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.

Bike-sharing offers an eco-friendly and efficient transportation alternative, addressing traffic congestion, environmental concerns, and promoting healthier lifestyles. Understanding the factors that influence bike-sharing trips made by members is essential for the long-term operational and financial sustainability of bike-sharing systems. However, existing studies have primarily relied on survey data and traditional statistical models, which are often constrained by limited sample sizes and an inability to fully capture non-linear relationships or complex interactions between various factors and bike-sharing membership trips. To address these shortcomings, this study leverages million-level trip records from Chicago’s Divvy bike-sharing system and applies explainable machine learning model to identify key determinants influencing bike-sharing trips made by members. Unlike traditional survey-based studies, the proposed framework exploits large-scale operational data to capture complex behavioral patterns and interactions that are not readily observable using standard models. The results indicate a strong positive association between membership-based bike-sharing trips and weekday morning and afternoon commuting periods. Additional factors, such as longer travel distances, proximity to downtown, higher proportions of younger populations, and greater shares of non-White residents, are also positively associated with membership trip activity. These findings both corroborate and extend existing literature, while providing new, data-driven insights enabled by advanced analytical methods. Based on the identified determinants, the study proposes targeted policy and operational strategies to encourage bike-sharing membership adoption. By explicitly overcoming prior methodological limitations, this research offers a robust and scalable analytical framework to support bike-sharing operators in service planning, membership expansion, and the sustainable growth of urban mobility systems.

Urban parks provide substantial environmental, social, and health benefits, yet their recreational economic value often remains unquantified due to limitations in traditional data collection methods. Although previous studies have estimated park recreational value, they rarely capture how this value varies across neighborhoods and seasons because fine-grained, time-sensitive data are typically unavailable. This study addresses this gap by applying large-scale smartphone mobility data and the Travel Cost Method (TCM) analysis to estimate the recreational use value of Dick Nichols District Park, which is one of the most visited District parks in Austin, Texas. Using consumer surplus as a monetary measure of recreational benefits, the analysis combines visitation rates, travel distances, and opportunity costs with neighborhood-level sociodemographic indicators to reveal spatial and temporal patterns in park use. Our results show that the Park’s 2019 (Before COVID-19) annual recreational use value ranges from $306,983.80 to $307,067.72. Spatially, block groups in Austin’s northeastern quadrant exhibit higher recreational value, likely reflecting stronger connectivity and moderate travel distances. Our temporal analysis shows that June has the highest monthly recreational value. This study illustrates how large-scale mobility data can be integrated into recreational value assessment, offering greater visibility, scalability, and cost-effectiveness than traditional approaches. By leveraging these richer data streams, planners and policymakers can conduct more equitable, evidence-based park planning and resource allocation.

This paper introduces a simulation-based optimization framework to simulate weekly travel activities from single-day data, addressing the diminishing relevance of a "Typical Day." The framework builds on the integrated land use and energy modeling system (iTLE), combining long- and short-term decision components, a Markov Chain Monte Carlo (MCMC)-based activity generator, and an activity scheduler. The optimization model accounts for individual travel preferences through constraints, iteratively calibrating activity transition probabilities to match desired weekly travel patterns. Key activities simulated include in-home work (IHW), in-person work, shopping, eating out, and recreation. Calibration results show deviations of 19.0%, 16.4%, and 15.2% for IHW, in-person work, and shopping, respectively, with validation deviations of 4.3% for eating out and 2.3% for recreation. The model highlights distinct work patterns and commute behaviors, offering flexibility for post-pandemic transportation planning policies.

With the advancement of globalization and neoliberalism, gentrification studies have expanded beyond the original focus on living space changes of low-income groups in urban communities in Western Europe and North America, to the broader changes in the social space in urban and rural areas globally, constituting a critical field of the “geography of gentrification”. The geography of gentrification connects with cutting-edge theories of glocalization, unbalanced development and capital switching, and has become a crucial heuristic tool for interpreting the (re)construction of urban and rural social spaces in the post-industrial era. This paper reviews the evolving trends in methods, data and evaluating indices amidst the shift from gentrification to the geography of gentrification, concerning three dimensions, i.e., consumption, production, and the integration of the consumption and production. Overall, the analytical paradigms have undergone a transformation from static to dynamic, and from qualitative to quantitative, and further, to mixed methods. The data sources have expanded beyond traditional statistical and survey data to multi-source big data. The indicator sets have developed from simple socio-economic indicators to complex multi-dimensional comprehensive evaluation systems. Furthermore, Artificial Intelligence (AI) and Internet of Things (IoT) technologies have enabled real-time monitoring and precise prediction of the process of gentrification, ushering new theoretical and methodological frontiers. This paper further highlights that studies of the geography of gentrification necessitate a continuous focus on scalar politics and comparative and critical studies, in particularly in China, in response to the official and social claims for common prosperity, equity, and spatial justice.

This paper introduces the Parcel Complementarity Model (PCM), a parcel-level analytical tool for evaluating and optimising land use mix through observed patterns of use and movement. Rather than relying on compositional measures such as land use mix diversity or proportional balance, PCM conceptualises land use mix as a system of functional complementary interaction shaped by asymmetric trip flows, visit frequency, and spatial adjacency. Using cadastral land use data and mobility survey data from the Madrid metropolitan area, the model quantifies both inter-parcel and intra-parcel complementarity through a Parcel Complementarity Index (PCI). PCM is applied to vacant parcels in Tres Cantos (Spain), which are treated as gaps within existing neighbourhood-scale functional complementarity sets rather than as isolated development opportunities. A multi-objective optimisation process is used to explore alternative land use allocation and configuration scenario under existing regulatory constraints. The results show that improvements in land use mix complementarity depend less on the presence of additional uses and more on how land uses are positioned and configured in relation to surrounding parcels and existing functional interaction patterns. PCM provides a transparent and replicable method for evaluating parcel-level complementarity and supporting early-stage planning decisions grounded in empirical use and movement relationships.

The complexity of urban environments influences pedestrians’ walkability, which is especially significant for people living in mega cities. While many studies identify influential factors, how these factors shape pedestrian wayfinding through complex and spatially varied mechanisms remains underexplored. This study addresses this gap by using a novel pedestrian navigation dataset as a proxy to quantify the perceived complexity of walking environments. By integrating multi-scale urban features—four at the macro-level and 14 at the micro-level derived from Street View Imagery—we systematically uncover the key correlates of navigation demand and their underlying effects. The results reveal that a combination of factors such as the number of Points of Interest, transportation accessibility, proportion of people in view, and intersection count are positively associated with pedestrians’ navigation behavior. More importantly, we demonstrate that their relationship is profoundly non-linear and exhibits strong spatial heterogeneity. These results are further validated through population normalization, sensitivity tests, and temporal comparisons between weekdays and weekends. Such analyses confirm the robust and independent association between environmental complexity and navigation behavior. By operationalizing these complex interrelationships, our work advances the theoretical framework for urban environmental complexity. The findings provide crucial evidence for moving beyond a "one-size-fits-all" approach, offering targeted, context-aware insights to foster truly human-centered urban planning and design.

Urban vitality in the Global South remains underexplored, despite rapid growth in urban big data that enables observation at increasingly fine spatial and temporal scales. Deep learning (DL) methods offer powerful means to analyse such data and capture complex spatiotemporal patterns of urban life; however, existing applications are heavily concentrated in China and the Global North, often overlooking the data constraints and contextual challenges faced by Southern cities. To address this imbalance, this study introduces a decision-support toolkit designed to guide the integration of DL into urban vitality research in Global South contexts. The toolkit combines three structured decision trees (covering the selection of urban vitality variables (across built environment and activity dimensions), big-data sources, and DL task types) with a Weighted Sum Model that ranks DL algorithms based on their frequency and relevance in the literature. A Global South applicability labelling system highlights issues related to data accessibility, contextual suitability, and potential bias. The toolkit is validated through multiple grounded case studies drawn from the literature. Rather than prescribing optimal methods, the toolkit lowers entry barriers by supporting informed, context-sensitive methodological decisions, offering a practical pathway for expanding DL-based urban vitality research in underrepresented contexts.

This paper revisits McDermott’s seminal 1976 critique, Artificial Intelligence Meets Natural Stupidity, in light of the rapid rise of generative AI. McDermott’s warnings about conceptual imprecision, rhetorical inflation, and anthropomorphic metaphors remain strikingly relevant today, particularly in domains where linguistic fluency is mistaken for genuine understanding. Using computational and urban science as a case study, the paper highlights the limitations of large language models (LLMs) in spatial reasoning, including their hallucination of map features, distortion of topological relationships, and failure to grasp metric consistency. These shortcomings exemplify the epistemological risks McDermott identified nearly five decades ago. The paper argues for a renewed commitment to epistemic discipline and humility in the development and communication of generative AI, especially in high-stakes domains like geospatial applications. It proposes concrete guidelines for integrating spatial theory, documenting failures, and avoiding misleading terminology, advocating for hybrid approaches that combine LLMs with GIS frameworks and human oversight. By operationalizing McDermott’s insights, the paper calls for transparent, grounded, and responsible AI systems that can genuinely support, rather than distort, urban decision-making.

Urban environments are increasingly complex, dynamic, and data-intensive, requiring advanced spatial intelligence to support proactive, evidence-based governance. Current smart city and urban informatics platforms are limited by static datasets, siloed architectures, and underutilised AI capabilities. This study proposes and demonstrates a novel AIoT-enabled platform architecture for built environment mapping and spatial decision support. Anchored in platform urbanism, the architecture integrates high-resolution imagery, pretrained deep learning models from the ArcGIS Living Atlas, iterative workflows in ArcGIS Pro, and interactive dissemination via ArcGIS Experience Builder. The platform is demonstrated through building footprint detection in three Brisbane suburbs using the Building Footprint Extraction Australia model. Suburb-level processing enhances computational efficiency, while analytical extensions support footprint change detection, flood exposure assessment, and land-use zoning overlays. Results indicate that the platform transforms manual, fragmented processes into automated, reproducible, and dynamic workflows directly applicable to urban planning. Although demonstrated for building footprints, the architecture is scalable to other urban features, including roads, parcels, and solar panels. Limitations include dependence on high-resolution imagery and pretrained models, highlighting opportunities for future work in multi-model integration, real-time data streams, and developing AI models tailored to diverse urban contexts. By bridging cutting-edge AI innovation with operational governance needs, the proposed platform offers a replicable pathway for embedding AI-enabled spatial intelligence into smart city management.

Digital 3D city models support urban planning, simulation, and immersive applications, but common production methods such as manual CAD modelling, photogrammetry/LiDAR, and GIS-based extrusion are often slow, costly, difficult to scale, and hard to update. Procedural modelling offers a scalable alternative, yet practitioners still need clear guidance on when to use it and how to evaluate its outputs. This paper presents and evaluates a CityEngine workflow that combines open geospatial inputs with rule-based generation of road networks, blocks and parcels, and buildings. Using a commodity laptop (Intel Core i5‑3210 M, 6 GB RAM) and CityEngine, we generated three canonical morphologies (organic, raster/grid, and radial) over an area of approximately 2 km² under both default and dense scenarios. We report computational performance metrics, including generation time, peak RAM, CPU seconds, exported file size, and polygon count, and we complement these with output checks aimed at plausibility and visual realism for each morphology. Compared with a traditional modelling workflow, procedural generation reduces production time by one to two orders of magnitude while keeping resource use within desktop limits. Based on the case study results, we derive a decision matrix (Table 3) that compares procedural modelling with photogrammetry/LiDAR, GIS extrusion, and manual/CAD approaches across criteria such as time, scalability, update cadence, and required visual detail. This synthesis positions procedural modelling as a practical middle ground and motivates hybrid workflows that combine procedural background fabric with data-driven and manual elements when projects must balance fidelity, cost, and the frequency of updates.