Urban Science

Post-war Aleppo is often framed through destruction, legal constraints, and the technical demands of reconstruction. This article challenges that assumption by re-reading Aleppo’s pre-2011 municipal vision as an analytical resource for post-war recovery. The study adopts a qualitative interpretive methodology based on municipal archival material, including the City Council work programme, strategic planning presentations, project documents, and materials related to the City Development Strategy, Madinatuna initiative, the old city, Bab Antakiya, and major public-space and service initiatives. The analysis followed three steps: identifying repeated municipal priorities and planning concepts; organizing them into thematic axes; and interpreting flagship projects as spatial expressions of a broader municipal vision. To assess post-war relevance, the archive is also read against evidence of damage, displacement, urban functionality, and heritage loss. The results show that Aleppo’s pre-2011 municipal vision can be reconstructed through six interrelated axes: strategic urban development and managed growth; the old city as a living urban fabric; urban repair in the city centre; mobility and accessibility; culture and social development; and development partnerships and international cooperation. The findings reveal that these axes formed a partially integrated municipal urbanism rather than isolated projects, while flagship interventions such as Bab Antakiya, the Green Path, the river corridor, and the Citadel surroundings materialized this logic. The study also finds that this vision remained institutionally vulnerable because of political centralization and limited municipal autonomy. It concludes that post-war recovery should build on critical continuity rather than reconstruction from scratch. Full article

National Forest Trails (NFTs), a key component of forest welfare infrastructure, increasingly require a shift from government-led management to citizen-participatory governance. This study examined the structural relationships among volunteer motivation, activity satisfaction, perceived quality-of-life (QoL) change, and behavioral intention in the context of NFT volunteering. A survey was conducted with 217 adults who had participated in forest trail volunteering programs in Korea, and the data were analyzed using structural equation modeling (SEM). The results showed that volunteer motivation had significant positive effects on reward importance, activity satisfaction, and perceived QoL change. Activity satisfaction positively influenced both Future Participation Intention and Active Participation Intention, whereas perceived QoL change had a significant positive effect only on Active Participation Intention. In addition, activity satisfaction and perceived QoL change mediated the relationship between volunteer motivation and Active Participation Intention. These findings suggest that forest trail volunteers are not merely supplementary labor for trail management, but active participants in forest governance who both contribute to and benefit from the environments they help sustain. Overall, the study indicates that sustainable NFT volunteering depends not only on motivation itself, but also on the quality and personal meaning of the volunteer experience. The findings highlight the importance of experience-centered program design, appropriate recognition systems, and greater attention to participant-centered well-being outcomes in sustainable forest trail governance. Full article

This work proposes a spatial optimization framework based on Monte Carlo Tree Search (MCTS) to support infrastructure planning in complex urban environments. The challenge lies in integrating diverse geospatial and socioeconomic data to balance efficiency, defined as potential demand, with territorial equity, related to mobility needs. The approach formulates the problem as a sequential decision process, capturing the interdependence of location choices and enabling structured exploration of the solution space. Unlike traditional optimization methods that rely on local heuristics or require strong simplifications, this framework accommodates non-linear relationships and competing objectives without sacrificing system complexity. The use of MCTS effectively balances exploration and exploitation, making it well-suited for high-dimensional, non-convex spatial problems. This methodology offers a flexible and scalable tool for urban planning, adaptable to various contexts and constraints. It supports generating solutions that are both efficient and aligned with equity considerations, providing valuable guidance for decision-making in rapidly evolving urban systems. Full article

This study introduces RE-VAL (REal-estate VALuation), an explainable framework for urban real-estate analysis that integrates reproducible data acquisition, geographically informed feature processing, predictive benchmarking, and interpretable outputs suitable for decision-support-oriented analysis. Unlike static automated valuation models, the RE-VAL framework is designed to reflect context-dependent market behaviour across heterogeneous urban areas. The comparative evaluation on 1153 residential listings from Cagliari (Italy) showed that MLP achieved the strongest predictive performance, while Random Forest provided the most convincing balance between predictive competitiveness and interpretability. Beyond point estimation, the framework leverages SHAP-based decomposition to translate algorithmic outputs into transparent, monetary-based “Bonus/Malus” adjustment tables. The analysis highlights the presence of potentially non-linear interactions, including a possible premium associated with energy efficiency in prestigious areas, and suggests that the framework can remain informative when incomplete technical data are preserved as potential proxy signals rather than being discarded as noise. Rather than identifying a single predictor, RE-VAL provides a transparent, extensible and decision-oriented workflow for urban real-estate valuation, advancing the integration of explainable artificial intelligence within complex spatial-economic systems. Full article

This study introduces a multi-source spatial methodology that moves beyond the traditional urban/rural dichotomy to classify the American landscape into detailed, temporally defined settlement types. By combining historical housing unit and population estimates (HHUUD10 and LTDB) standardized to 2010 census tract boundaries with high-resolution, grid-level data on the built environment (HISDAC-US), this research establishes a settlement typology based on the development history of detailed geographic units. This framework classifies areas (from Prewar Cores and 21st-Century Suburbs to exurban fringes, outlying towns and rural areas) based on their era of development and proximity to urban centers. Applying this typology reveals profound spatial and demographic decentralization spanning eighty years of metropolitan expansion. The findings demonstrate a stark geographic sorting: expanding greenfield edges and exurbs have become magnets for high-income, highly educated, and predominantly White populations. However, longitudinal tracking reveals a distinct morphological “life-course” within suburban rings. As older suburbs age and their housing stock depreciates, they open to wider demographic integration, transforming into destinations for Black and foreign-born residents. Furthermore, the data highlight a contemporary polarization of human capital, concentrated in both the newest suburban peripheries and the resurgent urban cores, contrasting with persistent economic decline in outlying towns and rural areas. Ultimately, this methodology provides a flexible, longitudinal framework for understanding the long-term morphological and demographic evolution of American settlement. Full article

In an increasingly urbanized world, ensuring equitable access to urban green spaces (UGS) is essential for human well-being. Previous studies have largely focused on measuring proximity or availability of UGS, often neglecting the role of the walkable environment and the interaction between supply, demand, and movement flows. To address this gap, we develop a novel modeling framework that integrates the Detour Index (DI) and Local Significance (LS) to jointly capture physical barriers and recreational flows within urban street networks. Using openly available data from OpenStreetMap and Urban Atlas, we model the walkable environment in Leipzig, Germany, at a high spatial resolution. The approach enables the identification of inefficient routes, potential barriers, and areas of high use intensity, providing actionable insights for urban planning. By combining network-based accessibility with flow-based indicators, our method advances existing approaches that rely on static distance measures. The analyses of different planning alternatives further demonstrate how changes in urban structure affect accessibility and crowding patterns. The framework is transferable and based on open data, providing a foundation for future research to integrate behavioral factors and richer datasets to further refine accessibility modeling. Full article

Background: Translating urban environmental health evidence into actionable policies remains challenging in South-Eastern Europe, where environmental epidemiology has yet to reach maturity and institutional capacity and cross-sector coordination are suboptimal. This study assessed stakeholders’ awareness, perceived roles, and prioritization of urban health challenges, alongside the barriers and evidence needs related to healthy and sustainable urban development. Methods: A cross-sectional online survey was conducted between March and May 2025 among 108 stakeholders identified through a collaborative evaluation process. Participants represented national institutions, municipal actors, academia, non-governmental organizations, business, and citizens. They reported on their role and influence, and were asked to identify priority urban health problems, relevant policies and actions, perceived barriers to decision-making, and expected benefits of addressing priority problems. Results: Most respondents reported limited or moderate influence on urban decision-making. Priority problems clustered around air pollution, traffic, and land-use pressures, with climate change and heat also frequently cited. Dominant barriers included lack of coordination and policy continuity, insufficient political support, and limited funding and institutional capacity. Anticipated gains centered on improved public health, cleaner air, and citizen satisfaction, with broader quality-of-life and economic co-benefits also identified. Conclusions: Prioritized urban environmental problems are largely consistent with scientific evidence on their health impacts, though certain risk factors remain underestimated. Access to specific, actionable scientific evidence and the co-production of solutions with broad stakeholder representation are essential prerequisites for effective urban health policy and practice. Full article

This study investigates whether spa settlements can be analytically interpreted through a relational spascape framework that reveals structural and configurational patterns beyond conventional typological classifications. In the context of increasing interest in therapeutic landscapes and heritage-sensitive development, spa settlements represent complex spatial systems shaped by the interplay of natural resources, urban form, and socio-cultural practices, yet they remain insufficiently understood through existing analytical models. The methodology is based on a structured analytical design combining three urbanization dimensions (material transformation, territorial regulation, and everyday life) with six thematic fields, operationalized through graded cross-affiliation scoring. The empirical research is conducted on a sample of 12 spa settlements in Serbia, selected to reflect diverse geographical, morphological, and developmental conditions. Statistical calibration was performed using Principal Component Analysis (PCA) and hierarchical clustering to identify underlying structural relationships and configurational groupings. The results indicate that spa settlements operate as multi-affiliated relational entities rather than fixed typologies, exhibiting dimension-specific structural logics and forming distinct configurational families depending on the analytical perspective applied. PCA reveals differentiated internal structures across dimensions, while clustering confirms the absence of a single stable typology. The findings support a relational understanding of spa settlements as dynamic spatial systems characterized by shifting alignments of material, regulatory, and experiential factors. Beyond the Serbian context, the study offers a transferable methodological framework that connects qualitative urban interpretation with quantitative spatial analysis, contributing to heritage-sensitive planning, territorial governance, and the management of spa systems as relational clusters. Full article

In recent years, the use of warm-season species, which are species requiring less water, has been pursued in continental areas, but their dormancy and spring green-up need to be properly defined. In urban green areas, we find that small-scale microclimatic differences, while less intense than classical urban–rural gradients, still influence vegetation performance and spring green-up. This study examines the impact of microclimatic temperature variation on the spring green-up of different cool-season and warm-season turfgrasses in the continental climate of Madrid, Spain. The evaluation of colour change during the spring green-up process has been conducted using different vegetation indices, and mathematical models for correlating temperature with the indices’ values have been obtained. The results indicate that with average temperatures varying by about 1.3 °C and 0.9 °C in January and February, respectively, there have been marked differences in spring green-up, especially in cool-season turfgrasses, of almost one month. In contrast, differences in warm-season turfgrasses were reduced. Among the four vegetation indices, Canopeo has proved to be the best for detecting the early stages of spring green-up, with R² values ranging from 0.43 to 0.92. Meanwhile, the tailored greenness index for turfgrass was the most effective for determining the moment at which warm-season grasses achieve the colouration of cool-season grasses, with R² ranging from 0.79 to 0.85. Finally, the green leaf index was particularly valuable for identifying differences among species and sectors throughout the entire spring green-up process. Models based on this index achieve high R² values (0.57 to 0.94), but these models predict the moment at which warm-season grasses achieve cool-season grasses’ colouration later than it actually occurs. Understanding how turfgrasses respond to these localised microclimatic conditions is essential for selecting resilient species and improving maintenance strategies in parks, sports areas, and other components of urban green infrastructure. Full article

Fragmented transit governance across multiple agencies makes measuring service inequality in large metropolitan regions notoriously difficult. This paper maps schedule-aware transit service intensity—an origin-side, supply-focused component of accessibility—across the Greater Toronto Area (GTA) by integrating General Transit Feed Specification (GTFS) data from six providers within an H3 hierarchical hexagonal grid. The measure does not capture destination access, travel time, transfers, fares, reliability, or crowding, and is therefore framed throughout as a service-intensity indicator rather than a full accessibility evaluation. We operationalize the indicator as the number of cumulative scheduled departures per hour reachable within an 800 m walking catchment for three distinct time windows: weekday peak, weekday midday, and Saturday midday. Across 9635 hexagons and 23,026 stops, our results reveal a sharply hierarchical regional network. When weighted by population, 16.4% of GTA residents have no scheduled service within walking distance during the weekday morning peak; the corresponding area-weighted share, reflecting the extensive greenbelt and agricultural fringe, is 70.6%. Only 22.6% of hexagons reach at least 12 departures per hour, while 75.5% of residents meet that threshold. Median service intensity drops from 234.25 departures per hour in the Urban Core to zero beyond the Inner Suburban Ring, and service thins out on weekends, with retention in the outer rings dropping to roughly 75% of weekday levels. Spearman correlations show that service intensity is concentrated in denser, more diverse, and lower-income census-tract contexts, with population density emerging as the strongest hex-level correlate ($\rho =0.69$); after Clifford–Richardson correction for spatial autocorrelation (effective $n\approx 745$), the principal CT-level correlations remain statistically significant ($p<{10}^{-15}$), and partial correlations controlling for density indicate that socioeconomic composition retains an independent, if attenuated, association. Under one-tract-one-observation aggregation ($n=1144$ unique tracts), the income gradient strengthens to $\rho =-0.74$ and becomes co-equal in magnitude with population density ($\rho =0.74$), confirming that the hex-level coefficients are not artifacts of pseudo-replication. A population-weighted Gini coefficient of 0.60 confirms substantial distributional inequality. Sensitivity analyses confirm that the Inner-to-Outer Suburban break is robust to alternative ring thresholds (10/25/40 and 20/35/50 km), to exclusion of the four Halton municipalities affected by incomplete local-feed coverage, to H3 resolution at the municipal level, and—in a representative shortest-path network sub-analysis for Pickering (not a full GTA-wide network-distance test)—to use of network rather than Euclidean walking distance. These patterns suggest that a substantial gap exists between where suburban residential growth has occurred and where frequent transit service is available, a pattern with historical roots in the 1996–2006 service–need alignment, though the 2006–2023 trajectory is not directly measured here. The results suggest that the transition zone between the inner and outer suburbs may warrant further investigation as a planning focus, and that cross-agency weekend service coordination merits further analysis as a potential equity dimension. This multi-agency H3 framework establishes a reproducible baseline for monitoring schedule-aware service intensity in polycentric metropolitan areas. Full article

Smart cities generate vast, heterogeneous data streams from transportation networks, energy grids, environmental sensors, and public services, yet the semantic fragmentation of these data silos prevents urban operators from deriving actionable, cross-domain intelligence. Knowledge graphs (KGs) have emerged as a powerful paradigm for integrating diverse, large-scale data collections through graph-based representations of entities and their relationships. This paper applies the Design Science Research Methodology (DSRM) to design, develop, and evaluate UrbanKG, a layered artifact that deploys knowledge graphs as the semantic backbone of smart city data infrastructure. We demonstrate the framework through a proof-of-concept implementation using publicly available urban datasets across five domains, yielding a 287,000-triple knowledge graph validated through cross-domain SPARQL queries and accessibility analysis. Following the six DSRM process steps—problem identification, objective definition, design and development, demonstration, evaluation, and communication—the framework addresses ontology design, multi-source data fusion, federated governance, temporal reasoning, and hybrid deductive–inductive inference. The artifact satisfies all five design objectives and contributes four transferable design principles. Six open research challenges are identified as the forward research agenda. Full article

Architectural, urban design, and planning practices are increasingly expected to demonstrate measurable impact, accountability, and responsiveness to complex environmental and social challenges. Evidence-based design (EBD) and research-informed design (RID), which ground design decisions in systematically gathered and critically evaluated knowledge, offer a structured pathway to bridge research and practice. Despite growing recognition, however, EBD and RID remain unevenly integrated across professional practice, particularly within small and medium-sized enterprises (SMEs), which constitute the majority of firms in Europe. This paper explores how SMEs understand, adopt, and operationalize research within architectural, urban design, and planning processes, while identifying the factors that enable or constrain the integration of research into practice. Drawing on a qualitative multiple-case study of four European firms located in Cyprus, Portugal, Italy, and Croatia the study uses semi-structured interviews and thematic analysis supported by AI-assisted coding to identify patterns in how systematic research is understood, enacted and positioned in everyday SME practices. The findings show that research integration depends less on firm size than on the interplay between client expectations, organizational culture, and professional ideology. Practices span a spectrum ranging from ad hoc, compliance-oriented, and project-specific inquiry to strategically embedded and, in one case, activist research-led modes. While research engagement can enhance credibility, efficiency, and innovation, persistent barriers—including limited resources, client resistance, deficient knowledge-management routines, and the absence of shared evaluative frameworks—continue to hinder systematic adoption. Building on the cross-case analysis, the paper proposes a conceptual framework of different modes of research integration in SMEs, offering a heuristic lens for understanding how organizational and contextual factors shape the uptake of research in design practice. The findings contribute to ongoing discussions on practice-based research and highlight the need for more context-sensitive approaches to research integration in small and medium-sized design firms. Full article

For decades, transportation planning has relied on utilitarian principles, which aim to maximize cumulative benefit by meeting the needs of the “average user.” This approach ignores fundamental differences between population groups and produces uniform solutions that fail to address the diverse needs of women, children, the elderly, and other disadvantaged populations. In response, there are growing calls for a transportation justice paradigm that emphasizes individuals’ ability to access meaningful opportunities according to their characteristics, abilities, and life circumstances. Autonomous Mobility on Demand (AMoD) holds the potential to transform future transportation systems. However, without deliberate planning, they risk replicating existing patterns of inequality for populations whose mobility needs differ from those of the average user. This study applies transportation justice principles to examine how AMoD systems can be designed to meet diverse user needs. Using a combination of an Autoencoder for learning reduced representations and an HDBSCAN clustering algorithm, the analysis identifies distinct travel patterns across socioeconomic groups. These findings reveal significant gaps between population segments, particularly among children and older adults, and demonstrate how AMoD systems could expand access to after-school activities, reduce social isolation among elderly women, and reduce various transportation-related social gaps by improving their ability to reach a wider range of opportunities. Full article

The integration of renewable energy technologies into urban buildings is a key strategy in sustainable city development. This study explores the application of building-integrated photovoltaic (BIPV) systems in a selected building at Vilnius Gediminas Technical University (VGTU), aiming to identify the most balanced solution among energy efficiency, architectural quality, and operational feasibility. Using a Building Information Model (BIM) of the existing structure, five alternative design scenarios were developed by varying the number and capacity of façade-mounted photovoltaic (PV) panels and semi-transparent PV windows. Each scenario was evaluated against six criteria: (1) potential solar energy yield, (2) temporal correlation between energy generation and building consumption, (3) maintenance accessibility and associated cost, (4) architectural aesthetics, (5) installation cost, and (6) cost effectiveness. To ensure a rigorous and interdisciplinary evaluation, the Delphi-based ELECTRE Multi-Criteria Decision-Making (MCDM) method was applied. Expert panels representing disciplines of construction engineering, architecture, electrical engineering, and business management participated in determining the relative importance of each criterion. The results demonstrate the potential of combining BIM-based energy simulation with expert-driven decision analysis to optimize BIPV integration strategies in complex urban environments. The proposed framework offers a replicable methodology for guiding sustainable façade design and supporting the adoption of renewable energy in various public and administrative buildings across cities. Full article

Walkability has traditionally been assessed through physical indicators and objective metrics of the built environment; however, persistent methodological fragmentation limits its interpretive capacity in complex urban contexts. This article proposes an operational analytical framework for the analysis of walkability in Latin American intermediate commercial cities, understood as a relational and multiscale urban condition. The study adopts a qualitative–analytical design based on a systematic literature review and the comparative analysis of seven international walkability assessment methodologies. Through this critical synthesis, a framework is constructed that integrates macro, meso and micro scales, differentiated analytical domains, and a sequential interpretative procedure. The main contribution lies in providing an analytical structure that enables coherent interpretation of the tensions between urban structure, socio-economic functioning and pedestrian experience, avoiding reductive or decontextualized readings of walking in intermediate commercial cities. Full article

Emergency response in urban gas pipeline networks is highly sensitive to stochastic traffic conditions, which introduce substantial uncertainty in crew travel times to leakage sites. Existing facility location models typically rely on predefined candidate sites and deterministic travel assumptions, limiting their ability to capture full-cycle dynamic recovery processes under random leakage events and traffic congestion. This study develops a candidate-free location optimization framework for repair station siting under stochastic road resistance conditions, aiming to characterize spatial variability in emergency response capability. The framework integrates a candidate-free facility location model with a hybrid greedy–Monte Carlo solution strategy to optimize station layouts across network-wide stochastic scenarios. Coverage reliability, response time, and construction cost are jointly considered to support robust siting decisions. A case study based on the real road and gas pipeline networks of City H demonstrates the effectiveness of the proposed approach. Across 20,000 stochastic road resistance scenarios, the optimized layout achieves an average service coverage rate of 97.77% within the specified response time threshold, while maintaining stable performance under variability. Although increasing the number of stations enhances response capability, the improvement exhibits clear diminishing marginal returns. These findings provide quantitative guidance for determining cost-effective station scale and prioritizing core hub locations under uncertainty. The proposed framework offers a structured decision-support tool for resilience-oriented planning, prioritization of critical segments, and evaluation of emergency response and maintenance strategies in urban gas pipeline systems. Full article

Dhaka, one of the world’s most densely populated megacities, has faced a severe ecological decline, with green cover plummeting from 44.80% in 1975 to approximately 24.50% by 2005. In response, urban rooftop farming has emerged as a vital adaptation strategy to mitigate the urban heat island effect and air pollution. Objective: This study evaluates the transition from “pixels to policy” by testing automated identification methods for URF to support evidence-based urban governance, specifically the 10.00% holding tax rebate offered by the Dhaka North City Corporation. Utilizing high-resolution (3 cm) drone imagery across three diverse areas of interest—representing planned, organic, and mixed-use urban fabrics, the research compares the performance of Support Vector Machines, U-Net, and Text-Segment Anything Model. Accuracy was validated using a confusion matrix based on 1000 randomly stratified sample points. The SVM model emerged as the most reliable, achieving a Kappa index of 0.74 and 100.00% user accuracy for identifying rooftop vegetation, significantly outperforming the U-Net model (Kappa 0.14). Spatial analysis quantified a distinct “green divide,” revealing that while planned residential zones achieved over 7.50% rooftop greening coverage, dense organic settlements were limited to 6.00%. The study concludes that high-accuracy SVM-based identification provides a scalable foundation for automating fiscal incentives. To bridge the socio-spatial green divide, policy interventions must shift toward inclusive greening strategies, such as vertical farming, and formal integration of URF into Dhaka’s blue-green infrastructure networks. Full article

Investment in infrastructure is considered the foundation for economic growth. However, traditional construction and maintenance methods in Egypt are carbon-intensive, which conflicts with sustainability strategies. Therefore, there was a need to develop a model for evaluating highway maintenance methods to facilitate decision-making on the best ones, economically, environmentally, and socially. This study included a model for evaluating sustainability in road maintenance. It integrated carbon management and value engineering to facilitate the selection of the best alternatives for achieving sustainability. The literature on sustainability criteria covering the project life cycle was consulted, and 27 key factors across the three sustainability criteria were selected. A questionnaire was conducted to determine the weights of the criteria using the Analytic Hierarchy Process (AHP). Road maintenance scenarios were then developed, and the carbon emissions for each were calculated. The cost of carbon disposal was added to the project life cycle cost using CCS technology. This model was named SRMVE because it ultimately combines economic and environmental challenges into a single factor to facilitate a comparison of the proposed alternatives and achieve the best degree of sustainability. The model results were compared with the sustainability scores generated by the AHP to assess the extent of agreement. This model provides decision-makers with a way to sort through maintenance alternatives and identify those with the lowest lifecycle emissions while maintaining the service and safety levels. Full article

Urban traffic accidents emerge from complex interactions among traffic instability, roadway structure, environmental disturbance, and temporal dynamics, yet many existing prediction approaches still treat accident risk as a discrete classification problem over isolated observations. This study proposes a Continuous Hazard Field Intelligence Framework for Traffic Accident Emergence and Urban Safety Prediction, which models hidden urban danger as a topology-aware spatio-temporal hazard field that evolves continuously across connected transportation infrastructure. The framework integrates heterogeneous urban traffic observations, including incident records, crash data, roadway attributes, temporal cues, and contextual risk factors, into a unified hazard-aware learning pipeline. A dedicated preprocessing strategy combines topology-constrained spatial alignment, temporal hazard window embedding, risk-diffusion feature lifting, hazard-sensitive normalization, and continuous hazard surface initialization to convert fragmented event-centered observations into a smooth and learning-ready hazard representation. A structured deep learning architecture is then developed to perform spatial hazard encoding, temporal hazard evolution, continuous hazard reconstruction, and localized accident emergence prediction. Experimental evaluation was conducted on two large-scale real-world traffic safety datasets, namely the XTraffic Incident Dataset (2022–2024) with 1,441,904 records and the Motor Vehicle Collisions–Crashes Dataset with 2,026,647 records. All model configurations were evaluated under the same experimental setting, using the same dataset-specific preprocessing protocol, a 70/30 train–test split, and identical evaluation metrics. The final CHFI configuration achieves 99.12% accuracy, 98.94% precision, 98.76% recall, 98.85% F1-score, and 0.998 AUC on Dataset 1, and 98.63% accuracy, 98.41% precision, 98.16% recall, 98.28% F1-score, and 0.997 AUC on Dataset 2. Compared with the initial non-hazard-aware baseline configuration evaluated under the same data split and evaluation protocol, the final CHFI model improves the F1-score by 7.91 percentage points on Dataset 1 and 8.26 percentage points on Dataset 2. These results indicate that the proposed hazard-field formulation can improve accident-emergence prediction within the controlled experimental setting, while the reported gains should be interpreted relative to the specified baseline and evaluation design. Full article