-suited for scalable smart city energy management. 2026-03-27 Smart Cities, Vol. 9, Pages 59: Advanced Multivariate Deep Learning Methodology for Forecasting Wind Speed and Solar Irradiation

Smart Cities doi: 10.3390/smartcities9040059

Authors: Md Shafiullah Abdul Rahman Katranji Mannan Hassan Md Mahfuzur Rahman Sk. A. Shezan

The transition to smart cities is accelerating distributed wind and solar deployment. However, their intermittency challenges grid operation, thereby making accurate machine-learning-based prediction of wind speed and global horizontal irradiance (GHI) crucial. This study presents a cost-effective approach that enhances prediction accuracy by extracting additional features from timestamp records for deep learning models used to forecast GHI and wind speed. Unlike conventional methods that require onsite meteorological measurements, the proposed approach uses only date and time information as inputs to multivariate deep neural networks, including recurrent neural networks, gated recurrent units, long short-term memory (LSTM), bidirectional LSTM, and convolutional neural networks. For wind speed prediction, the proposed configuration achieves R2 up to 0.9987, with RMSE as low as 0.067 m/s for 3 d ahead forecasting, outperforming univariate baselines and matching models. For GHI forecasting, the time-based configuration attains R2 values above 0.9994 in 12 h ahead predictions, with the RMSE reduced to approximately 4.47 W/m2, representing a substantial improvement over univariate models. The proposed framework maintains strong performance, particularly under clear and sunny conditions. These results demonstrate that timestamp-engineered features can deliver forecasting accuracy comparable to conventional multivariate meteorological models while significantly reducing infrastructure requirements, making the approach well-suited for scalable smart city energy management.

]]> Advanced Multivariate Deep Learning Methodology for Forecasting Wind Speed and Solar Irradiation Md Shafiullah Abdul Rahman Katranji Mannan Hassan Md Mahfuzur Rahman Sk. A. Shezan doi: 10.3390/smartcities9040059 Smart Cities 2026-03-27 Smart Cities 2026-03-27 9 4 Article 59 10.3390/smartcities9040059 https://www.mdpi.com/2624-6511/9/4/59 Smart Cities, Vol. 9, Pages 58: Urban Communication in Smart Cities: Stakeholder Participation Motivators https://www.mdpi.com/2624-6511/9/4/58 The smart city concept has become a dominant framework for contemporary urban governance, largely driven by advances in digital technologies and data-driven decision-making. However, the prevailing technocratic orientation of smart city development risks marginalising the sociopolitical dimensions of urban governance, particularly citizen and stakeholder participation. Although smart governance frameworks increasingly recognise participation as a normative principle, limited empirical attention has been paid to the participation motivators that drive engagement among different urban stakeholder groups. This study addresses this gap by analysing the key motivators influencing stakeholder participation in urban development within a smart city context. Building on established behavioural and participation theories, the article develops an Urban Participation Motivator Model comprising four core motivators: social pressure, emotional trigger, rational motivation, and reward for participation. The model is empirically tested using quantitative survey data from 620 respondents representing four stakeholder groups in Riga, Latvia: municipal residents, municipal employees, municipal politicians, and real estate developers. Data are analysed using descriptive statistics and non-parametric methods, including the Kruskal–Wallis test. The results reveal statistically significant differences in the perceived importance of participation motivators across stakeholder groups. Emotional triggers and social pressure emerge as the most influential motivators overall, while rational motivation is particularly salient for professional stakeholders. Reward for participation plays a weaker but differentiated role, being most relevant for municipal employees. These findings highlight the need for differentiated motivator-sensitive urban communication and participation strategies to enhance inclusiveness, democratic legitimacy, and long-term engagement in smart city development. 2026-03-26 Smart Cities, Vol. 9, Pages 58: Urban Communication in Smart Cities: Stakeholder Participation Motivators

Smart Cities doi: 10.3390/smartcities9040058

Authors: Laura Minskere Diana Kalnina Jelena Salkovska Anda Batraga

The smart city concept has become a dominant framework for contemporary urban governance, largely driven by advances in digital technologies and data-driven decision-making. However, the prevailing technocratic orientation of smart city development risks marginalising the sociopolitical dimensions of urban governance, particularly citizen and stakeholder participation. Although smart governance frameworks increasingly recognise participation as a normative principle, limited empirical attention has been paid to the participation motivators that drive engagement among different urban stakeholder groups. This study addresses this gap by analysing the key motivators influencing stakeholder participation in urban development within a smart city context. Building on established behavioural and participation theories, the article develops an Urban Participation Motivator Model comprising four core motivators: social pressure, emotional trigger, rational motivation, and reward for participation. The model is empirically tested using quantitative survey data from 620 respondents representing four stakeholder groups in Riga, Latvia: municipal residents, municipal employees, municipal politicians, and real estate developers. Data are analysed using descriptive statistics and non-parametric methods, including the Kruskal–Wallis test. The results reveal statistically significant differences in the perceived importance of participation motivators across stakeholder groups. Emotional triggers and social pressure emerge as the most influential motivators overall, while rational motivation is particularly salient for professional stakeholders. Reward for participation plays a weaker but differentiated role, being most relevant for municipal employees. These findings highlight the need for differentiated motivator-sensitive urban communication and participation strategies to enhance inclusiveness, democratic legitimacy, and long-term engagement in smart city development.

]]> Urban Communication in Smart Cities: Stakeholder Participation Motivators Laura Minskere Diana Kalnina Jelena Salkovska Anda Batraga doi: 10.3390/smartcities9040058 Smart Cities 2026-03-26 Smart Cities 2026-03-26 9 4 Article 58 10.3390/smartcities9040058 https://www.mdpi.com/2624-6511/9/4/58 Smart Cities, Vol. 9, Pages 57: Startup-Driven Air-Front Smart City Policy Evaluation Using Integrated Accessibility Index: A Case Study of Aichi, Singapore, and Munich https://www.mdpi.com/2624-6511/9/4/57 The Air-front Smart City (ASC) concept is proposed to address the stagnation of industries in developed countries and stimulate economic growth in developing countries while maintaining a higher quality of life for people and contributing to decarbonization and overall United Nations SDGs in an existing study. However, no studies have been conducted to assess ASC policies. Therefore, this study integrates the integrated accessibility index into the quality of life (QOL) and quality of business (QOB) evaluation models to assess the startup ecosystem in Aichi, Singapore, and Munich within the ASC concept. The study uses survey data conducted in Aichi to estimate monetary values of QOL and QOB component indicators, calculates the integrated accessibility indices, and estimates QOL and QOB. Furthermore, the study sets scenarios to assess the impacts of living and business urban policies in Aichi. Additionally, the study using Aichi parameters compares the startup ecosystem in Singapore and Munich. The result shows that the key drivers of startup attraction are corporate tax rate, economic growth, and safety; enhancing these indicators directly increases startups’ QOB, business partners, and residents’ QOL. It was found that QOB in Singapore is comparatively higher, whereas QOL is higher in Aichi. 2026-03-25 Smart Cities, Vol. 9, Pages 57: Startup-Driven Air-Front Smart City Policy Evaluation Using Integrated Accessibility Index: A Case Study of Aichi, Singapore, and Munich

Smart Cities doi: 10.3390/smartcities9040057

Authors: Mustafa Mutahari Nao Sugiki Tsuyoshi Takano Hiroyoshi Morita Yoshitsugu Hayashi Kojiro Matsuo

The Air-front Smart City (ASC) concept is proposed to address the stagnation of industries in developed countries and stimulate economic growth in developing countries while maintaining a higher quality of life for people and contributing to decarbonization and overall United Nations SDGs in an existing study. However, no studies have been conducted to assess ASC policies. Therefore, this study integrates the integrated accessibility index into the quality of life (QOL) and quality of business (QOB) evaluation models to assess the startup ecosystem in Aichi, Singapore, and Munich within the ASC concept. The study uses survey data conducted in Aichi to estimate monetary values of QOL and QOB component indicators, calculates the integrated accessibility indices, and estimates QOL and QOB. Furthermore, the study sets scenarios to assess the impacts of living and business urban policies in Aichi. Additionally, the study using Aichi parameters compares the startup ecosystem in Singapore and Munich. The result shows that the key drivers of startup attraction are corporate tax rate, economic growth, and safety; enhancing these indicators directly increases startups’ QOB, business partners, and residents’ QOL. It was found that QOB in Singapore is comparatively higher, whereas QOL is higher in Aichi.

]]> Startup-Driven Air-Front Smart City Policy Evaluation Using Integrated Accessibility Index: A Case Study of Aichi, Singapore, and Munich Mustafa Mutahari Nao Sugiki Tsuyoshi Takano Hiroyoshi Morita Yoshitsugu Hayashi Kojiro Matsuo doi: 10.3390/smartcities9040057 Smart Cities 2026-03-25 Smart Cities 2026-03-25 9 4 Article 57 10.3390/smartcities9040057 https://www.mdpi.com/2624-6511/9/4/57 Smart Cities, Vol. 9, Pages 56: Comparative Evaluation of Traffic Load Prediction Models for Intelligent Transportation Systems Using High-Resolution Urban Data https://www.mdpi.com/2624-6511/9/4/56 Short-term traffic load prediction is a fundamental component of intelligent transportation systems (ITSs), supporting real-time monitoring, congestion mitigation, and adaptive traffic management in smart cities. Owing to the dynamic and nonlinear nature of urban traffic, identifying prediction models that align with real-world traffic dynamics remains a key challenge. This study presents a comparative evaluation of data-driven traffic load prediction models using high-resolution one-minute traffic data collected from a major urban roundabout in Jeddah, Saudi Arabia. The evaluated models include regression-based machine learning approaches and recurrent deep learning architectures, which are assessed under consistent preprocessing and evaluation conditions. Model performance is evaluated using standard error metrics and complemented by temporal and residual analyses to examine prediction behavior under different traffic regimes. The optimized GRU model achieved the best predictive accuracy with an RMSE of 149.12 veh/h, followed closely by the optimized LSTM model (RMSE = 150.85 veh/h). The results indicate that while conventional machine learning models can effectively capture overall traffic trends under relatively stable conditions, recurrent deep learning models demonstrate stronger capability in modeling nonlinear temporal dependencies and rapid traffic fluctuations when properly configured. In addition, a variability-based regime analysis was conducted to evaluate model robustness under different traffic demand dynamics, revealing that model performance advantages are context-dependent rather than universal. The findings highlight the importance of systematic comparative evaluation and data-driven model selection for developing reliable traffic prediction components in real-time ITS applications and sustainable urban mobility planning. 2026-03-25 Smart Cities, Vol. 9, Pages 56: Comparative Evaluation of Traffic Load Prediction Models for Intelligent Transportation Systems Using High-Resolution Urban Data

Smart Cities doi: 10.3390/smartcities9040056

Authors: Sara Atef

Short-term traffic load prediction is a fundamental component of intelligent transportation systems (ITSs), supporting real-time monitoring, congestion mitigation, and adaptive traffic management in smart cities. Owing to the dynamic and nonlinear nature of urban traffic, identifying prediction models that align with real-world traffic dynamics remains a key challenge. This study presents a comparative evaluation of data-driven traffic load prediction models using high-resolution one-minute traffic data collected from a major urban roundabout in Jeddah, Saudi Arabia. The evaluated models include regression-based machine learning approaches and recurrent deep learning architectures, which are assessed under consistent preprocessing and evaluation conditions. Model performance is evaluated using standard error metrics and complemented by temporal and residual analyses to examine prediction behavior under different traffic regimes. The optimized GRU model achieved the best predictive accuracy with an RMSE of 149.12 veh/h, followed closely by the optimized LSTM model (RMSE = 150.85 veh/h). The results indicate that while conventional machine learning models can effectively capture overall traffic trends under relatively stable conditions, recurrent deep learning models demonstrate stronger capability in modeling nonlinear temporal dependencies and rapid traffic fluctuations when properly configured. In addition, a variability-based regime analysis was conducted to evaluate model robustness under different traffic demand dynamics, revealing that model performance advantages are context-dependent rather than universal. The findings highlight the importance of systematic comparative evaluation and data-driven model selection for developing reliable traffic prediction components in real-time ITS applications and sustainable urban mobility planning.

]]> Comparative Evaluation of Traffic Load Prediction Models for Intelligent Transportation Systems Using High-Resolution Urban Data Sara Atef doi: 10.3390/smartcities9040056 Smart Cities 2026-03-25 Smart Cities 2026-03-25 9 4 Article 56 10.3390/smartcities9040056 https://www.mdpi.com/2624-6511/9/4/56 Smart Cities, Vol. 9, Pages 55: Smart Tourism for All: Optimizing Rental Hub Locations for Specialized Off-Road Wheelchairs Using Spatial Analysis https://www.mdpi.com/2624-6511/9/4/55 The development of Smart Tourism often overlooks the “Wilderness Last Mile”, leading to the spatial exclusion of people with disabilities in mountain areas. This problem exists because standard tourist maps and urban-centric accessibility models rely on averaged terrain data, failing to identify critical micro-scale barriers (e.g., short, sudden steep ascents) that pose severe safety and traction risks for off-road wheelchair users. To address this gap, this article presents a novel GIS methodology for planning accessible off-road tourism for electric Specialized Off-Road Wheelchairs. The proposed four-stage analytical model includes (1) graph-based trail network topologization to enable precise routing; (2) traction safety verification utilizing high-resolution (1 × 1 m) Digital Elevation Model (DEM) micro-segmentation to detect hidden slope barriers; (3) multi-criteria evaluation combining a user-calibrated Difficulty Index (EDI) and a Tourism Quality Index (TQI); and (4) a hub optimization algorithm that prioritizes locations maximizing the diversity of accessible routes. The method was empirically tested in a case study of the Bieszczady Mountains (Poland), calibrating the model with the technical limits (25% max slope) of a prototype wheelchair. The experimental results clearly validate the model’s superiority over traditional approaches: the micro-segmentation successfully identified hidden terrain traps, disqualifying 55% of the standard trail network that would have otherwise been deemed safe by average-slope assessments. Furthermore, the model identified a contiguous safe network of 153 km and pinpointed the optimal rental hub location, ensuring the highest inclusivity and route variety. Ultimately, this approach transforms raw spatial data into safe, ready-made tourism products, providing a precise tool with which to implement Universal Design in natural environments. 2026-03-24 Smart Cities, Vol. 9, Pages 55: Smart Tourism for All: Optimizing Rental Hub Locations for Specialized Off-Road Wheelchairs Using Spatial Analysis

Smart Cities doi: 10.3390/smartcities9040055

Authors: Marcin Jacek Kłos Marcin Staniek

The development of Smart Tourism often overlooks the “Wilderness Last Mile”, leading to the spatial exclusion of people with disabilities in mountain areas. This problem exists because standard tourist maps and urban-centric accessibility models rely on averaged terrain data, failing to identify critical micro-scale barriers (e.g., short, sudden steep ascents) that pose severe safety and traction risks for off-road wheelchair users. To address this gap, this article presents a novel GIS methodology for planning accessible off-road tourism for electric Specialized Off-Road Wheelchairs. The proposed four-stage analytical model includes (1) graph-based trail network topologization to enable precise routing; (2) traction safety verification utilizing high-resolution (1 × 1 m) Digital Elevation Model (DEM) micro-segmentation to detect hidden slope barriers; (3) multi-criteria evaluation combining a user-calibrated Difficulty Index (EDI) and a Tourism Quality Index (TQI); and (4) a hub optimization algorithm that prioritizes locations maximizing the diversity of accessible routes. The method was empirically tested in a case study of the Bieszczady Mountains (Poland), calibrating the model with the technical limits (25% max slope) of a prototype wheelchair. The experimental results clearly validate the model’s superiority over traditional approaches: the micro-segmentation successfully identified hidden terrain traps, disqualifying 55% of the standard trail network that would have otherwise been deemed safe by average-slope assessments. Furthermore, the model identified a contiguous safe network of 153 km and pinpointed the optimal rental hub location, ensuring the highest inclusivity and route variety. Ultimately, this approach transforms raw spatial data into safe, ready-made tourism products, providing a precise tool with which to implement Universal Design in natural environments.

]]> Smart Tourism for All: Optimizing Rental Hub Locations for Specialized Off-Road Wheelchairs Using Spatial Analysis Marcin Jacek Kłos Marcin Staniek doi: 10.3390/smartcities9040055 Smart Cities 2026-03-24 Smart Cities 2026-03-24 9 4 Article 55 10.3390/smartcities9040055 https://www.mdpi.com/2624-6511/9/4/55 Smart Cities, Vol. 9, Pages 54: GeoBIM for Geothermal Energy Efficiency in Buildings and Smart Cities: A Review https://www.mdpi.com/2624-6511/9/3/54 The global drive toward energy transition and carbon neutrality requires integrated and data-driven approaches for managing buildings and smart cities. Existing urban energy assessment frameworks remain fragmented and often lack multiscale interoperability between building-level models and territorial datasets. At the same time, shallow geothermal energy is emerging as an efficient and renewable solution for sustainable heating and cooling. To address these gaps, this study examines the potential of GeoBIM, the integration of Building Information Modeling (BIM) and Geographic Information Systems (GIS), as a unified framework for multiscale energy analysis and for supporting shallow geothermal applications. A systematic literature review was conducted based on the PRISMA framework, combining a systematic literature review using the Scopus database with the critical examination of representative case studies. The results show that GeoBIM-based modeling improves data quality, enhances thermal performance assessments, and supports the implementation of shallow geothermal systems, including energy piles and district-scale ground-coupled networks. Reported applications demonstrate energy consumption reductions exceeding 40% in certain urban contexts. Several research gaps and challenges were identified, particularly data interoperability issues, lack of standardization, computational complexity, and the need for specialized training. Overall, the review indicates that GeoBIM offers a promising pathway for optimizing resources, supporting informed decision-making, and advancing resilient and sustainable smart buildings and cities. 2026-03-23 Smart Cities, Vol. 9, Pages 54: GeoBIM for Geothermal Energy Efficiency in Buildings and Smart Cities: A Review

Smart Cities doi: 10.3390/smartcities9030054

Authors: Hugo Alexandre Silva Pinto Luis M. Ferreira Gomes Luis J. Andrade Pais Miguel Nepomuceno Luís Filipe Almeida Bernardo Vanessa Gonçalves Maria Vitoria Morais Leonardo Marchiori

The global drive toward energy transition and carbon neutrality requires integrated and data-driven approaches for managing buildings and smart cities. Existing urban energy assessment frameworks remain fragmented and often lack multiscale interoperability between building-level models and territorial datasets. At the same time, shallow geothermal energy is emerging as an efficient and renewable solution for sustainable heating and cooling. To address these gaps, this study examines the potential of GeoBIM, the integration of Building Information Modeling (BIM) and Geographic Information Systems (GIS), as a unified framework for multiscale energy analysis and for supporting shallow geothermal applications. A systematic literature review was conducted based on the PRISMA framework, combining a systematic literature review using the Scopus database with the critical examination of representative case studies. The results show that GeoBIM-based modeling improves data quality, enhances thermal performance assessments, and supports the implementation of shallow geothermal systems, including energy piles and district-scale ground-coupled networks. Reported applications demonstrate energy consumption reductions exceeding 40% in certain urban contexts. Several research gaps and challenges were identified, particularly data interoperability issues, lack of standardization, computational complexity, and the need for specialized training. Overall, the review indicates that GeoBIM offers a promising pathway for optimizing resources, supporting informed decision-making, and advancing resilient and sustainable smart buildings and cities.

]]> GeoBIM for Geothermal Energy Efficiency in Buildings and Smart Cities: A Review Hugo Alexandre Silva Pinto Luis M. Ferreira Gomes Luis J. Andrade Pais Miguel Nepomuceno Luís Filipe Almeida Bernardo Vanessa Gonçalves Maria Vitoria Morais Leonardo Marchiori doi: 10.3390/smartcities9030054 Smart Cities 2026-03-23 Smart Cities 2026-03-23 9 3 Review 54 10.3390/smartcities9030054 https://www.mdpi.com/2624-6511/9/3/54 Smart Cities, Vol. 9, Pages 53: Clustering of Driver Behavioral Strategies During Speed Cushion Traversal: A Driving Simulator Study https://www.mdpi.com/2624-6511/9/3/53 Traffic calming measures are widely used to reduce operating speeds and mitigate crash risk in urban corridors; however, the way drivers adapt their control strategy when traversing Berlin speed cushions is still poorly described from a multivariate behavioral perspective. This study proposes a behavior-oriented analysis to identify recurring speed-cushion traversal strategies using driving simulator telemetry. A fixed-base simulator reproduced a real urban corridor, and trajectories were segmented in device-centered spatial windows capturing approach, traversal, and immediate recovery. Each segment was summarized by three indicators describing longitudinal and lateral control: mean speed, peak braking demand, and average lane position deviation. Features were standardized and clustered using k-means. The number of clusters was selected primarily through mean silhouette evaluation, while resampling-based checks and a Gaussian mixture modeling comparison were used as supportive evidence rather than competing decision rules. Three traversal profiles emerged: smooth cautious, reactive cautious, and unmoderated fast. The introduction of speed cushions shifted the distribution of segments towards cautious profiles, while driver-level concentration within a single profile was moderate. Overall, results indicate that speed cushions influence the whole vehicle control strategy, offering a quantitative basis for behavior-oriented evaluation of local traffic calming interventions in smart-city contexts. 2026-03-20 Smart Cities, Vol. 9, Pages 53: Clustering of Driver Behavioral Strategies During Speed Cushion Traversal: A Driving Simulator Study

Smart Cities doi: 10.3390/smartcities9030053

Authors: Gaetano Bosurgi Alessia Ruggeri Giuseppe Sollazzo Orazio Pellegrino Domenico Passeri

Traffic calming measures are widely used to reduce operating speeds and mitigate crash risk in urban corridors; however, the way drivers adapt their control strategy when traversing Berlin speed cushions is still poorly described from a multivariate behavioral perspective. This study proposes a behavior-oriented analysis to identify recurring speed-cushion traversal strategies using driving simulator telemetry. A fixed-base simulator reproduced a real urban corridor, and trajectories were segmented in device-centered spatial windows capturing approach, traversal, and immediate recovery. Each segment was summarized by three indicators describing longitudinal and lateral control: mean speed, peak braking demand, and average lane position deviation. Features were standardized and clustered using k-means. The number of clusters was selected primarily through mean silhouette evaluation, while resampling-based checks and a Gaussian mixture modeling comparison were used as supportive evidence rather than competing decision rules. Three traversal profiles emerged: smooth cautious, reactive cautious, and unmoderated fast. The introduction of speed cushions shifted the distribution of segments towards cautious profiles, while driver-level concentration within a single profile was moderate. Overall, results indicate that speed cushions influence the whole vehicle control strategy, offering a quantitative basis for behavior-oriented evaluation of local traffic calming interventions in smart-city contexts.

]]> Clustering of Driver Behavioral Strategies During Speed Cushion Traversal: A Driving Simulator Study Gaetano Bosurgi Alessia Ruggeri Giuseppe Sollazzo Orazio Pellegrino Domenico Passeri doi: 10.3390/smartcities9030053 Smart Cities 2026-03-20 Smart Cities 2026-03-20 9 3 Article 53 10.3390/smartcities9030053 https://www.mdpi.com/2624-6511/9/3/53 Smart Cities, Vol. 9, Pages 52: Smart Urban Logistics and Tube-Based Freight Systems: A Review of Technological Integration and Implementation Barriers https://www.mdpi.com/2624-6511/9/3/52 Background: Smart urban logistics has emerged as a key element of sustainable city development, with direct effects on economic performance, environmental quality, and urban livability. Issues with traffic, pollutants, infrastructure strain, and last-mile delivery efficiency have become more pressing due to rapid urbanization and the expansion of e-commerce. In this regard, underground or enclosed corridor-based tube-based freight transit systems have surfaced as a viable smart infrastructure option for automated and low-impact commodities delivery. Methods: This study adopts an analytical literature review complemented by a structured case study analysis to examine the potential role of tube-based freight transport systems in future urban logistics. Key technological concepts, including pneumatic tubes, automated capsule transport, and integration with digital platforms, the Physical Internet, and smart city management systems, are examined through a structured analytical review of the literature. Results: The outcome of the reviewed studies indicates that tube-based systems can contribute to congestion alleviation, emission reduction, and improved delivery reliability by shifting selected freight flows away from surface transport networks. However, governance frameworks, infrastructure integration, and institutional coordination mechanisms continue to have a significant impact on claimed performance outcomes. Conclusions: Tube-based freight systems represent a promising but conditional pathway toward smarter and more sustainable urban logistics. Their large-scale deployment is forced by high capital costs, standardization challenges, regulatory uncertainty, and social acceptance issues. Coordinated investment plans, encouraging legal frameworks, and integrated urban planning techniques in line with smart city goals are needed to overcome these obstacles. 2026-03-19 Smart Cities, Vol. 9, Pages 52: Smart Urban Logistics and Tube-Based Freight Systems: A Review of Technological Integration and Implementation Barriers

Smart Cities doi: 10.3390/smartcities9030052

Authors: Fellaki Soumaya Molk Oukili Garti Arif Jabir Jawab Fouad

Background: Smart urban logistics has emerged as a key element of sustainable city development, with direct effects on economic performance, environmental quality, and urban livability. Issues with traffic, pollutants, infrastructure strain, and last-mile delivery efficiency have become more pressing due to rapid urbanization and the expansion of e-commerce. In this regard, underground or enclosed corridor-based tube-based freight transit systems have surfaced as a viable smart infrastructure option for automated and low-impact commodities delivery. Methods: This study adopts an analytical literature review complemented by a structured case study analysis to examine the potential role of tube-based freight transport systems in future urban logistics. Key technological concepts, including pneumatic tubes, automated capsule transport, and integration with digital platforms, the Physical Internet, and smart city management systems, are examined through a structured analytical review of the literature. Results: The outcome of the reviewed studies indicates that tube-based systems can contribute to congestion alleviation, emission reduction, and improved delivery reliability by shifting selected freight flows away from surface transport networks. However, governance frameworks, infrastructure integration, and institutional coordination mechanisms continue to have a significant impact on claimed performance outcomes. Conclusions: Tube-based freight systems represent a promising but conditional pathway toward smarter and more sustainable urban logistics. Their large-scale deployment is forced by high capital costs, standardization challenges, regulatory uncertainty, and social acceptance issues. Coordinated investment plans, encouraging legal frameworks, and integrated urban planning techniques in line with smart city goals are needed to overcome these obstacles.

]]> Smart Urban Logistics and Tube-Based Freight Systems: A Review of Technological Integration and Implementation Barriers Fellaki Soumaya Molk Oukili Garti Arif Jabir Jawab Fouad doi: 10.3390/smartcities9030052 Smart Cities 2026-03-19 Smart Cities 2026-03-19 9 3 Review 52 10.3390/smartcities9030052 https://www.mdpi.com/2624-6511/9/3/52 Smart Cities, Vol. 9, Pages 51: Detection of P-Wave Arrival as a Structural Transition in Seismic Signals: An Approach Based on SVD Entropy https://www.mdpi.com/2624-6511/9/3/51 Early and reliable detection of P-wave arrivals is critical for seismic monitoring and earthquake early warning, particularly under low signal-to-noise ratio (SNR) and non-stationary noise conditions. This study presents an automatic detection method based on singular value decomposition (SVD) entropy computed in sliding time windows with local signal filtering. Within this framework, the P-wave onset is interpreted as a local structural change in the signal rather than a simple energy increase. SVD entropy captures the redistribution of energy among dominant signal components, providing high sensitivity to the initial P-wave arrival even at moderate and low noise levels (SNR≥2). The method was validated using real seismic data from four regional stations operating under different noise conditions. Analysis of detection parameters revealed strong station dependence. For stations affected by low-frequency drift, polynomial detrending was identified as a necessary preprocessing step to ensure a stable entropy response and reliable detection. The proposed approach achieves detection accuracies of up to 93–98% at SNR≥2, significantly outperforming the classical STA/LTA algorithm and demonstrating performance comparable to modern deep learning methods. Since the method does not require model training or labeled datasets, it provides an interpretable and computationally efficient solution for automatic seismic monitoring. These properties make the proposed approach particularly suitable for real-time seismic monitoring systems and distributed sensor networks operating under limited computational resources. All computational stages were performed at the Farabi Supercomputer Centre of Al-Farabi Kazakh National University. The method requires no model training or labeled data, making it an interpretable, robust, and computationally efficient solution for automatic seismic monitoring and early warning systems. 2026-03-19 Smart Cities, Vol. 9, Pages 51: Detection of P-Wave Arrival as a Structural Transition in Seismic Signals: An Approach Based on SVD Entropy

Smart Cities doi: 10.3390/smartcities9030051

Authors: Margulan Ibraimov Zhanseit Tuimebayev Alua Maksutova Alisher Skabylov Dauren Zhexebay Azamat Khokhlov Lazzat Abdizhalilova Aliya Aktymbayeva Yuxiao Qin Serik Khokhlov

Early and reliable detection of P-wave arrivals is critical for seismic monitoring and earthquake early warning, particularly under low signal-to-noise ratio (SNR) and non-stationary noise conditions. This study presents an automatic detection method based on singular value decomposition (SVD) entropy computed in sliding time windows with local signal filtering. Within this framework, the P-wave onset is interpreted as a local structural change in the signal rather than a simple energy increase. SVD entropy captures the redistribution of energy among dominant signal components, providing high sensitivity to the initial P-wave arrival even at moderate and low noise levels (SNR≥2). The method was validated using real seismic data from four regional stations operating under different noise conditions. Analysis of detection parameters revealed strong station dependence. For stations affected by low-frequency drift, polynomial detrending was identified as a necessary preprocessing step to ensure a stable entropy response and reliable detection. The proposed approach achieves detection accuracies of up to 93–98% at SNR≥2, significantly outperforming the classical STA/LTA algorithm and demonstrating performance comparable to modern deep learning methods. Since the method does not require model training or labeled datasets, it provides an interpretable and computationally efficient solution for automatic seismic monitoring. These properties make the proposed approach particularly suitable for real-time seismic monitoring systems and distributed sensor networks operating under limited computational resources. All computational stages were performed at the Farabi Supercomputer Centre of Al-Farabi Kazakh National University. The method requires no model training or labeled data, making it an interpretable, robust, and computationally efficient solution for automatic seismic monitoring and early warning systems.

]]> Detection of P-Wave Arrival as a Structural Transition in Seismic Signals: An Approach Based on SVD Entropy Margulan Ibraimov Zhanseit Tuimebayev Alua Maksutova Alisher Skabylov Dauren Zhexebay Azamat Khokhlov Lazzat Abdizhalilova Aliya Aktymbayeva Yuxiao Qin Serik Khokhlov doi: 10.3390/smartcities9030051 Smart Cities 2026-03-19 Smart Cities 2026-03-19 9 3 Article 51 10.3390/smartcities9030051 https://www.mdpi.com/2624-6511/9/3/51 Smart Cities, Vol. 9, Pages 50: Towards Supporting Real-Time Estimation of Vehicle Fuel Consumption and CO2 Emissions in Smart City Applications https://www.mdpi.com/2624-6511/9/3/50 This paper evaluates a simplified physics-based energy demand model designed to estimate vehicle fuel consumption and CO2 emissions—a critical tool for sustainable transportation planning and smart city applications. Unlike data-driven regression models that lack generalizability for user-defined conditions or complex physics-based approaches that rely on extensive, often proprietary data, the simplified model is distinguished by its minimal parameter requirements, depending primarily on a single, overarching powertrain efficiency value. A key contribution is the comprehensive empirical evaluation of the simplified model against official Environmental Protection Agency (EPA) test data across multiple driving cycles and vehicle types, providing a rigorous validation previously absent in the literature. We identify optimal powertrain efficiency values that are directly derived from publicly available vehicle specifications, ensuring transparency and accessibility. Our findings demonstrate that this simple, physics-based model accurately estimates fuel consumption and CO2 emissions for standard EPA cycles and can be effectively generalized to user-defined scenarios. This establishes a computationally efficient, interpretable, and robust method for environmental impact assessment, policy evaluation, and real-time emissions estimation. 2026-03-18 Smart Cities, Vol. 9, Pages 50: Towards Supporting Real-Time Estimation of Vehicle Fuel Consumption and CO2 Emissions in Smart City Applications

Smart Cities doi: 10.3390/smartcities9030050

Authors: Abrar Alali Stephan Olariu

This paper evaluates a simplified physics-based energy demand model designed to estimate vehicle fuel consumption and CO2 emissions—a critical tool for sustainable transportation planning and smart city applications. Unlike data-driven regression models that lack generalizability for user-defined conditions or complex physics-based approaches that rely on extensive, often proprietary data, the simplified model is distinguished by its minimal parameter requirements, depending primarily on a single, overarching powertrain efficiency value. A key contribution is the comprehensive empirical evaluation of the simplified model against official Environmental Protection Agency (EPA) test data across multiple driving cycles and vehicle types, providing a rigorous validation previously absent in the literature. We identify optimal powertrain efficiency values that are directly derived from publicly available vehicle specifications, ensuring transparency and accessibility. Our findings demonstrate that this simple, physics-based model accurately estimates fuel consumption and CO2 emissions for standard EPA cycles and can be effectively generalized to user-defined scenarios. This establishes a computationally efficient, interpretable, and robust method for environmental impact assessment, policy evaluation, and real-time emissions estimation.

]]> Towards Supporting Real-Time Estimation of Vehicle Fuel Consumption and CO2 Emissions in Smart City Applications Abrar Alali Stephan Olariu doi: 10.3390/smartcities9030050 Smart Cities 2026-03-18 Smart Cities 2026-03-18 9 3 Article 50 10.3390/smartcities9030050 https://www.mdpi.com/2624-6511/9/3/50 Smart Cities, Vol. 9, Pages 49: Mapping Urban Digital Twins Across Regions: An Exploratory Study of Maturity, Implementation Status, and Authority https://www.mdpi.com/2624-6511/9/3/49 An increasing number of municipalities are adopting urban digital twins (UDTs) to improve urban management. Although the models differ widely, municipalities face similar challenges in their implementation. Therefore, sharing insights on UDTs provides an opportunity for collective growth. To facilitate this growth, the present exploratory study maps the characteristics, challenges, and potentials of 99 UDTs in Europe, North America, and Asia. We first estimate the UDT readiness based on established features, along with contextual and local authority involvement indicators. Next, we conduct semi-structured interviews with key individuals from eight selected cities to contextualize the review findings. The mapping results indicate that most UDTs in our sample operate at the municipal level, and that over half (57%) are not in series operation. The reviewed UDTs are mid-level in maturity, and local authority involvement is a key driver of scalability. We infer that UDT progress depends as much on common frameworks, organizational readiness, governance capacity, and relevant data as on technology. Collaborations with private companies and researchers can play a central role in the long-term sustainment and growth of UDT infrastructures. 2026-03-10 Smart Cities, Vol. 9, Pages 49: Mapping Urban Digital Twins Across Regions: An Exploratory Study of Maturity, Implementation Status, and Authority

Smart Cities doi: 10.3390/smartcities9030049

Authors: Jasmin Hiller Mohamed Mansour Noemi Kremer David Crampen Sascha von Behren

An increasing number of municipalities are adopting urban digital twins (UDTs) to improve urban management. Although the models differ widely, municipalities face similar challenges in their implementation. Therefore, sharing insights on UDTs provides an opportunity for collective growth. To facilitate this growth, the present exploratory study maps the characteristics, challenges, and potentials of 99 UDTs in Europe, North America, and Asia. We first estimate the UDT readiness based on established features, along with contextual and local authority involvement indicators. Next, we conduct semi-structured interviews with key individuals from eight selected cities to contextualize the review findings. The mapping results indicate that most UDTs in our sample operate at the municipal level, and that over half (57%) are not in series operation. The reviewed UDTs are mid-level in maturity, and local authority involvement is a key driver of scalability. We infer that UDT progress depends as much on common frameworks, organizational readiness, governance capacity, and relevant data as on technology. Collaborations with private companies and researchers can play a central role in the long-term sustainment and growth of UDT infrastructures.

]]> Mapping Urban Digital Twins Across Regions: An Exploratory Study of Maturity, Implementation Status, and Authority Jasmin Hiller Mohamed Mansour Noemi Kremer David Crampen Sascha von Behren doi: 10.3390/smartcities9030049 Smart Cities 2026-03-10 Smart Cities 2026-03-10 9 3 Article 49 10.3390/smartcities9030049 https://www.mdpi.com/2624-6511/9/3/49 Smart Cities, Vol. 9, Pages 48: Urban Freight in Casablanca: Congestion, Emissions, and Welfare Losses from Large-Scale Simulation-Based Dynamic Assignment https://www.mdpi.com/2624-6511/9/3/48 Urban business-to-business distribution in Casablanca relies heavily on light commercial vehicles (LCVs) operating in a constrained street environment where loading/unloading access, intersection capacity, and recurring bottlenecks jointly shape performance and environmental impacts. However, high-resolution freight origin–destination (OD) observations and junction calibration data are limited, which complicates direct estimations of congestion and externalities attributable to commercial activity. This study develops a reproducible, large-scale modeling workflow that couples tour-based freight demand generation in order units with simulation-based traffic assignment (SBA) on a metropolitan network and translates network performance into emissions and monetary losses. Warehouses are modeled as primary producers and commercial activity zones as attractors via sector-tagged production and attraction functions; the resulting order distribution is converted to OD vehicle trips using the tour-based trip generation procedure with the mean targets-per-tour fixed to one to ensure numerical stability, yielding a direct-shipment approximation appropriate for stress–response analysis. Junction impedance is represented through turn-type volume–delay relationships and node-level impedance procedures, and congestion is evaluated using vehicle kilometers traveled/vehicle hours traveled (VKT/VHT)-based indicators, delay-intensity measures, and link/node bottleneck rankings. Across demand-scaling scenarios, VKT increases from 302,159 to 1,017,686 veh·km/day, while network delay rises nonlinearly from 392.5 to 2738.4 veh·h/day, indicating saturation-driven amplification of time losses. The Handbook of Emission Factors for Road Transport (HBEFA)-compatible emission estimates scale with activity: total carbon dioxide (CO2) increases from 154.1 to 519.5 t/day, and nitrogen oxides (NOx) and particulate matter (PM2.5) totals rise proportionally under fixed fleet assumptions. Monetizing delay with a purchasing-power-adjusted value-of-time range yields a congestion cost per trip that increases from approximately 0.20 to 0.41 Moroccan dirham, MAD/trip (at 60 MAD/veh·h), consistent with rising delay intensity. Bottleneck extraction shows welfare losses to be structurally concentrated on a small persistent corridor set, led by ‘Boulevard de la Résistance’, with recurrent hotspots including ‘Rue d’Arcachon’ and ‘Rue d’Ifni’. The framework supports policy-relevant reporting of congestion, emissions, and welfare impacts under data scarcity, with explicit sensitivity bounds. 2026-03-10 Smart Cities, Vol. 9, Pages 48: Urban Freight in Casablanca: Congestion, Emissions, and Welfare Losses from Large-Scale Simulation-Based Dynamic Assignment

Smart Cities doi: 10.3390/smartcities9030048

Authors: Amine Mohamed El Amrani Mouhsene Fri Othmane Benmoussa Naoufal Rouky

Urban business-to-business distribution in Casablanca relies heavily on light commercial vehicles (LCVs) operating in a constrained street environment where loading/unloading access, intersection capacity, and recurring bottlenecks jointly shape performance and environmental impacts. However, high-resolution freight origin–destination (OD) observations and junction calibration data are limited, which complicates direct estimations of congestion and externalities attributable to commercial activity. This study develops a reproducible, large-scale modeling workflow that couples tour-based freight demand generation in order units with simulation-based traffic assignment (SBA) on a metropolitan network and translates network performance into emissions and monetary losses. Warehouses are modeled as primary producers and commercial activity zones as attractors via sector-tagged production and attraction functions; the resulting order distribution is converted to OD vehicle trips using the tour-based trip generation procedure with the mean targets-per-tour fixed to one to ensure numerical stability, yielding a direct-shipment approximation appropriate for stress–response analysis. Junction impedance is represented through turn-type volume–delay relationships and node-level impedance procedures, and congestion is evaluated using vehicle kilometers traveled/vehicle hours traveled (VKT/VHT)-based indicators, delay-intensity measures, and link/node bottleneck rankings. Across demand-scaling scenarios, VKT increases from 302,159 to 1,017,686 veh·km/day, while network delay rises nonlinearly from 392.5 to 2738.4 veh·h/day, indicating saturation-driven amplification of time losses. The Handbook of Emission Factors for Road Transport (HBEFA)-compatible emission estimates scale with activity: total carbon dioxide (CO2) increases from 154.1 to 519.5 t/day, and nitrogen oxides (NOx) and particulate matter (PM2.5) totals rise proportionally under fixed fleet assumptions. Monetizing delay with a purchasing-power-adjusted value-of-time range yields a congestion cost per trip that increases from approximately 0.20 to 0.41 Moroccan dirham, MAD/trip (at 60 MAD/veh·h), consistent with rising delay intensity. Bottleneck extraction shows welfare losses to be structurally concentrated on a small persistent corridor set, led by ‘Boulevard de la Résistance’, with recurrent hotspots including ‘Rue d’Arcachon’ and ‘Rue d’Ifni’. The framework supports policy-relevant reporting of congestion, emissions, and welfare impacts under data scarcity, with explicit sensitivity bounds.

]]> Urban Freight in Casablanca: Congestion, Emissions, and Welfare Losses from Large-Scale Simulation-Based Dynamic Assignment Amine Mohamed El Amrani Mouhsene Fri Othmane Benmoussa Naoufal Rouky doi: 10.3390/smartcities9030048 Smart Cities 2026-03-10 Smart Cities 2026-03-10 9 3 Article 48 10.3390/smartcities9030048 https://www.mdpi.com/2624-6511/9/3/48 Smart Cities, Vol. 9, Pages 47: Prediction of Building Carbon Emissions in Campus Areas Based on Building a Carbon Emission Correlation Factor https://www.mdpi.com/2624-6511/9/3/47 This study introduces a new method for predicting carbon emissions from campus buildings, which is crucial to achieving low-carbon campuses in higher education and meeting “Carbon Peaking and Carbon Neutrality Goals”. The method begins with manually classifying buildings and introducing a carbon emission correlation factor, linking each building type’s emissions to the total category emissions. Using this factor, three models—Seasonal Autoregressive Integrated Moving Average (SARIMA), Long Short-Term Memory (LSTM), and Random Forest (RF)—were developed to predict emissions. The results show improved accuracy after adding the correlation factor: 17.23%, 6.159%, and 3.949% for the SARIMA model in Categories A, B, and C, respectively; 2.76%, 12.636%, and 3.370% for LSTM; and 3.61%, 10.893%, and 4.776% for Random Forest. These results demonstrate the value of using carbon emission correlation factors to improve prediction accuracy and promote sustainable campus development. 2026-03-04 Smart Cities, Vol. 9, Pages 47: Prediction of Building Carbon Emissions in Campus Areas Based on Building a Carbon Emission Correlation Factor

Smart Cities doi: 10.3390/smartcities9030047

Authors: Jingjing Wang Mingzhu Xiu Bo Zhao Li Song

This study introduces a new method for predicting carbon emissions from campus buildings, which is crucial to achieving low-carbon campuses in higher education and meeting “Carbon Peaking and Carbon Neutrality Goals”. The method begins with manually classifying buildings and introducing a carbon emission correlation factor, linking each building type’s emissions to the total category emissions. Using this factor, three models—Seasonal Autoregressive Integrated Moving Average (SARIMA), Long Short-Term Memory (LSTM), and Random Forest (RF)—were developed to predict emissions. The results show improved accuracy after adding the correlation factor: 17.23%, 6.159%, and 3.949% for the SARIMA model in Categories A, B, and C, respectively; 2.76%, 12.636%, and 3.370% for LSTM; and 3.61%, 10.893%, and 4.776% for Random Forest. These results demonstrate the value of using carbon emission correlation factors to improve prediction accuracy and promote sustainable campus development.

]]> Prediction of Building Carbon Emissions in Campus Areas Based on Building a Carbon Emission Correlation Factor Jingjing Wang Mingzhu Xiu Bo Zhao Li Song doi: 10.3390/smartcities9030047 Smart Cities 2026-03-04 Smart Cities 2026-03-04 9 3 Article 47 10.3390/smartcities9030047 https://www.mdpi.com/2624-6511/9/3/47 Smart Cities, Vol. 9, Pages 46: An Analytical Approach to Evaluating Traffic Performance at Urban Railway Level Crossings for Sustainable Mobility in Smart Cities https://www.mdpi.com/2624-6511/9/3/46 Irregular and non-cyclical railway level-crossing closures generate traffic disruptions that cannot be directly assessed using standard intersection analysis methods. Railway level crossings interrupt road traffic in irregular, non-cyclical intervals, yet no dedicated analytical methodology exists for estimating their traffic impacts. Microsimulation tools such as PTV Vissim and SUMO may support such analyses, although modelling adjustments are required to represent non-cyclical closures realistically. This study proposes an analytical alternative based on adapting capacity-calculation procedures for signalised intersections from Polish regulations, derived from Highway Capacity Manual (HCM) principles. The method provides approximate estimates of maximum queue length and average time loss. Empirical data collected in Wrocław, Poland, were compared with results from Vissim and SUMO. While the analytical model supports preliminary assessment of traffic performance at level crossings, its outputs depend on simplified assumptions and limited empirical calibration. The method is intended as a complementary tool rather than a replacement for detailed microsimulation. 2026-03-02 Smart Cities, Vol. 9, Pages 46: An Analytical Approach to Evaluating Traffic Performance at Urban Railway Level Crossings for Sustainable Mobility in Smart Cities

Smart Cities doi: 10.3390/smartcities9030046

Authors: Wojciech Kazimierz Szczepanek Maciej Kruszyna

Irregular and non-cyclical railway level-crossing closures generate traffic disruptions that cannot be directly assessed using standard intersection analysis methods. Railway level crossings interrupt road traffic in irregular, non-cyclical intervals, yet no dedicated analytical methodology exists for estimating their traffic impacts. Microsimulation tools such as PTV Vissim and SUMO may support such analyses, although modelling adjustments are required to represent non-cyclical closures realistically. This study proposes an analytical alternative based on adapting capacity-calculation procedures for signalised intersections from Polish regulations, derived from Highway Capacity Manual (HCM) principles. The method provides approximate estimates of maximum queue length and average time loss. Empirical data collected in Wrocław, Poland, were compared with results from Vissim and SUMO. While the analytical model supports preliminary assessment of traffic performance at level crossings, its outputs depend on simplified assumptions and limited empirical calibration. The method is intended as a complementary tool rather than a replacement for detailed microsimulation.

]]> An Analytical Approach to Evaluating Traffic Performance at Urban Railway Level Crossings for Sustainable Mobility in Smart Cities Wojciech Kazimierz Szczepanek Maciej Kruszyna doi: 10.3390/smartcities9030046 Smart Cities 2026-03-02 Smart Cities 2026-03-02 9 3 Article 46 10.3390/smartcities9030046 https://www.mdpi.com/2624-6511/9/3/46 Smart Cities, Vol. 9, Pages 45: Artificial Intelligence in Water Distribution Networks: A Systematic Review of Models, Input Variables, Databases, and Output Strategies for Leak Detection https://www.mdpi.com/2624-6511/9/3/45 Early leak detection in water distribution networks is essential to minimize losses and improve operational efficiency. This systematic review analyzes 53 studies published between 2018 and 2025 that employed machine learning, deep learning, and hybrid approaches. The results show that pressure is the most widely used and most sensitive input variable for identifying hydraulic anomalies. Most datasets originate from EPANET-generated simulations, while experimental and field data are less common due to their high costs and operational complexity. Machine learning models, particularly SVMs, achieve accuracies between 94 and 100%, demonstrating stability with noisy data and low computational cost, while in deep learning, CNNs are most effective for multiclass classification and localization, typically reaching 95–99% accuracy. Hybrid approaches that combine automatic feature extraction (e.g., CNNs or autoencoders) with conventional classifiers (such as SVMs or LSSVMs) yield the best results, surpassing 97% accuracy and achieving localization errors below 0.2 m. Based on these findings, a theoretical model is proposed using a hybrid CNN + SVM approach to enhance accuracy, robustness, and adaptability in real-time monitoring systems. 2026-03-01 Smart Cities, Vol. 9, Pages 45: Artificial Intelligence in Water Distribution Networks: A Systematic Review of Models, Input Variables, Databases, and Output Strategies for Leak Detection

Smart Cities doi: 10.3390/smartcities9030045

Authors: Mariana Zuñiga-Uribe Rafael Rojas-Galván José M. Álvarez-Alvarado Marcos Aviles Gerardo I. Pérez-Soto Victor Pérez-Moreno

Early leak detection in water distribution networks is essential to minimize losses and improve operational efficiency. This systematic review analyzes 53 studies published between 2018 and 2025 that employed machine learning, deep learning, and hybrid approaches. The results show that pressure is the most widely used and most sensitive input variable for identifying hydraulic anomalies. Most datasets originate from EPANET-generated simulations, while experimental and field data are less common due to their high costs and operational complexity. Machine learning models, particularly SVMs, achieve accuracies between 94 and 100%, demonstrating stability with noisy data and low computational cost, while in deep learning, CNNs are most effective for multiclass classification and localization, typically reaching 95–99% accuracy. Hybrid approaches that combine automatic feature extraction (e.g., CNNs or autoencoders) with conventional classifiers (such as SVMs or LSSVMs) yield the best results, surpassing 97% accuracy and achieving localization errors below 0.2 m. Based on these findings, a theoretical model is proposed using a hybrid CNN + SVM approach to enhance accuracy, robustness, and adaptability in real-time monitoring systems.

]]> Artificial Intelligence in Water Distribution Networks: A Systematic Review of Models, Input Variables, Databases, and Output Strategies for Leak Detection Mariana Zuñiga-Uribe Rafael Rojas-Galván José M. Álvarez-Alvarado Marcos Aviles Gerardo I. Pérez-Soto Victor Pérez-Moreno doi: 10.3390/smartcities9030045 Smart Cities 2026-03-01 Smart Cities 2026-03-01 9 3 Systematic Review 45 10.3390/smartcities9030045 https://www.mdpi.com/2624-6511/9/3/45 Smart Cities, Vol. 9, Pages 44: Privacy-Preserving, Non-Iterative Coordinated Day-Ahead Scheduling of Multi-Area Active Distribution Networks via Equivalent Projection https://www.mdpi.com/2624-6511/9/3/44 A distribution network is transforming into multi-area distribution networks. Traditional iterative multi-area coordination methods protect the privacy of each area but face a high communication burden and convergence issues. To address these challenges, this paper proposes a non-iterative day-ahead scheduling method based on equivalent projection (EP). A deterministic scheduling model is established for multi-area distribution networks that are connected by soft open points (SOPs). An EP-based multi-area coordination method is proposed to transform the scheduling model into a reduced-dimensional problem that eliminates private data from areas. This enables privacy-preserving multi-area scheduling without iterative information exchange, thereby reducing the communication burden and achieving convergence in day-ahead coordination. Simulation results on the IEEE 33-bus five-region system show that the proposed method reduces online coordination time to 0.17 s compared to 181.06 s for the iterative baseline. Furthermore, tests on the larger IEEE 123-bus five-region system confirm its computational scalability in day-ahead scheduling, achieving a solution within 7.20 s with an optimality gap of 0.40%. 2026-02-27 Smart Cities, Vol. 9, Pages 44: Privacy-Preserving, Non-Iterative Coordinated Day-Ahead Scheduling of Multi-Area Active Distribution Networks via Equivalent Projection

Smart Cities doi: 10.3390/smartcities9030044

Authors: Ling Luo Tiantian Chen Chenhong Huang Na Wang Zhen Zheng Jiangke Yang Jian Ping Zheng Yan

A distribution network is transforming into multi-area distribution networks. Traditional iterative multi-area coordination methods protect the privacy of each area but face a high communication burden and convergence issues. To address these challenges, this paper proposes a non-iterative day-ahead scheduling method based on equivalent projection (EP). A deterministic scheduling model is established for multi-area distribution networks that are connected by soft open points (SOPs). An EP-based multi-area coordination method is proposed to transform the scheduling model into a reduced-dimensional problem that eliminates private data from areas. This enables privacy-preserving multi-area scheduling without iterative information exchange, thereby reducing the communication burden and achieving convergence in day-ahead coordination. Simulation results on the IEEE 33-bus five-region system show that the proposed method reduces online coordination time to 0.17 s compared to 181.06 s for the iterative baseline. Furthermore, tests on the larger IEEE 123-bus five-region system confirm its computational scalability in day-ahead scheduling, achieving a solution within 7.20 s with an optimality gap of 0.40%.

]]> Privacy-Preserving, Non-Iterative Coordinated Day-Ahead Scheduling of Multi-Area Active Distribution Networks via Equivalent Projection Ling Luo Tiantian Chen Chenhong Huang Na Wang Zhen Zheng Jiangke Yang Jian Ping Zheng Yan doi: 10.3390/smartcities9030044 Smart Cities 2026-02-27 Smart Cities 2026-02-27 9 3 Article 44 10.3390/smartcities9030044 https://www.mdpi.com/2624-6511/9/3/44 Smart Cities, Vol. 9, Pages 43: From Hours to Milliseconds: Dual-Horizon Fault Prediction for Dynamic Wireless EV Charging via Digital Twin Integrated Deep Learning https://www.mdpi.com/2624-6511/9/3/43 Dynamic Wireless Power Transfer (DWPT) is emerging as critical smart city infrastructure for sustainable urban mobility, enabling electric vehicle charging while driving. However, DWPT introduces complex fault scenarios requiring intelligent monitoring. Existing fault diagnosis approaches for wireless power transfer systems face three key complexities: (1) they are limited to static charging with only 2–4 fault categories, failing to address the time-varying coupling dynamics and segmented coil handover transients inherent in dynamic charging; (2) they lack integration with the host distribution grid, ignoring grid-side disturbances that propagate to charging stations; and (3) they offer only reactive detection without predictive capability for incipient fault management. This paper presents a deep neural network (DNN)-based fault diagnosis framework utilizing multi-station sensor fusion for DWPT systems integrated with the IEEE 13-bus distribution network to address these limitations. The system monitors 36 sensor features across three charging stations, employing feature-level concatenation with station-specific normalization for multi-station fusion, achieving 97.85% classification accuracy across eight fault types. Unlike static charging, the framework explicitly models time-varying coupling dynamics due to vehicle motion, including segmented coil handover effects. A digital twin provides dual-horizon prediction: long-term forecasting (24–72 h) for incipient faults and real-time detection under 50 ms for critical protection, with fault probability outputs and ranked fault lists enabling actionable maintenance decisions. The DNN outperforms SVM (92.45%), Random Forest (94.82%), and LSTM (96.54%) with statistical significance (p<0.001), while maintaining model inference latency of 4.2 ms, suitable for edge deployment. Circuit-based analysis provides analytical justification for fault signatures, and practical parameter acquisition methods enable real-world implementation. Five case studies validate robustness across highway, urban, and grid disturbance scenarios with detection accuracies exceeding 95%. 2026-02-26 Smart Cities, Vol. 9, Pages 43: From Hours to Milliseconds: Dual-Horizon Fault Prediction for Dynamic Wireless EV Charging via Digital Twin Integrated Deep Learning

Smart Cities doi: 10.3390/smartcities9030043

Authors: Mohammed Ahmed Mousa Ali Sayghe Salem Batiyah Abdulrahman Husawi

Dynamic Wireless Power Transfer (DWPT) is emerging as critical smart city infrastructure for sustainable urban mobility, enabling electric vehicle charging while driving. However, DWPT introduces complex fault scenarios requiring intelligent monitoring. Existing fault diagnosis approaches for wireless power transfer systems face three key complexities: (1) they are limited to static charging with only 2–4 fault categories, failing to address the time-varying coupling dynamics and segmented coil handover transients inherent in dynamic charging; (2) they lack integration with the host distribution grid, ignoring grid-side disturbances that propagate to charging stations; and (3) they offer only reactive detection without predictive capability for incipient fault management. This paper presents a deep neural network (DNN)-based fault diagnosis framework utilizing multi-station sensor fusion for DWPT systems integrated with the IEEE 13-bus distribution network to address these limitations. The system monitors 36 sensor features across three charging stations, employing feature-level concatenation with station-specific normalization for multi-station fusion, achieving 97.85% classification accuracy across eight fault types. Unlike static charging, the framework explicitly models time-varying coupling dynamics due to vehicle motion, including segmented coil handover effects. A digital twin provides dual-horizon prediction: long-term forecasting (24–72 h) for incipient faults and real-time detection under 50 ms for critical protection, with fault probability outputs and ranked fault lists enabling actionable maintenance decisions. The DNN outperforms SVM (92.45%), Random Forest (94.82%), and LSTM (96.54%) with statistical significance (p<0.001), while maintaining model inference latency of 4.2 ms, suitable for edge deployment. Circuit-based analysis provides analytical justification for fault signatures, and practical parameter acquisition methods enable real-world implementation. Five case studies validate robustness across highway, urban, and grid disturbance scenarios with detection accuracies exceeding 95%.

]]> From Hours to Milliseconds: Dual-Horizon Fault Prediction for Dynamic Wireless EV Charging via Digital Twin Integrated Deep Learning Mohammed Ahmed Mousa Ali Sayghe Salem Batiyah Abdulrahman Husawi doi: 10.3390/smartcities9030043 Smart Cities 2026-02-26 Smart Cities 2026-02-26 9 3 Article 43 10.3390/smartcities9030043 https://www.mdpi.com/2624-6511/9/3/43 Smart Cities, Vol. 9, Pages 42: Assessment and Realization of the Benefits of Collaboration Among Ridesharing Service Providers Based on Metaheuristic Algorithms https://www.mdpi.com/2624-6511/9/3/42 As ridesharing is one of the emerging sustainable transport modes that has been widely adopted by commuters and travelers in cities, it has been extensively studied for over a decade. Although many research issues related to ridesharing have been studied, most studies focus on these issues in the context of single ridesharing service providers. However, the existence of multiple ridesharing service providers poses unaddressed research issues. In economics, collaboration might enable two companies to achieve greater market share and efficiency than they could achieve independently. “One plus one is greater than two” refers to the concept of synergy, where combining two elements creates a result that is more valuable or effective than the sum of their individual parts. An interesting question is whether multiple ridesharing service providers can benefit from collaboration. This study aims to assess and realize the benefits of collaboration among ridesharing service providers using metaheuristic algorithms. In this paper, we will study this research question based on two decision models: (1) Decision Model 1 for multiple independent ridesharing service providers and (2) Decision Model 2 for a Collaborative Ridesharing Service Provider. We formulated the optimization of these two decision models and developed twelve metaheuristic algorithms for the two decision models, and conducted experiments to study their effectiveness in terms of performance and computational efficiency. The results indicate that the benefits that can be realized depend critically on the type of metaheuristic algorithm used. The results of this study show that “one plus one is greater than two” holds for ridesharing if an effective solver is used. 2026-02-25 Smart Cities, Vol. 9, Pages 42: Assessment and Realization of the Benefits of Collaboration Among Ridesharing Service Providers Based on Metaheuristic Algorithms

Smart Cities doi: 10.3390/smartcities9030042

Authors: Fu-Shiung Hsieh

As ridesharing is one of the emerging sustainable transport modes that has been widely adopted by commuters and travelers in cities, it has been extensively studied for over a decade. Although many research issues related to ridesharing have been studied, most studies focus on these issues in the context of single ridesharing service providers. However, the existence of multiple ridesharing service providers poses unaddressed research issues. In economics, collaboration might enable two companies to achieve greater market share and efficiency than they could achieve independently. “One plus one is greater than two” refers to the concept of synergy, where combining two elements creates a result that is more valuable or effective than the sum of their individual parts. An interesting question is whether multiple ridesharing service providers can benefit from collaboration. This study aims to assess and realize the benefits of collaboration among ridesharing service providers using metaheuristic algorithms. In this paper, we will study this research question based on two decision models: (1) Decision Model 1 for multiple independent ridesharing service providers and (2) Decision Model 2 for a Collaborative Ridesharing Service Provider. We formulated the optimization of these two decision models and developed twelve metaheuristic algorithms for the two decision models, and conducted experiments to study their effectiveness in terms of performance and computational efficiency. The results indicate that the benefits that can be realized depend critically on the type of metaheuristic algorithm used. The results of this study show that “one plus one is greater than two” holds for ridesharing if an effective solver is used.

]]> Assessment and Realization of the Benefits of Collaboration Among Ridesharing Service Providers Based on Metaheuristic Algorithms Fu-Shiung Hsieh doi: 10.3390/smartcities9030042 Smart Cities 2026-02-25 Smart Cities 2026-02-25 9 3 Article 42 10.3390/smartcities9030042 https://www.mdpi.com/2624-6511/9/3/42 Smart Cities, Vol. 9, Pages 41: A Comprehensive Analysis of Incident and Object Detection in Traffic Environments https://www.mdpi.com/2624-6511/9/3/41 Traffic accident detection and object detection have become key areas of research due to their direct impact on safety, traffic congestion mitigation, and intelligent traffic planning. This study presents a structured analysis of classical detection methods and artificial intelligence-based techniques, highlighting their methodologies, objectives, and performance results. The study categorizes existing research into threshold-based approaches, statistical approaches, image processing, rule-based approaches, and machine learning approaches, with further emphasis on predictive modeling, graph-based approaches, and optimization approaches. Considerable emphasis is placed on identifying systems that are capable of operating under adverse weather conditions such as fog, rain, and snow. These scenarios significantly affect detection accuracy. Although several authors incorporate environmental resilience into their models, most studies still evaluate performance under ideal conditions, revealing a critical gap in research. This analysis highlights the need to develop robust detection mechanisms that can adapt to real-world variability and environmental disturbances. Findings show that AI-based methods significantly outperform classical approaches in terms of adaptability and scalability, but their dependence on training data limits their performance in adverse conditions. The study concludes with recommendations for future work to prioritize multimodal sensing, generalization across weather conditions, and integration of environmental intelligence to ensure reliable real-time detection of traffic events under all operating conditions. 2026-02-25 Smart Cities, Vol. 9, Pages 41: A Comprehensive Analysis of Incident and Object Detection in Traffic Environments

Smart Cities doi: 10.3390/smartcities9030041

Authors: Patrik Kovačovič Rastislav Pirník Tomáš Tichý Júlia Kafková Gabriel Gašpar Pavol Kuchár

Traffic accident detection and object detection have become key areas of research due to their direct impact on safety, traffic congestion mitigation, and intelligent traffic planning. This study presents a structured analysis of classical detection methods and artificial intelligence-based techniques, highlighting their methodologies, objectives, and performance results. The study categorizes existing research into threshold-based approaches, statistical approaches, image processing, rule-based approaches, and machine learning approaches, with further emphasis on predictive modeling, graph-based approaches, and optimization approaches. Considerable emphasis is placed on identifying systems that are capable of operating under adverse weather conditions such as fog, rain, and snow. These scenarios significantly affect detection accuracy. Although several authors incorporate environmental resilience into their models, most studies still evaluate performance under ideal conditions, revealing a critical gap in research. This analysis highlights the need to develop robust detection mechanisms that can adapt to real-world variability and environmental disturbances. Findings show that AI-based methods significantly outperform classical approaches in terms of adaptability and scalability, but their dependence on training data limits their performance in adverse conditions. The study concludes with recommendations for future work to prioritize multimodal sensing, generalization across weather conditions, and integration of environmental intelligence to ensure reliable real-time detection of traffic events under all operating conditions.

]]> A Comprehensive Analysis of Incident and Object Detection in Traffic Environments Patrik Kovačovič Rastislav Pirník Tomáš Tichý Júlia Kafková Gabriel Gašpar Pavol Kuchár doi: 10.3390/smartcities9030041 Smart Cities 2026-02-25 Smart Cities 2026-02-25 9 3 Review 41 10.3390/smartcities9030041 https://www.mdpi.com/2624-6511/9/3/41 Smart Cities, Vol. 9, Pages 40: The Convergence of Artificial Intelligence and Public Policy in Shaping the Future of Ride-Hailing: A Review https://www.mdpi.com/2624-6511/9/2/40 In the context in which on-demand mobility services are rapidly gaining popularity in the transportation sector, this article provides a literature review focusing on the emerging research topics related to ride-hailing. Based on a comprehensive review of the existing scientific literature, ten main research areas are identified, covering aspects ranging from operational algorithms to macro-level policy impacts enforced by local authorities. Each topic is discussed and analyzed based on available published research. This work analyzes state-of-the-art research directions such as demand forecasting, passenger–driver matching algorithms, pricing strategies, electric vehicle integration, trust and security aspects, quality of service and user satisfaction, integration with public transportation, and robotaxi integration. The solutions identified pave the way for new, evolving technologies related to on-demand mobility services and ride-hailing, a domain at the intersection of data science, artificial intelligence, and futuristic urban planning. Finally, the main results of this work are focused on the integration of AI, the optimization of the latency–security trade-off, and the development of unified global transportation standards that better address the balance between technological efficiency, sustainability, environmental protection, and social equity. 2026-02-23 Smart Cities, Vol. 9, Pages 40: The Convergence of Artificial Intelligence and Public Policy in Shaping the Future of Ride-Hailing: A Review

Smart Cities doi: 10.3390/smartcities9020040

Authors: Cătălin Beguni Alin-Mihai Căilean Eduard Zadobrischi Sebastian-Andrei Avătămăniței Alexandru Lavric Florinel-Mădălin Stoian

In the context in which on-demand mobility services are rapidly gaining popularity in the transportation sector, this article provides a literature review focusing on the emerging research topics related to ride-hailing. Based on a comprehensive review of the existing scientific literature, ten main research areas are identified, covering aspects ranging from operational algorithms to macro-level policy impacts enforced by local authorities. Each topic is discussed and analyzed based on available published research. This work analyzes state-of-the-art research directions such as demand forecasting, passenger–driver matching algorithms, pricing strategies, electric vehicle integration, trust and security aspects, quality of service and user satisfaction, integration with public transportation, and robotaxi integration. The solutions identified pave the way for new, evolving technologies related to on-demand mobility services and ride-hailing, a domain at the intersection of data science, artificial intelligence, and futuristic urban planning. Finally, the main results of this work are focused on the integration of AI, the optimization of the latency–security trade-off, and the development of unified global transportation standards that better address the balance between technological efficiency, sustainability, environmental protection, and social equity.

]]> The Convergence of Artificial Intelligence and Public Policy in Shaping the Future of Ride-Hailing: A Review Cătălin Beguni Alin-Mihai Căilean Eduard Zadobrischi Sebastian-Andrei Avătămăniței Alexandru Lavric Florinel-Mădălin Stoian doi: 10.3390/smartcities9020040 Smart Cities 2026-02-23 Smart Cities 2026-02-23 9 2 Review 40 10.3390/smartcities9020040 https://www.mdpi.com/2624-6511/9/2/40 Smart Cities, Vol. 9, Pages 39: Co-Creating Climate-Resilient Streets: Digital Twin-Based Simulations for Outdoor Thermal Comfort https://www.mdpi.com/2624-6511/9/2/39 Rapid urbanization and climate change are intensifying heat exposure in cities, making effective adaptation strategies essential. This study presents a streamlined digital twin modeling framework for simulating the impact of nature-based solutions (NBSs) on outdoor thermal comfort, developed within the Intelligent Communities Lifecycle (ICL) software suite. The approach automates the import of urban geometry from OpenStreetMap and integrates geolocated weather data, enabling users to efficiently test scenarios involving NBSs and surface material modifications. Outdoor thermal comfort is quantified using the Universal Thermal Climate Index (UTCI), with results visualized through an interactive cloud-based 3D platform to support participatory urban planning. The methodology is demonstrated in Meunierstraat, Leuven (Belgium), where three planning alternatives are compared across seasonal extremes. Simulations show that targeted NBS interventions, particularly temporary participatory measures, can improve thermal comfort under extreme heat. However, the benefits are seasonally dependent and spatially heterogeneous, emphasizing the value of high-resolution, scenario-based analysis. This integrated workflow enhances both technical evidence and stakeholder engagement. While the tool is capable of linking outdoor comfort improvements with building energy performance and carbon emissions, the present paper focuses solely on the outdoor thermal comfort results, leaving indoor–outdoor coupling analysis as a direction for future work. 2026-02-22 Smart Cities, Vol. 9, Pages 39: Co-Creating Climate-Resilient Streets: Digital Twin-Based Simulations for Outdoor Thermal Comfort

Smart Cities doi: 10.3390/smartcities9020039

Authors: Koldo Urrutia-Azcona Valentina Bonetti Mohammad Mizanur Nele Janssen Niall Buckley Mark De Wit Kieran Murray Niall Byrne

Rapid urbanization and climate change are intensifying heat exposure in cities, making effective adaptation strategies essential. This study presents a streamlined digital twin modeling framework for simulating the impact of nature-based solutions (NBSs) on outdoor thermal comfort, developed within the Intelligent Communities Lifecycle (ICL) software suite. The approach automates the import of urban geometry from OpenStreetMap and integrates geolocated weather data, enabling users to efficiently test scenarios involving NBSs and surface material modifications. Outdoor thermal comfort is quantified using the Universal Thermal Climate Index (UTCI), with results visualized through an interactive cloud-based 3D platform to support participatory urban planning. The methodology is demonstrated in Meunierstraat, Leuven (Belgium), where three planning alternatives are compared across seasonal extremes. Simulations show that targeted NBS interventions, particularly temporary participatory measures, can improve thermal comfort under extreme heat. However, the benefits are seasonally dependent and spatially heterogeneous, emphasizing the value of high-resolution, scenario-based analysis. This integrated workflow enhances both technical evidence and stakeholder engagement. While the tool is capable of linking outdoor comfort improvements with building energy performance and carbon emissions, the present paper focuses solely on the outdoor thermal comfort results, leaving indoor–outdoor coupling analysis as a direction for future work.

]]> Co-Creating Climate-Resilient Streets: Digital Twin-Based Simulations for Outdoor Thermal Comfort Koldo Urrutia-Azcona Valentina Bonetti Mohammad Mizanur Nele Janssen Niall Buckley Mark De Wit Kieran Murray Niall Byrne doi: 10.3390/smartcities9020039 Smart Cities 2026-02-22 Smart Cities 2026-02-22 9 2 Article 39 10.3390/smartcities9020039 https://www.mdpi.com/2624-6511/9/2/39 Smart Cities, Vol. 9, Pages 38: Advancing Smart Cities in Africa: Barriers, Potentials, and Strategic Pathways for Sustainable Urban Transformation https://www.mdpi.com/2624-6511/9/2/38 Smart cities utilise advanced technology to enhance the quality of life, economic efficiency, and environmental sustainability of citizens. This transformation is both vital and complex in Africa due to rapid urbanisation and socio-economic challenges. This paper examines the prospects, challenges, and pathways toward smart city development in African cities. The study was conducted through a systematic literature review and case study analyses of initiatives for smart city development in Africa. The findings indicate that infrastructure deficits, financial constraints, weak policy frameworks, limited expertise, and socio-economic inequalities are the key challenges. The high use of mobile technologies, innovation hubs, and increasing policy support have created opportunities. Strategic actions for transforming African cities include strengthening infrastructure through public–private partnerships, developing financial mechanisms, creating coherent policies, promoting inclusivity, and building technical capacity. Technologies such as Information and Communication Technology (ICT) and Artificial Intelligence (AI) are among the key enablers, supporting the growth of Small and Medium-Sized Enterprises (SMEs), improving infrastructure, fostering inclusive governance, managing resources sustainably, and enhancing public services such as healthcare and education. The study also proposes a conceptual framework for smart cities in Africa and outlines a pathway to unlock the continent’s potential for smart cities. It is argued that African cities need to address systemic challenges, leverage unique opportunities, and ensure inclusivity at the urban level. An integrated approach that utilises advanced technologies and prioritises sustainability and resilience is essential for developing smart and inclusive cities. 2026-02-19 Smart Cities, Vol. 9, Pages 38: Advancing Smart Cities in Africa: Barriers, Potentials, and Strategic Pathways for Sustainable Urban Transformation

Smart Cities doi: 10.3390/smartcities9020038

Authors: Dillip Kumar Das Ayodeji Olatunji Aiyetan Mohamed Mostafa Hassan Mostafa

Smart cities utilise advanced technology to enhance the quality of life, economic efficiency, and environmental sustainability of citizens. This transformation is both vital and complex in Africa due to rapid urbanisation and socio-economic challenges. This paper examines the prospects, challenges, and pathways toward smart city development in African cities. The study was conducted through a systematic literature review and case study analyses of initiatives for smart city development in Africa. The findings indicate that infrastructure deficits, financial constraints, weak policy frameworks, limited expertise, and socio-economic inequalities are the key challenges. The high use of mobile technologies, innovation hubs, and increasing policy support have created opportunities. Strategic actions for transforming African cities include strengthening infrastructure through public–private partnerships, developing financial mechanisms, creating coherent policies, promoting inclusivity, and building technical capacity. Technologies such as Information and Communication Technology (ICT) and Artificial Intelligence (AI) are among the key enablers, supporting the growth of Small and Medium-Sized Enterprises (SMEs), improving infrastructure, fostering inclusive governance, managing resources sustainably, and enhancing public services such as healthcare and education. The study also proposes a conceptual framework for smart cities in Africa and outlines a pathway to unlock the continent’s potential for smart cities. It is argued that African cities need to address systemic challenges, leverage unique opportunities, and ensure inclusivity at the urban level. An integrated approach that utilises advanced technologies and prioritises sustainability and resilience is essential for developing smart and inclusive cities.

]]> Advancing Smart Cities in Africa: Barriers, Potentials, and Strategic Pathways for Sustainable Urban Transformation Dillip Kumar Das Ayodeji Olatunji Aiyetan Mohamed Mostafa Hassan Mostafa doi: 10.3390/smartcities9020038 Smart Cities 2026-02-19 Smart Cities 2026-02-19 9 2 Systematic Review 38 10.3390/smartcities9020038 https://www.mdpi.com/2624-6511/9/2/38 Smart Cities, Vol. 9, Pages 37: Estimating Building Air Change Rates with Multizone Models at Urban Scale: Comparative Case Studies https://www.mdpi.com/2624-6511/9/2/37 Accurate estimation of building-specific air change rates is important for reliable urban-scale energy modeling, particularly in densely populated regions where airflow calculations must account for complex boundary conditions associated with urban geometry. This study applied lumped-parameter airflow models to simulate interzone airflow by calculating the internal pressures using simplified building representations. Air change rates were calculated by solving a system of nonlinear equations, with boundary conditions defined by localized wind inputs corrected using aerodynamic parameters extracted from three-dimensional urban geometry. By linking these wind-related boundary conditions with lumped-parameter airflow models, the methodology describes spatial variability in natural infiltration across a broad range of urban densities. Two cities were compared to test the variability in building air change rates using local boundary conditions: New York City, a dense modern city, and Turin, a typical medium-density European city. Moreover, verifying the lumped-parameter model against CONTAM (Version 3.4.0.6) showed accurate results, with a mean absolute percentage error of 1.2% across 120 simulated weather scenarios. Furthermore, comparing energy consumption predictions using building-specific air change rates to those using fixed air change rates showed improved accuracy, resulting in an average error reduction of 27% over the entire heating season for a sample building. This scalable, automated approach enables more accurate assessments of ventilation-driven energy use in compact urban areas. 2026-02-18 Smart Cities, Vol. 9, Pages 37: Estimating Building Air Change Rates with Multizone Models at Urban Scale: Comparative Case Studies

Smart Cities doi: 10.3390/smartcities9020037

Authors: Yasemin Usta William Stuart Dols Cristina Bertani Guglielmina Mutani

Accurate estimation of building-specific air change rates is important for reliable urban-scale energy modeling, particularly in densely populated regions where airflow calculations must account for complex boundary conditions associated with urban geometry. This study applied lumped-parameter airflow models to simulate interzone airflow by calculating the internal pressures using simplified building representations. Air change rates were calculated by solving a system of nonlinear equations, with boundary conditions defined by localized wind inputs corrected using aerodynamic parameters extracted from three-dimensional urban geometry. By linking these wind-related boundary conditions with lumped-parameter airflow models, the methodology describes spatial variability in natural infiltration across a broad range of urban densities. Two cities were compared to test the variability in building air change rates using local boundary conditions: New York City, a dense modern city, and Turin, a typical medium-density European city. Moreover, verifying the lumped-parameter model against CONTAM (Version 3.4.0.6) showed accurate results, with a mean absolute percentage error of 1.2% across 120 simulated weather scenarios. Furthermore, comparing energy consumption predictions using building-specific air change rates to those using fixed air change rates showed improved accuracy, resulting in an average error reduction of 27% over the entire heating season for a sample building. This scalable, automated approach enables more accurate assessments of ventilation-driven energy use in compact urban areas.

]]> Estimating Building Air Change Rates with Multizone Models at Urban Scale: Comparative Case Studies Yasemin Usta William Stuart Dols Cristina Bertani Guglielmina Mutani doi: 10.3390/smartcities9020037 Smart Cities 2026-02-18 Smart Cities 2026-02-18 9 2 Article 37 10.3390/smartcities9020037 https://www.mdpi.com/2624-6511/9/2/37 Smart Cities, Vol. 9, Pages 36: Tackling the Complexity of Emergency Response Systems: Creating Transport-Focused Digital Twins https://www.mdpi.com/2624-6511/9/2/36 Providing medical and technical assistance to people in life-threatening situations requires the coordinated cooperation of numerous actors within the emergency response system. The efficiency of the emergency response system is thereby influenced by the transport infrastructure and the traffic conditions. Organizations and authorities with safety responsibilities are increasingly faced with the challenge of assessing the impact of changes to the transport system on the overall system’s effectiveness. The overall objective of this paper is to develop an efficient and cost-effective simulation and analysis platform for generating transport-focused digital twins, enabling organizations and authorities to monitor the current emergency response system and digitally analyze various ‘what-if’ scenarios for future planning. Our model combines various data sources, including real-time traffic data, recorded GPS data from emergency vehicles (EVs), and the road network. The data serves as the foundation for the indicator-based network analysis and the system model. The main actors in the emergency response system are modeled in the agent-based model to analyze the spatiotemporal impact of changes in the transport system on the system’s effectiveness. The developed simulation and analysis platform is applied to a case study of the Munich Fire Department, Germany. First, a network analysis using regression of EV speed on reported real-time traffic speed helps identify problematic areas where EVs are affected by traffic. Secondly, the agent-based model of the Munich fire department demonstrates good validation results against historical incident data, with recorded trajectory data used for model calibration. Our work contributes to efficient, data-driven planning for future emergency response systems. 2026-02-18 Smart Cities, Vol. 9, Pages 36: Tackling the Complexity of Emergency Response Systems: Creating Transport-Focused Digital Twins

Smart Cities doi: 10.3390/smartcities9020036

Authors: Fabian Schuhmann Moritz Sturm Till Zacher Markus Lienkamp

Providing medical and technical assistance to people in life-threatening situations requires the coordinated cooperation of numerous actors within the emergency response system. The efficiency of the emergency response system is thereby influenced by the transport infrastructure and the traffic conditions. Organizations and authorities with safety responsibilities are increasingly faced with the challenge of assessing the impact of changes to the transport system on the overall system’s effectiveness. The overall objective of this paper is to develop an efficient and cost-effective simulation and analysis platform for generating transport-focused digital twins, enabling organizations and authorities to monitor the current emergency response system and digitally analyze various ‘what-if’ scenarios for future planning. Our model combines various data sources, including real-time traffic data, recorded GPS data from emergency vehicles (EVs), and the road network. The data serves as the foundation for the indicator-based network analysis and the system model. The main actors in the emergency response system are modeled in the agent-based model to analyze the spatiotemporal impact of changes in the transport system on the system’s effectiveness. The developed simulation and analysis platform is applied to a case study of the Munich Fire Department, Germany. First, a network analysis using regression of EV speed on reported real-time traffic speed helps identify problematic areas where EVs are affected by traffic. Secondly, the agent-based model of the Munich fire department demonstrates good validation results against historical incident data, with recorded trajectory data used for model calibration. Our work contributes to efficient, data-driven planning for future emergency response systems.

]]> Tackling the Complexity of Emergency Response Systems: Creating Transport-Focused Digital Twins Fabian Schuhmann Moritz Sturm Till Zacher Markus Lienkamp doi: 10.3390/smartcities9020036 Smart Cities 2026-02-18 Smart Cities 2026-02-18 9 2 Article 36 10.3390/smartcities9020036 https://www.mdpi.com/2624-6511/9/2/36 Smart Cities, Vol. 9, Pages 35: A Stochastic Optimization Model for Electric Freight Operations on Predefined Long-Haul Routes with Partial Recharging and Heterogeneous Fleets https://www.mdpi.com/2624-6511/9/2/35 The electrification of long-haul freight transport introduces significant challenges in fleet planning, charging decisions, and reliability management under uncertainty. This study proposed a Stochastic Electric Freight Operations Planning Problem on Predefined Routes with Partial Recharging and Heterogeneous Fleets (SEFOP-PR-HF), to support corridor-based electric truck operations under uncertain demand. The model represents real-world interregional logistics, where vehicles operate on fixed long-haul routes and may perform partial recharging at fast-charging stations. Freight demand is modeled as a normally distributed random variable, and Chance-Constrained Programming (CCP) is employed to ensure probabilistic feasibility of vehicle capacity and battery constraints. The objective is to minimize total long-term system cost, including fleet acquisition and charging expenditures, while maintaining operational reliability. A Mixed-Integer Linear Programming (MILP) formulation is applied for multiple corridor instances using real heavy-duty electric truck data. Computational results show that incorporating demand uncertainty improves robustness but raises total cost by 6–33% compared to deterministic solutions. Sensitivity analyses further reveal how reliability levels and demand variability influence fleet allocation and charging strategies. 2026-02-17 Smart Cities, Vol. 9, Pages 35: A Stochastic Optimization Model for Electric Freight Operations on Predefined Long-Haul Routes with Partial Recharging and Heterogeneous Fleets

Smart Cities doi: 10.3390/smartcities9020035

Authors: Kantapong Niyomphon Warisa Nakkiew Parida Jewpanya Wasawat Nakkiew

The electrification of long-haul freight transport introduces significant challenges in fleet planning, charging decisions, and reliability management under uncertainty. This study proposed a Stochastic Electric Freight Operations Planning Problem on Predefined Routes with Partial Recharging and Heterogeneous Fleets (SEFOP-PR-HF), to support corridor-based electric truck operations under uncertain demand. The model represents real-world interregional logistics, where vehicles operate on fixed long-haul routes and may perform partial recharging at fast-charging stations. Freight demand is modeled as a normally distributed random variable, and Chance-Constrained Programming (CCP) is employed to ensure probabilistic feasibility of vehicle capacity and battery constraints. The objective is to minimize total long-term system cost, including fleet acquisition and charging expenditures, while maintaining operational reliability. A Mixed-Integer Linear Programming (MILP) formulation is applied for multiple corridor instances using real heavy-duty electric truck data. Computational results show that incorporating demand uncertainty improves robustness but raises total cost by 6–33% compared to deterministic solutions. Sensitivity analyses further reveal how reliability levels and demand variability influence fleet allocation and charging strategies.

]]> A Stochastic Optimization Model for Electric Freight Operations on Predefined Long-Haul Routes with Partial Recharging and Heterogeneous Fleets Kantapong Niyomphon Warisa Nakkiew Parida Jewpanya Wasawat Nakkiew doi: 10.3390/smartcities9020035 Smart Cities 2026-02-17 Smart Cities 2026-02-17 9 2 Article 35 10.3390/smartcities9020035 https://www.mdpi.com/2624-6511/9/2/35