Although bicycle theft is a common issue across many urban cities, the empirical evidence of bicycle theft patterns is sparse, in particular within Canada. Existing studies have primarily focused on the built environment, while largely overlooking the potential influence of topography and street centrality. Drawing on principles from environmental criminology, this study explores the spatial distribution of reported bicycle theft in Toronto, Canada, between 2014 and 2024 (n = 37,318) across three spatial scales. Measures of spatial access were used to capture both the proximity and availability of select built environment features, alongside street centrality and topographical elements. Findings indicate that both street elevation and hilliness were negatively associated with bicycle theft, suggesting that streets at higher elevation and in more hilly areas experience fewer theft. Several infrastructure-related features, including public transportation stops, bikeshare stations, and bicycle lanes, also emerged as consistent predictors of theft, while street centrality, slope, and parks were not significant. Bicycle parking facilities and universities were only predictive at the smallest spatial scale. These findings highlight the importance of incorporating topography into bicycle theft research, as these factors may shape offender decision making, target accessibility, and perceived effort.

This study investigates how the collective mobility (including movement and visiting) of residents and non-residents affects neighbourhood burglary levels. While past research has linked mobility to urban crime, this study explores how these relationships vary across population groups and social contexts at the neighbourhood level. Using mobile phone GPS data, we distinguished between residents and non-residents based on daily movement patterns. We then measured their mobility within defined spatial and temporal units. An explainable machine learning method (XGBoost and SHAP) was used to assess how mobility patterns influence burglary in London’s LSOAs from 2020 to 2021. Results show that increased collective mobility is generally associated with higher burglary levels. Specifically, non-resident footfall and residents’ stay-at-home time have a stronger influence than other variables like residents’ travelled distance. The impact also varies across neighbourhoods and shifts during periods of COVID-19 restrictions and relaxations. These findings confirm the dynamic link between mobility and crime, highlighting the value of understanding population-specific patterns to inform more targeted policing strategies.

Urban emergencies significantly disrupt the subjective well-being (SWB) of urban population, while limited research has explored how time-use patterns interact with personality traits to shape SWB in crisis contexts. Understanding these mechanisms is essential for effective urban management and community resilience. This study investigates the influence of time use and personality profiles on SWB during urban emergencies, using data from the Shanghai lockdown. We identify three distinct personality profiles (i.e., Positive, Introverted, and Sensitive) and examine their heterogeneous responses. Our findings reveal that key quality-of-life factors, including health perception, social connection, and community liveability, directly influence SWB. Furthermore, time-use patterns, such as outdoor activities, paid work, sleep, online socialising, entertainment, and offline leisure, significantly affect residents’ life quality and SWB. In addition, personality traits moderate these effects: Positive individuals are particularly sensitive to sleep duration, while Sensitive individuals experience greater well-being variations due to outdoor activities. By revisiting the interactions between time use, personality traits, and SWB, our findings offer evidence-based guidance for policymakers and urban planners. This knowledge advances the understanding of psychological adaptation during urban emergencies and provides a foundation for more targeted approaches to community welfare, thereby strengthening community resilience during future crises.

Urban agglomeration, a product of advanced urbanization and industrial transformation, plays a critical role in national spatial and economic systems. Urban agglomeration resilience remains underexplored in existing literature, particularly regarding how multi-scale interactions between macro-level network structures and micro-level public perceptions jointly shape regional adaptive capacities during crises. To address this gap, this study proposes a novel dual-perspective framework integrating population mobility network analysis (macro) and public sentiment analytics (micro) to evaluate the resilience of eight major Chinese urban agglomerations during the COVID-19 epidemic. The results indicate the agglomerations robust intercity connectivity and stable structural networks, such as polycentricity structures or breaking the inter-provincial effect, exhibit higher resilience. Based on the experimental results, we propose multi-scale development strategies. It is argued that the development of urban agglomerations should focus on breaking down urban barriers, enhancing network hierarchies and complexity, and mitigate long-term urban vulnerabilities of unexpected events.

Delineating the boundary or impact area of an economic, cultural, or lifestyle region has been a long-lasting problem in urban and regional geography. The fundamental difficulty lies in the exact definition of a region, and what criteria need to be considered. Existing methods either use criterion-based definitions or network-based measures to evaluate the affiliation of a city to a region. However, both types of methods only give static and definitive results but ignore the dynamism and graduality between regions. In this paper, we propose a Singular Value Decomposition (SVD)-based method to depict the impact areas of regions in China using individual connections among cities. Using the individual mobility data from an online map service, we decompose the mobility patterns of China into a series of eigen-mobility-patterns—each corresponds to the impact area of a city, or a mobility-based region. The overlay of multiple eigen-mobility patterns depicts the “blurred” boundary between the respective regions—or their competing hinterlands. We hope the method could be used to help understand the complexity of drawing regional boundaries and help policymakers to identify the non-confined but blurred economic and cultural landscape of various contexts in regional governance.

Redlining is a discriminatory practice of systematically denying loans or mortgages to residents in specific neighborhoods based on racial or ethnical composition. In current literature research, there is a lack of understanding of the public perceptions of impacts of historical redlining practices at large geographic scales. Although some social groups and organizations conducted surveys or interviews to obtain public perceptions of it on small groups of people in certain areas, our knowledge of the impacts of redlining is limited and may reflect bias. This study used geotagged tweets from 2011 to 2023 to investigate public perceptions of redlining practices in U.S. counties. Multiscale geographically weighted regression (MGWR) was performed to explore both spatial heterogeneity and varying scales of associations between percentage of redlining-related geotagged tweets with negative sentiment and potential explanatory shaping factors in U.S. counties. Counties with a higher average household size, a higher percentage of people aged 45+, a lower homeownership rate, and a higher mobile home percentage have a significant association nationwide with more negative-sentiment expression in redlining-related tweets. However, counties with a lower insurance coverage are less likely to express negative sentiment in redlining-related tweets in some eastern U.S. counties, indicating a local significant association. The findings help people better understand the relationship between public perceptions of redlining practices and potential shaping factors. This study’s methodology can also be applied to investigate public perspectives or perceptions on other controversial social topics.

Urban centers, as core zones for development, are often defined more by functional concepts than explicit boundaries. This ambiguity complicates policy formulation and results in a gap between planning objectives and actual development. Existing studies primarily utilize multi-source data to delineate the actual functional scope of urban centers. However, relying solely on current situation analysis lacks the forward-looking ‘spatial potential’ dimension, thus limiting the effective evaluation and optimization of planning, especially for TOD-based urban centers. Therefore, spatial potential is introduced as a critical intermediary to link and compare planning intentions with actual outcomes. Taking Wujiaochang subcenter in Shanghai as a case study, this study proposes a ‘Planned-Actual-Potential’ (P-A-P) multi-dimensional analysis framework. The differences between these three scopes are compared to derive mismatches between planned supply and actual demand. It is found that due to market forces, the Actual Scope is partially beyond the Planned Scope, while some potential parcels lack corresponding planning support, leading to resource and functional mismatches. Finally, practical suggestions are proposed for planning and policy optimization, including detecting and supporting the potential, yet unplanned, parcels.

As cities adopt pervasive sensing, integrated data platforms, and AI, recommender systems are becoming central to shaping equitable, efficient, and citizen-focused urban services. This survey synthesizes peer-reviewed work across mobility, healthcare, energy, tourism, retail, and e-governance, offering a taxonomy linking collaborative filtering, content-based methods, hybrid designs, deep learning, and context-aware approaches to urban decision-making needs. Our review spans major smart-city domains, with most empirical studies in mobility and tourism, while deep and graph-based techniques remain unevenly distributed and comparatively rare in governance and energy. We examine how heterogeneous data sources, including IoT streams, geospatial signals, environmental indicators, and demographic attributes, are fused to support personalization under constraints such as latency, reliability, and privacy. The review highlights advances that address sparsity and cold start through graph neural models, sequence modeling, and transfer learning, and it covers operational enablers such as edge inference and streaming architectures for real-time recommendation. We assess risk and governance dimensions, including privacy preservation, fairness, exposure balance across neighborhoods, explainability, and mechanisms for audit and oversight. The survey identifies opportunities in pollution management, citizen education, and participatory platforms that broaden civic engagement. It also outlines how hybrid physical-virtual interactions, digital twins, immersive interfaces, generative models, and emerging quantum algorithms may reshape personalization and oversight in city-scale settings. Finally, we call for field evaluations and standardized benchmarks that jointly measure accuracy, latency, robustness to distribution shift, and equity.

Urban recreation and leisure spaces (RLSs) are vital venues for citizens to relax, socialize, and experience urban life. Public perception of RLSs represents a crucial component of urban studies. Traditional Natural Language Processing (NLP)-based methods for analyzing RLS perceptions from social media data face limitations in semantic understanding, multidimensional sentiment differentiation, and spatial recognition. To overcome these limitations, we propose and validate a novel Large Language Model (LLM)-based analytical framework for multidimensional perception assessment of urban recreation and leisure spaces. Through comparative evaluation of three mainstream LLMs (DeepSeek-R1, Kimi, and QWEN), we selected the best-performing Qwen model (F1-score=0.899) to construct a multidimensional Aspect-Based Sentiment Analysis (ABSA) framework. Taking Hangzhou, China as a case study, we collected note data from the "REDnote" platform and employed the LLM to identify seven perception dimensions and determine sentiment polarities. Building upon the ABSA perception evaluation data generated by the LLM, we further conducted spatial distribution analysis, keyword co-occurrence network analysis, and place-activity bipartite network analysis to reveal perception patterns and their underlying causes. The findings indicate that: a) Hangzhou's recreation and leisure spaces excel in "soft power" dimensions (cultural atmosphere, spatial aesthetics) but require optimization in "hard power" aspects (accessibility, functional configuration); b) Hangzhou's leisure resources are unevenly distributed, with perception evaluations exhibiting a core-periphery structure; c) open outdoor spaces are more positively perceived than enclosed commercial complexes, with "city walking" emerging as the dominant positive activity. This research confirms the transformative value of LLM as core analytical engines rather than preprocessing tools, providing a new research paradigm and practical guidance for the planning and management of urban recreation and leisure spaces.

Urbanization is a global phenomenon with critical challenges for land use management and ecosystem conservation. This work examines urbanization dynamics and their effects on land cover categories, emphasizing the importance of understanding these processes for effective urban management and planning. The study focuses on the peri-urban areas of the second largest Algerian metropolis Oran, specifically examining the south and west peripheries along two major road axes, which have witnessed significant land use changes over the past three decades. With an AUC accuracy of 0.9, the application of integrated Land Change Modeler (LCM) and Logistic Regression analysis revealed a notable increase in urban areas in the periphery of Oran between 1998 and 2019, resulting in a 4340.97-hectare expansion of the urban area. Modeling projections indicate that this trend will continue with the urban area more than doubling from 2019 to 2030, with an expected 11,031-hectare for the urban category by 2030. These results highlight a growing urban sprawl, accompanied by a decline in agricultural areas, forest cover, and Ramsar-designated wetlands, which play a critical role in sustaining regional biodiversity. Furthermore, the analysis identifies distance to roads and proximity to urban settlements as key drivers influencing urban growth in the study area. These findings emphasize the need for a more effective urban planning policy and enforcement mechanisms to balance urban growth and with ecological preservation and agricultural sustainability. This research contributes to a better understanding of the complex land use and land cover patterns in North African contexts and offers insights to local and regional stakeholders developing reliable land management strategies in rapidly urbanizing regions.

Urban AI discourse has been dominated by Large Language Models (LLMs), yet these models misalign with the specific operational needs of cities, which demand low-latency, context-sensitive, and infrastructure-light solutions. This opinion paper addresses that gap by proposing Small Language Models (SLMs) as a viable alternative and introduces “SLM Urbanism,” a layered conceptual framework that reimagines urban AI deployment. Drawing on recent literature, the framework comprises five layers, computational, task-specialised, application, governance, and citizen-centric, each aligning technical affordances with urban imperatives. Using a normative, design-oriented method, the study contrasts SLMs’ low-cost, edge-native, and interpretable architectures with the compute-heavy, opaque nature of LLMs. The discussion situates SLMs as enablers of locally tuned, explainable, and democratically aligned intelligence that better serve urban equity and efficiency goals. Findings highlight that SLMs often outperform LLMs in resource-constrained settings, enhancing trust, transparency, and civic agency in AI-mediated governance. Importantly, the paper does not reject LLMs entirely but advocates a hybrid future of modular urban intelligence where SLMs lead a shift from centralised automation to distributed, planner-guided agency.

Street-view imagery provides valuable insights into the physical and social dimensions of urban environments. Seoul, South Korea, known for its rapid urban transformation, presents a distinctive blend of traditional urban centers and newly developed districts. To gain a comprehensive understanding of Seoul’s urban development, we constructed a street-view database spanning 14 years (2010–2023), comprising 423,353 images. To enhance data quality, noise components within the images were removed using advanced object detection and image inpainting techniques. We then segmented objects relevant to the commercial ecosystem and extracted features related to the intensity, shape, and texture for each object. The dataset includes street-view images, object masks, and their associated feature sets, all of which are publicly accessible to the research community. This resource offers a robust foundation for examining dynamic changes in Seoul’s urban environment. By leveraging this dataset, researchers can investigate the unique characteristics of Seoul’s evolving urban landscape and explore their implications for the commercial area.

Urbanisation is a global phenomenon, with major cities worldwide undergoing rapid transformation driven by economic and population growth. However, the urbanisation process in Brisbane City remains comparatively underexplored relative to other Australian metropolitan areas. This study presents a novel integrated framework that combines Google Earth Engine (GEE), Bayesian weight of evidence (WofE), and Artificial Neural Network–Cellular Automata (ANN–CA) to analyse and forecast spatiotemporal patterns of urban change. The research addresses three objectives: (i) monitoring urban settlements in Brisbane City from 1990 to 2021, (ii) identifying the drivers of urban expansion between 1990 and 2021, (iii) projecting future urban growth to 2030, and (iv) critically assessing the capability, strengths, and weaknesses of the ANN–CA model. Random forest classification using GEE achieved overall, producer, and user accuracies ranging from 0.97 to 1.00. The results revealed a period of stagnation and slight decline during 1990–2000, followed by accelerated expansion from 2000–2021, during which the urban area nearly doubled from 142.29 km² to 307.41 km². WofE analysis highlighted key determinants of urban growth, including distance to the central business district, proximity to waterways, roads, and points of interest, as well as topographic variables. ANN–CA simulations underscored the model’s sensitivity to underfitting, overfitting, and imbalanced change rates. Adaptive-period recalibration improved performance, with validation on 2021 dataset yielding 93.69% overall accuracy and Kappa coefficient of 0.67. Based on this corrective method, the model projects Brisbane’s urban extent to reach 380.45 km² by 2030. This integrated approach offers methodological advances and new insights into the mechanisms and trajectories of urban expansion.

Urban Heat Island Intensity (UHII) has become a pressing urban climate issue in rapidly developing nations such as Bangladesh. This study presents a nationwide thana-level assessment of UHII trends from 1990 to 2023 using remote sensing, geospatial analysis, and machine learning techniques. Land Surface Temperature (LST) was derived from Landsat imagery to quantify UHII, and a Space–Time Cube framework with Mann–Kendall trend analysis was applied to identify persistent, intensifying, emerging, and diminishing hotspot patterns. Major urban centers, including Dhaka, Narayanganj, and Khulna, exhibited increasing UHII, while Barisal and Mymensingh showed emerging cold spots. A Random Forest model was developed to forecast UHII up to 2040, revealing further intensification in densely populated and industrial zones. The results indicate that major metropolitan areas, particularly Dhaka, Narayanganj, and Khulna, exhibit persistent and intensifying heat hotspots, whereas divisions like Barisal and Mymensingh show emerging cold spots. The findings emphasize the need for climate-responsive urban planning and green infrastructure. This study establishes a baseline for long-term UHII monitoring and serves as a framework for future research aimed at developing predictive models and targeted mitigation strategies to enhance urban climate resilience.

The pedestrian volume, a critical indicator of urban vitality, has been broadly investigated in urban streets, particularly in China. However, how the street environment impacts the pedestrian volume has not received much attention in current Chinese cities. This study has adopted a machine learning model of LightGBM to test the association between 22 typical street environmental factors (spatial elements & spatial proximity) and the pedestrian volume (two models: the average value & the distance weighted value), and the SHAP approach to interpret and visualize the results achieved using the model. Guangzhou, a mega city in southern China, was chosen as the location studied. Key findings achieved are as follows: 1) Several environmental factors, particularly the density of commercial points of interest (POIs) and functional density, could significantly affect the average pedestrian volume. While most paired environmental factors may also produce important interaction effects, the strongest one was specifically observed between commercial and transportation POIs. 2) The distance-weighted pedestrian volume was significantly impacted by all 22 environmental factors, with commercial POIs having the highest impact. Furthermore, although most paired environmental factors had significant interaction effects, these effects were generally small. 3) Most paired environmental factors had significant interaction effects on both average and distance-weighted pedestrian volumes. However, the size of these effects was smaller relative to their main effects.

Accurately predicting PM_2.5 concentrations remains a major challenge due to the complex and nonlinear nature of its formation and transport processes. Traditional models often struggle to capture the spatiotemporal dynamics of PM_2.5, particularly under varying meteorological conditions. In recent years, Koopman operator theory has attracted increasing attention for its ability to transform nonlinear systems into linear representations, thereby enhancing model interpretability and stability. However, most existing Koopman models primarily focus on temporal dynamics and overlook the spatial correlations. To address this limitation, we propose a novel framework called Graph Attention Physics-Constrained Learning (GAPCL). This method combines Graph Attention Networks—designed to model spatial dependencies between PM₂.₅ monitoring stations—with the Physics-Constrained Learning framework grounded in Koopman theory. The model employs an attention mechanism to dynamically weight PM_2.5 monitoring stations, uncover spatial relationships, and integrates graph topology with Koopman eigenfunctions to represent the spatiotemporal evolution of complex nonlinear dynamical systems. The effectiveness of GAPCL was validated using hourly data from 2019 to 2021 in the Beijing-Tianjin-Hebei region. The results demonstrated that the model achieved superior prediction accuracy, particularly for short-term forecasts. Compared to the Spatial Physics Constrained Learning (SPCL), GAPCL improved the RMSE, MAE, IA, and r by an average of 12.07%, 11.47%, 11.16%, and 11.11%, respectively. Additionally, the mean RMSE of GAPCL was 3.26% lower than the next-best SPCL and 26.64% lower than the worst-performing Long Short-Term Memory Network. The GAPCL model significantly improves outlier prediction accuracy by dynamically weighting PM_2.5 stations to better capture spatial dependencies.

At present, China's total demand for railway construction at home and abroad is at a historically high level. Under the huge construction demand, it is particularly important to reduce the logistics and transportation costs in railway construction. This study aims to reduce the construction cost of logistics bases during railway construction. On the basis of drawing on industry site selection experience and principles, combined with the idea of the set coverage problem, a secondary logistics node site selection model for railway construction is constructed. Based on the heuristic algorithm and Voronoi diagram technology, the optimal solution algorithm of the site selection model is designed. Applying the research algorithm to actual railway construction cases, the optimal solution output showed that the number of logistics points and supply facilities was lower than that of traditional heuristic algorithms. The computation time of the research algorithm was 7.52 ± 1.33 s, which was not significantly different from the computation time of the comparison algorithm. The results indicate that the designed railway site selection model and model optimization algorithm have strong automatic site selection capabilities, which can significantly reduce the construction cost of logistics nodes and have certain application potential.

With the rapid accumulation of multi-source spatial data in cities, the identification of urban and rural functional zones and the modeling of dynamic structures have become important research directions in urban intelligent planning. However, existing methods are difficult to fully reflect the functional heterogeneity and dynamic vitality performance in complex regions. Therefore, this study proposes an urban–rural functional vitality recognition framework that integrates semantic modeling and graph neural networks. It integrates theme modeling and word vector construction to construct multi-semantic features and identifies functional regions through density clustering. At the same time, it constructs a graph structure based on spatial adjacency relationships and uses graph convolutional networks for functional category recognition. In performance testing, when the number of iterations reached 300, the F1-score of the proposed model was 0.91, the coupling correlation coefficient was 0.834, and the boundary F1-score was 0.82. In the actual application test within the Fifth Ring Road area of Beijing, the Olympic Park scored 0.813 on the leisure park, indicating a highly concentrated spatial response. The experiment shows that the proposed method achieves coupling modeling consistency in the area within the Fifth Ring Road of Beijing, and demonstrates good capabilities in urban function classification, spatial relationship modeling, and vitality response analysis. This study aims to provide intelligent support for urban–rural spatial governance and data-driven urban planning.

Emergency groundwater supply is crucial for maintaining regional stability and supporting the livelihoods of both urban and rural populations during disaster events. Given the variety of natural disasters in China and the existing deficiencies in rapid water source detection, this paper focuses on developing advanced groundwater surveying technologies and decision support systems to expedite post-disaster water restoration. We propose a Space-Aerial-Ground (SAG) integrated technology framework that synergizes multi-source remote sensing (RS), geographic information systems (GIS), and geophysical prospecting. By incorporating multiple data sources, including RS, geological, and hydrological datasets, a rapid assessment model targeting groundwater potential was created through multi-criteria decision analysis. Coupled with a targeted approach combining unmanned aerial vehicle (UAV) reconnaissance and geophysical profiling, this allows for precisely identifying groundwater storage spaces and strategically placing emergency wells in disaster-affected areas. To facilitate its operation, a software platform called the Intelligent Survey and Rapid Analysis System of Groundwater Sources (GISRAS), featuring analytical positioning and field adaptability, was engineered with modular capabilities. Extensive testing of this framework and technical suite across a range of typical disaster scenarios has produced promising results in terms of reliability and performance. This research provides a validated, rapid, and accurate solution for groundwater exploration under extreme conditions, significantly enhancing China’s emergency water supply capabilities.

This paper presents a traffic accident prediction model developed for IB-category rural roads in the Republic of Serbia, utilizing the largest dataset analyzed in the country to date. The model employs interpretable machine learning techniques to assess the impact of road geometry, traffic exposure, and quality on accident frequency. The model exhibits robust predictive accuracy with a R² of 79%, especially in pinpointing high-risk regions linked to increased traffic density and geometric limitations. SHAP-cluster analysis was used to interpret variable contributions and reveal hidden patterns in cluster-specific risk profiles, which can be used to define and prioritize prevention measures. Future study will expand this framework by extending it to various road types, including freeways, and by investigating additional elements, such as user behavior and weather conditions, that may improve forecast accuracy. The results provide a practical tool for road authorities and policymakers aiming to improve traffic safety on the rural road network.

Urban scaling theories posit that larger cities exhibit disproportionately higher levels of socioeconomic activity and human interactions. Yet, evidence from developing countries (especially those marked by stark socioeconomic disparities) remains limited. To address this gap, we analyse a month-long dataset of 3.1 billion voice-call records from Brazil’s 100 most populous cities, providing a national-scale test of urban scaling laws. We measure interactions using two complementary proxies: the number of phone-based contacts (voice-call degrees) and the number of trips inferred from consecutive calls in distinct locations. Our findings reveal clear superlinear relationships in both metrics, indicating that larger urban centres exhibit intensified remote communication and physical mobility. We further observe that gross domestic product (GDP) also scales superlinearly with population, consistent with broader claims that economic output grows faster than city size. Conversely, the number of antennas required per user scales sublinearly, suggesting economies of scale in telecommunications infrastructure. Although the dataset covers a single provider, its widespread coverage in major cities supports the robustness of the results. We nonetheless discuss potential biases, including city-specific marketing campaigns and predominantly prepaid users, as well as the open question of whether higher interaction drives wealth or vice versa. Overall, this study enriches our understanding of urban scaling especially in the global south, emphasising how communication and mobility jointly shape the socioeconomic landscapes of rapidly growing cities.