Search Results (1,660)

This study explores digital inequality as a socio-spatial phenomenon within the context of smart inclusion, focusing on the Regional Unit of Xanthi, Greece—a region marked by ethno-cultural diversity and pronounced urban–rural contrasts. Using a mixed-methods design, this research integrates secondary quantitative data with qualitative insights from semi-structured interviews, aiming to uncover how spatial, demographic, and cultural variables shape digital engagement. Geographic Information System (GIS) tools are employed to map disparities in internet access and ICT infrastructure, revealing significant gaps linked to geography, education, and economic status. The findings demonstrate that digital inequality is particularly acute in rural, minority, and economically marginalized communities, where limited infrastructure intersects with low digital literacy and socio-economic disadvantage. Interview data further illuminate how residents navigate exclusion, emphasizing generational divides, perceptions of technology, and place-based constraints. By bridging spatial analysis with lived experience, this study advances the conceptualization of digitally inclusive smart regions. It offers policy-relevant insights into how territorial inequality undermines the goals of smart development and proposes context-sensitive interventions to promote equitable digital participation. The case of Xanthi underscores the importance of integrating spatial justice into smart city and regional planning agendas. Full article

Ensuring a sustainable and healthy human environment in university dormitories is essential for students’ learning, living, and overall health and well-being. To address this need, we carried out a series of systematic field measurements of the noise levels at 30 dormitories in three representative major urban universities in a major provincial capital city in China and designed and implemented a comprehensive questionnaire and surveyed 1005 students about their perceptions of their acoustic environment. We proposed and applied a sustainability–health-oriented, multidimensional assessment framework to assess the acoustic environment of the dormitories and student responses to natural sound, technological sounds, and human-made sounds. Using the Structural Equation Modeling (SEM) approach combined with the field measurements and student surveys, we identified three categories and six factors on student health and well-being for assessing the acoustic environment of university dormitories. The field data indicated that noise levels at most of the measurement points exceeded the recommended or regulatory thresholds. Higher noise impacts were observed in early mornings and evenings, primarily due to traffic noise and indoor activities. Natural sounds (e.g., wind, birdsong, water flow) were highly valued by students for their positive effect on the students’ pleasantness and satisfaction. Conversely, human and technological sounds (traffic noise, construction noise, and indoor noise from student activities) were deemed highly disturbing. Gender differences were evident in the assessment of the acoustic environment, with male students generally reporting higher levels of the pleasantness and preference for natural sounds compared to female students. Educational backgrounds showed no significant influence on sound perceptions. The findings highlight the need for providing actionable guidelines for dormitory ecological design, such as integrating vertical greening in dormitory design, water features, and biodiversity planting to introduce natural soundscapes, in parallel with developing campus activity standards and lifestyle during noise-sensitive periods. The multidimensional assessment framework will drive a sustainable human–ecology–sound symbiosis in university dormitories, and the category and factor scales to be employed and actions to improve the level of student health and well-being, thus, providing a reference for both research and practice for sustainable cities and communities. Full article

This study examines diurnal surface temperature dynamics across major Moroccan cities during the growing season and explores the interaction between urban and vegetated surfaces. We also introduce the Urban Thermal Impact Ratio (UTIR), a novel metric designed to quantify urban thermal comfort as a function of the surface urban heat island (SUHI) intensity. The analysis is based on outputs from a land surface model (LSM) for the year 2010, integrating high-resolution Landsat and MODIS data to characterize land cover and biophysical parameters across twelve land cover types. Our findings reveal moderate urban–vegetation temperature differences in coastal cities like Tangier (1.8 °C) and Rabat (1.0 °C), where winter vegetation remains active. In inland areas, urban morphology plays a more dominant role: Fes, with a 20% impervious surface area (ISA), exhibits a smaller SUHI than Meknes (5% ISA), due to higher urban heating in the latter. The Atlantic desert city of Dakhla shows a distinct pattern, with a nighttime SUHI of 2.1 °C and a daytime urban cooling of −0.7 °C, driven by irrigated parks and lawns enhancing evapotranspiration and shading. At the regional scale, summer UTIR values remain below one in Tangier-Tetouan-Al Hoceima, Rabat-Sale-Kenitra, and Casablanca-Settat, suggesting that urban conditions generally stay within thermal comfort thresholds. In contrast, higher UTIR values in Marrakech-Safi, Beni Mellal-Khénifra, and Guelmim-Oued Noun indicate elevated heat discomfort. At the city scale, the UTIR in Tangier, Rabat, and Casablanca demonstrates a clear diurnal pattern: it emerges around 11:00 a.m., peaks at 1:00 p.m., and fades by 3:00 p.m. This study highlights the critical role of vegetation in regulating urban surface temperatures and modulating urban–rural thermal contrasts. The UTIR provides a practical, scalable indicator of urban heat stress, particularly valuable in data-scarce settings. These findings carry significant implications for climate-resilient urban planning, optimized energy use, and the design of public health early warning systems in the context of climate change. Full article

High-resolution remote sensing imagery plays an essential role in urban management and environmental monitoring, providing detailed insights for applications ranging from land cover mapping to disaster response. Semantic segmentation methods are among the most effective techniques for comprehensive land cover mapping, and they commonly employ ImageNet-based pre-training semantics. However, traditional fine-tuning processes exhibit poor transferability across different downstream tasks and require large amounts of labeled data. To address these challenges, we introduce Denoising Diffusion Probabilistic Models (DDPMs) as a generative pre-training approach for semantic features extraction in remote sensing imagery. We pre-trained a DDPM on extensive unlabeled imagery, obtaining features at multiple noise levels and resolutions. In order to integrate and optimize these features efficiently, we designed a multi-layer perceptron module with residual connections. It performs channel-wise optimization to suppress feature redundancy and refine representations. Additionally, we froze the feature extractor during fine-tuning. This strategy significantly reduces computational consumption and facilitates fast transfer and deployment across various interpretation tasks on homogeneous imagery. Our comprehensive evaluation on the sparsely labeled dataset MiniFrance-S and the fully labeled Gaofen Image Dataset achieved mean intersection over union scores of 42.7% and 66.5%, respectively, outperforming previous works. This demonstrates that our approach effectively reduces reliance on labeled imagery and increases transferability to downstream remote sensing tasks. Full article

Dark asphalt surfaces, absorbing about 95% of solar radiation and warming to 60–70 °C during summer, intensify urban heat while providing substantial prospects for energy extraction. This review evaluates four primary technologies—asphalt solar collectors (ASCs, including phase change material (PCM) integration), photovoltaic (PV) systems, vibration-based harvesting, thermoelectric generators (TEGs)—focusing on their principles, efficiencies, and urban applications. ASCs achieve up to 30% efficiency with a 150–300 W/m² output, reducing pavement temperatures by 0.5–3.2 °C, while PV pavements yield 42–49% efficiency, generating 245 kWh/m² and lowering temperatures by an average of 6.4 °C. Piezoelectric transducers produce 50.41 mW under traffic loads, and TEGs deliver 0.3–5.0 W with a 23 °C gradient. Applications include powering sensors, streetlights, and de-icing systems, with ASCs extending pavement life by 3 years. Hybrid systems, like PV/T, achieve 37.31% efficiency, enhancing UHI mitigation and emissions reduction. Economically, ASCs offer a 5-year payback period with a USD 3000 net present value, though PV and piezoelectric systems face cost and durability challenges. Environmental benefits include 30–40% heat retention for winter use and 17% increased PV self-use with EV integration. Despite significant potential, high costs and scalability issues hinder adoption. Future research should optimize designs, develop adaptive materials, and validate systems under real-world conditions to advance sustainable urban infrastructure. Full article

This study presents an AI-enhanced pedestrian simulation model for subway stations, combining the Social Force Model (SFM) with LiDAR trajectory data from Samseong Station in Seoul. To reflect time-dependent behavioral differences, RMSProp-based optimization is performed separately for the morning peak, leisure hours, and evening peak, yielding time-specific parameter sets. Compared to baseline models with static parameters, the proposed method reduces prediction errors (MSE) by 50.1% to 84.7%. The model integrates adaptive learning rates, mini-batch training, and L2 regularization, enabling robust convergence and generalization across varied pedestrian densities. Its accuracy and modular design support real-world applications such as pre-construction design testing, post-opening monitoring, and capacity planning. The framework also contributes to Sustainable Urban Mobility Plans (SUMPs) by enabling predictive, data-driven evaluation of pedestrian flow dynamics in complex station environments. Full article

Under the continuous disturbance of ecosystems driven by urbanization, landscape fragmentation and the disruption of ecological processes and functions are key challenges in optimizing ecological networks (EN). This study aims to examine the spatiotemporal evolution of topological patterns, ecological processes, and ecosystem services (ES) in Wuhan from the “pattern–process–function” perspective. To overcome the lag in research concerning the coupling of ecological processes, functions, and spatial patterns, we explore the long-term dynamic evolution of ecosystem structure, process, and function by integrating multi-source data, including remote sensing, enabling comprehensive spatiotemporal analysis from 2000 to 2020. Addressing limitations in current EN optimization approaches, we integrate morphological spatial pattern analysis (MSPA), use circuit theory to identify EN components, and conduct spatial optimization accurately. We further assess the effectiveness of two scenario types: “pattern–function” and “pattern–process”. The results reveal a distinct “increase-then-decrease” trend in EN structural attributes: from 2000 to 2020, source areas declined from 39 (900 km²) to 37 (725 km²), while corridor numbers fluctuated before stabilizing at 89. Ecological processes and functions exhibited phased fluctuations. Among water-related indicators, water conservation (as a core function), and modified normalized difference water index (MNDWI, as a key process) predominantly drive positive correlations under the “pattern–function” and “pattern–process” scenarios, respectively. The “pattern–function” scenario strengthens core area connectivity (24% and 4% slower degradation under targeted/random attacks, respectively), enhancing resistance to general disturbances, whereas the “pattern–process” scenario increases redundancy in edge transition zones (21% slower degradation under targeted attacks), improving resilience to targeted disruptions. This complementary design results in a gradient EN structure characterized by core stability and peripheral resilience. This study pioneers an EN optimization framework that systematically integrates identification, assessment, optimization, and validation into a closed-loop workflow. Notably, it establishes a quantifiable, multi-objective decision basis for EN optimization, offering transferable guidance for green infrastructure planning and ecological restoration from a pattern–process–function perspective. Full article

Societies are aiming to have a higher ecological consciousness in wastewater treatment operations and achieve a more sustainable future. With this said, global demands for larger quantities of resources and the consequent waste generated will inevitably lead to the exhaustion of current municipal wastewater treatment works. The utilization of biosolids (particularly microbial proteins) from wastewater treatment operations could generate a sustainable bio-adhesive for the wood industry, reduce carbon footprint, mitigate health concerns related to the use of carcinogenic components, and support a more circular economic option for wastewater treatment. A techno-economic analysis for three 10 MGD wastewater treatment operations producing roughly 11,300 dry pounds of biosolids per day, in conjunction with co-feedstock defatted soy flour protein at varying ratios (i.e., 0%, 15%, and 50% wet weight), was conducted. Aspen Capital Cost Estimator V12 was used to design and estimate installed equipment additions for wastewater treatment plant integration into an urban biorefinery process. Due to the mechanical attributes and market competition, the chosen selling prices of each adhesive per pound were set for analysis as USD 0.75 for Plant Option P1, USD 0.85 for Plant Option P2, and USD 1.00 for Plant Option P3. Over a 20-year life, each plant option demonstrated economic viability with high NPVs of USD 107.9M, USD 178.7M, and USD 502.2M and internal rates of return (IRRs) of 24.0%, 29.0%, and 44.2% respectively. The options examined have low production costs of USD 0.14 and USD 0.19 per pound, minimum selling prices of USD 0.42–USD 0.51 per pound, resulting in between 2- and 4-year payback periods. Sensitivity analysis shows the effects biosolid production fluctuations, raw material market price, and adhesive selling price have on economics. The results proved profitable even with large variations in the feedstock and raw material prices, requiring low market selling prices to reach the hurdle rate of examination. This technology is economically enticing, and the positive environmental impact of waste utilization encourages further development and analysis of the bio-adhesive process. Full article

Efficient detection of road surface defects is vital for timely maintenance and traffic safety. This study introduces a novel AI-powered web framework, TriRoad AI, that integrates multiple versions of the You Only Look Once (YOLO) object detection algorithms—specifically YOLOv8 and YOLOv11—for automated detection of potholes and cracks. A user-friendly browser interface was developed to enable real-time image analysis, confidence-based prediction filtering, and severity-based geolocation mapping using OpenStreetMap. Experimental evaluation was conducted using two datasets: one from online sources and another from field-collected images in Ankara, Turkey. YOLOv8 achieved a mean accuracy of 88.43% on internet-sourced images, while YOLOv11-B demonstrated higher robustness in challenging field environments with a detection accuracy of 46.15%, and YOLOv8 followed closely with 44.92% on mixed field images. The Gemini AI model, although highly effective in controlled environments (97.64% detection accuracy), exhibited a significant performance drop of up to 80% in complex field scenarios, with its accuracy falling to 18.50%. The proposed platform’s uniqueness lies in its fully integrated, browser-based design, requiring no device-specific installation, and its incorporation of severity classification with interactive geospatial visualization. These contributions address current gaps in generalization, accessibility, and practical deployment, offering a scalable solution for smart infrastructure monitoring and preventive maintenance planning in urban environments. Full article

To address the modeling complexity and multi-objective collaborative optimization challenges in multi-depot and multiple unmanned aerial vehicle (UAV) delivery task planning, this paper proposes a bi-layer planning framework, which comprehensively considers resource constraints, multi-depot coordination, and the coupling characteristics of path execution. The novelty of this work lies in the seamless integration of an enhanced genetic algorithm and tailored swarm optimization within a unified two-tier architecture. The upper layer tackles the task assignment problem by formulating a multi-objective optimization model aimed at minimizing economic costs, delivery delays, and the number of UAVs deployed. The Enhanced Non-Dominated Sorting Genetic Algorithm II (ENSGA-II) is developed, incorporating heuristic initialization, goal-oriented search operators, an adaptive mutation mechanism, and a staged evolution control strategy to improve solution feasibility and distribution quality. The main contributions are threefold: (1) a novel ENSGA-II design for efficient and well-distributed task allocation; (2) an improved PSO-based path planner with chaotic initialization and adaptive parameters; and (3) comprehensive validation demonstrating substantial gains over baseline methods. The lower layer addresses the path planning problem by establishing a multi-objective model that considers path length, flight risk, and altitude variation. An improved particle swarm optimization (PSO) algorithm is proposed by integrating chaotic initialization, linearly adjusted acceleration coefficients and maximum velocity, a stochastic disturbance-based position update mechanism, and an adaptively tuned inertia weight to enhance algorithmic performance and path generation quality. Simulation results under typical task scenarios demonstrate that the proposed model achieves an average reduction of 47.8% in economic costs and 71.4% in UAV deployment quantity while significantly reducing delivery window violations. The framework exhibits excellent capability in multi-objective collaborative optimization. The ENSGA-II algorithm outperforms baseline algorithms significantly across performance metrics, achieving a hypervolume (HV) value of 1.0771 (improving by 72.35% to 109.82%) and an average inverted generational distance (IGD) of 0.0295, markedly better than those of comparison algorithms (ranging from 0.0893 to 0.2714). The algorithm also demonstrates overwhelming superiority in the C-metric, indicating outstanding global optimization capability in terms of distribution, convergence, and the diversity of the solution set. Moreover, the proposed framework and algorithm are both effective and feasible, offering a novel approach to low-altitude urban logistics delivery problems. Full article

Urban road travel time prediction is a critical component of intelligent transportation systems. However, accurate prediction remains challenging due to the high volatility and randomness of urban road traffic. This study compares the predictive performance of deep learning methods with traditional shallow learning methods for urban road travel time prediction, and explores the potential for improving prediction effectiveness through multi-run training strategies for hyperparameter optimization and ensemble learning. The study employs urban road travel time data from Shenzhen, China, designing 10 prediction scenarios with different sliding time window lengths and prediction scales. To address the randomness issue in deep learning models, we adopt a strategy of conducting five independent training runs for each hyperparameter configuration and using statistical measures to obtain stable performance evaluations. For model comparison, we implement multiple shallow learning models (linear regression, ridge regression, LASSO regression, random forest) and deep learning models (LSTM-DNN, DNN), and construct ensemble learning models based on linear regression and LSTM-DNN as base learners. The experimental results demonstrate that: (1) deep learning models generally outperform shallow learning models in terms of Mean Absolute Percentage Error (MAPE), particularly the LSTM-DNN model which achieves the best MAPE values across all prediction scenarios with 30 min sliding time windows; (2) in terms of Root Mean Square Error (RMSE), shallow learning models such as random forest perform better in most scenarios; (3) ensemble learning models show certain advantages in some prediction scenarios, but the improvement effects are limited and scenario-dependent. The research results provide empirical reference for method selection in urban road travel time prediction, while also revealing the limitations of single data sources and the differences in model performance under different evaluation metrics, offering directions for future research. Full article

This paper examines how artificial intelligence (AI) can be strategically deployed to enhance urban planning and environmental livability in Riyadh by generating data-driven, people-centric design interventions. Unlike previous studies that concentrate primarily on visualization, this research proposes an integrative appraisal framework that combines AI-generated design with site-specific environmental data and native vegetation typologies. This study was conducted across key jurisdictional areas including the Northern Ring Road, King Abdullah Road, Al Rabwa, Al-Malaz, Al-Suwaidi, Al-Batha, and King Fahd Road. Using AI tools, urban scenarios were developed to incorporate expanded pedestrian pathways (up to 3.5 m), dedicated bicycle lanes (up to 3.0 m), and ecologically adaptive green buffer zones featuring native drought-resistant species such as Date Palm, Acacia, and Sidr. The quantitative analysis of post-intervention outcomes revealed surface temperature reductions of 3.2–4.5 °C and significant improvements in urban esthetics, walkability, and perceived safety—measured on a five-point Likert scale with 80–100% increases in user satisfaction. Species selection was validated for ecological adaptability, minimal maintenance needs, and compatibility with Riyadh’s sandy soils. This study directly supports the Kingdom of Saudi Arabia’s Vision 2030 by demonstrating how emerging technologies like AI can drive smart, sustainable urban transformation. It aligns with Vision 2030’s urban development goals under the Quality-of-Life Program and environmental sustainability pillar, promoting healthier, more connected cities with elevated livability standards. The research not only delivers practical design recommendations for planners seeking to embed sustainability and digital innovation in Saudi urbanism but also addresses real-world constraints such as budgetary limitations and infrastructure integration. Full article

The demand for large-scale, heavy-duty autonomous pavement-sweeping robots is rising due to urban growth, hygiene needs, and labor shortages. Ensuring their health and safe operation in dynamic outdoor environments is vital, as terrain unevenness and slope gradients can accelerate wear, increase maintenance costs, and pose safety risks. This study introduces an AI-driven condition monitoring (CM) framework designed to detect terrain unevenness and slope gradients in real time, distinguishing between safe and unsafe conditions. As system vibration levels and energy consumption vary with terrain unevenness and slope gradients, vibration and current data are collected for five CM classes identified: safe, moderately safe terrain, moderately safe slope, unsafe terrain, and unsafe slope. A simple-structured one-dimensional convolutional neural network (1D CNN) model is developed for fast and accurate prediction of the safe to unsafe classes for real-time application. An in-house developed large-scale autonomous pavement-sweeping robot, PANTHERA 2.0, is used for data collection and real-time experiments. The training dataset is generated by extracting representative vibration and heterogeneous slope data using three types of interoceptive sensors mounted in different zones of the robot. These sensors complement each other to enable accurate class prediction. The dataset includes angular velocity data from an IMU, vibration acceleration data from three vibration sensors, and current consumption data from three current sensors attached to the key motors. A CM-map framework is developed for real-time monitoring of the robot by fusing the predicted anomalous classes onto a 3D occupancy map of the workspace. The performance of the trained CM framework is evaluated through offline and real-time field trials using statistical measurement metrics, achieving an average class prediction accuracy of 92% and 90.8%, respectively. This demonstrates that the proposed CM framework enables maintenance teams to take timely and appropriate actions, including the adoption of suitable maintenance strategies. Full article

In Brazil, approximately 93 trillion litres of water are withdrawn annually from surface and groundwater sources, with urban human use being the second-largest water consumer. Therefore, reducing water consumption in buildings is crucial. This study performed a technical and economic analysis of isolated and combined water-saving strategies at the Central Library of the Federal University of Santa Catarina (UFSC). The strategies assessed included water-saving appliances, rainwater harvesting, and greywater and blackwater reuse, individually and in four combined scenarios. User surveys provided data on the frequency and duration of water appliance use and cleaning activities, while on-site water flow measurements enabled the estimation of water end uses. The potential for potable water savings was then determined for each strategy and scenario. The highest savings (77.96%) were achieved by combining water-saving appliances with blackwater reuse, followed by a combination of water-saving appliances, greywater reuse, and rainwater harvesting (65.73%). All strategies were economically viable, except the combination of water-saving appliances with greywater reuse, which showed a negative net present value. The scenario combining water-saving appliances and blackwater reuse generated the most significant financial savings (R$7782.48 per month), with a payback period of 50 months. Given its environmental and economic benefits, these scenarios were recommended for implementation. The study may be replicated worldwide, and one key conclusion is that libraries consume a significant amount of potable water for non-potable purposes, which should be supplemented with alternative sources. It is essential to consider whether the building is already built or under design, as some implementation processes require design modifications. Full article

Rising temperatures are one of the most severe consequences of climate change, and the built environment plays a significant role in exacerbating heat, particularly in urban areas. In densely populated cities with hot climates, buildings release heat generated from cooling their interiors, contributing to the urban heat island (UHI) effect. Global research actively seeks ways to reduce UHI and promote a more sustainable built environment. Leadership in Energy and Environmental Design (LEED) is among the most widely used sustainability assessment systems. Additionally, digital technologies, especially Building Information Modelling (BIM), are increasingly used to assess and improve energy performance in buildings. While there are frameworks that apply LEED and BIM separately to address UHI strategies, there are potential LEED–BIM integrations which need to be investigated. This study investigates how LEED and BIM can be integrated to support UHI mitigation efforts. A systematic literature review was conducted to examine existing integrations, analyzing trends by publication year, country, and building type. The study identified approximately thirty examples of LEED–BIM integrations supporting ten UHI mitigation strategies. However, it also highlighted underutilized BIM technologies and gaps in addressing certain strategies. The study proposes a framework to help practitioners and policymakers apply LEED–BIM integrations more efficiently, reducing the effort required to implement UHI mitigation strategies while enhancing their practicality and effectiveness. Full article