Environment and Planning B: Urban Analytics and City Science

Traditional urban planning frequently overlooks Children’s Independent Mobility (CIM) – the developmental stage where children begin to navigate their environment without adult supervision. Current educational methods often fail to bridge the ‘knowledge-behaviour gap’ which represents the disconnect between knowing traffic safety rules and applying them in real-world situations. To address this, this study presents a site-specific geogame using a Minecraft digital twin of two school neighbourhoods in Utrecht, Netherlands. Both the game environment and the engagement process were co-designed with traffic-focused local authorities to ensure relevance to real issues. Primary school children navigated the virtual environment and responded to embedded spatial questionnaires regarding traffic safety rules around their schools. The results demonstrate that this approach shifts children’s roles from passive learners to active ‘citizen-experts’. Analysis of in-game movement and chat logs revealed specific spatial insights actionable for planners, including the identification of perceived danger zones and preferred shortcuts. The study concludes that geogames may offer a scalable method to capture children’s situated spatial knowledge and effectively integrate their perspectives into the urban design process.

Labeled Mobile Laser Scanning (MLS) data are increasingly in demand for applications such as urban planning and autonomous driving. However, there is a severe shortage of manually labeled, high-fidelity MLS datasets, especially from developing countries like India. Deep learning models trained on less complex environments often fail to generalize to Indian scenarios, hindering the development of robust applications. To address this gap, we introduce Ke-MLS, the largest publicly available, expert-labeled MLS LiDAR dataset from Kerala, India. The dataset comprises 48 classes and supports the training of a variety of deep learning models for multiple applications. We evaluate the performance of state-of-the-art 3D deep learning algorithms on Ke-MLS, achieving mean Intersection-Over-Union (mIoU) scores in the range of 70–80%. The dataset is publicly available at https://lidaverse.com/.

This study evaluates the extent to which fully automated street network modelling can reproduce the analytical outcomes of a hybrid (automated–manual) approach for centrality and accessibility analysis across four morphologically distinct cities: Nicosia, London, Gothenburg, and Madrid. Results show that the geometry-preserving segmentation logic of the automated workflow systematically increases network granularity relative to the continuity-merging rules applied in the hybrid model, producing higher node densities and shorter street segments, particularly in cities with irregular, historically layered street patterns. Despite these geometric differences, angular integration exhibits strong to near-perfect rank correlation between hybrid and automated models across all cases, with agreement increasing at larger spatial radii. This indicates that global configurational structure is robust in automated simplification. Angular betweenness displays lower, though still moderate to high, correspondence, especially at smaller radii, reflecting its sensitivity to over-segmentation and local geometric variation. Spatial autocorrelation analysis reveals that ranking differences are strongly clustered in footpaths in open green spaces and detailed paths in residential areas. However, the differences are more locally confined and diminish at larger radii. Accessibility results further demonstrate scale-dependent divergence: short-range attraction reach and attraction distance estimates align closely between models, whereas discrepancies increase at larger thresholds due to the cumulative effects of finer-grained connectivity and additional pedestrian paths in automated networks. Overall, the findings indicate that automated street network models reliably capture large-scale integration and accessibility patterns across diverse urban contexts, while local, flow-sensitive measures remain more affected by network granularity and path representation. These results support the use of automated workflows for scalable and comparative urban analysis, with targeted manual refinement reserved for contexts requiring high local precision.

In the UK, and particularly London, property is a magnet for the global elite, drawn by both the glamour and the consistent rate of return of the housing market. Often, companies in tax or secrecy havens are used as the vehicle for these investments, making understanding this property class challenging. In 2015, the UK government began regularly releasing data on these offshore property investments. This paper analyses the first decade of this valuable but difficult-to-use dataset, first parsing and classifying the data into a structured format, then identifying the major residential trends. Over the last 10 years, the absolute value of residential OCOD property has increased from £64 to £80 billion; however, the relative value has decreased from 2.4 to 1.9 times the national average. London is the hub of offshore residential property, accounting for 45% of all properties by volume and 81% by value. However, these overall changes obscure more complex dynamics as luxury properties, owned by companies incorporated in the British Virgin Islands, decreased in value and volume across the time period. In contrast, there was an increase in housing developments being built by companies incorporated in Jersey and Guernsey. As Named Entity Recognition using deep learning is a critical part of the address parsing pipeline, we test different approaches and find that although training a model using weakly supervised learning (F1 = 0.97) marginally outperforms a model trained on a small, high-quality dataset (F1 = 0.95), this does not outweigh the cost of creating the labelling rules. As a result, we believe that investing more time in high-quality manual labelling is a better choice. The outputs of this paper are a pip-installable Python library and a pre-trained NER model that processes the datasets, increasing accessibility to this valuable resource for social and economic study.

This study provides empirical evidence that parcel-level socioeconomic indices can be reliably inferred from urban form using deep learning. Building on a representation that links cadastral parcels with digital surface models, we train EfficientNet variants to predict return on investment (ROI)—used here as a representative parcel-level economic indicator—directly from volumetric form. Across more than 24,000 parcels in a North American city, the models exhibit stable convergence and consistent generalization, capturing systematic variations across residential, commercial, and industrial morphologies. Although errors increase in dense commercial cores—where financial volatility and vertical complexity are highest—predictions remain bounded and preserve spatial gradients of ROI. The learned embeddings further reveal coherent manifolds structured by building massing, footprint geometry, and block configuration, indicating that the model extracts underlying spatial principles that correlate with economic outcomes. These findings demonstrate that urban form encodes measurable signals of economic performance and establish morphological learning as a viable pathway for integrating financial, environmental, and socio-cultural indices into form-based urban analysis and design.

Tactile paving is vital infrastructure for safe mobility among 2.2 billion visually impaired individuals worldwide, but in complex urban environments it faces both static damage and dynamic encroachment. This study develops an intelligent evaluation framework that integrates visual-language models (VLMs) with pedestrian-view street imagery to assess tactile paving usability around urban metro stations. Using GPT-4o and GoPro-collected imagery, we built a three-tier risk detection system covering the tactile paving body, a 250 mm proximity zone, and the surrounding environment. The framework includes 26 structural and 24 situational indicators with differentiated risk-scoring thresholds. Based on 110 metro stations within Beijing’s Third Ring Road, we analyzed the spatial distribution of tactile paving obstructions. The 250 mm proximity zone showed the highest obstruction rate (34.46%), exceeding the tactile body (33.03%) and environment (19.79%), mainly due to spatial pressure from wall attachments, poles, and adjacent facilities. Structural obstacles reflected persistent damage and encroachment, whereas situational obstacles showed greater temporality, peak intensity, and spatial variability, especially within the proximity zone. AI evaluations closely matched expert ratings (Pearson r = 0.943), and iterative scoring reduced false positives from 54% to 11%, confirming the reliability of VLMs in complex urban contexts. Fengtai District scored poorest in both indicator categories, with Majiapu Station as a key case. We recommend introducing a “proximity buffer zone” and improving fine-scale maintenance in high-density areas. The resulting intelligent platform is scalable and transferable for nationwide monitoring and governance of accessible infrastructure.

The household electricity consumption (HEC) directly contributes to energy demand and carbon emissions that are crucial in mitigating climate changes. This study applied linear regression and machine-learning models to examine the associations between HEC and green space attributes, individual and household characteristics, and user satisfaction. The city of Xi’an, China, was selected to collect data by residents’ survey and spatial analysis. The linear model results showed that key factors were mainly related to individual and household characteristics, as well as satisfaction with green spaces. In contrast, the random forest model revealed threshold effects, indicating that keeping the distance to the nearest green space within 1,200 m and providing at least four green spaces within a 1 km radius can effectively promote outdoor visits and reduce HEC. The analysis of dual-factor interactions revealed that simultaneously enhancing both accessibility and landscape quality of nearby green spaces represents an effective pathway for reducing HEC. These findings not only elucidate the mechanisms linking green space accessibility and HEC, but also provide quantitative guidance and actionable thresholds for optimizing the spatial configuration, accessibility, and service efficiency of urban green spaces. This study contributes practical guidance on embedding energy-saving and carbon-reduction strategies within green space system planning, advancing the transition toward sustainable and climate-responsive urban development.

Instant delivery has emerged as a critical component of urban mobility, with its spatiotemporal dynamics significantly shaping street congestion, emissions, and gig labor conditions. Here, I developed a 3D interactive animation to vividly visualize the spatiotemporal trajectories of on-demand deliveries based on 2508 real-world orders delivered by 113 unique riders in Beijing. This visualization transforms fragmented origin–destination (OD) order data into a dynamic exploration of street-level delivery mobility, revealing riders’ multi-stop routing patterns, street flow distributions, and collective urban delivery rhythms. This case demonstrates the potential of dynamic visualization in urban trajectory analytics.

Street greenery, as critical green infrastructure, provides extensive ecosystem services, and accurately evaluating its value benefits urban greening strategies and funding decisions. Previous studies relying on cross-sectional data and hedonic regression models are limited by confounding factors, thus failing to accurately measure the net effects of street greenery characteristics on housing prices. To address this limitation, hedonic regression, propensity score matching and difference-in-differences methodologies were employed based on housing price and built environment data from 2017 to 2022 to analyze how street greenery quantity and vegetation structure affect housing prices. Results indicated that street greenery impacts differ significantly between the central area and the expanded central area, revealing a negative price effect defined as the “Green Burden Effect” in expanded central area. Additionally, greenery quantity changes exerted stronger and more stable price impacts compared to vegetation structure. The DID analysis further clarified temporal changes in these relationships. Employing multiple econometric models revealed the complex spatial-temporal relationships between street greenery and housing prices, emphasizing the importance of spatially targeted greening strategies to optimize residential values and promote equitable urban development.

OpenStreetMap (OSM) is now an important data source for many mobility services. In particular, the OSM road network model is often used by cycling applications and studies. A very common operation with cycling data is map-matching, where the GPS traces of cycling trips are matched against the road network model. However, cyclists can take many unconventional paths that do not always match the official road network model. This fuzziness can severely compromise the ability of map-matching algorithms to produce valuable results. In this work, we introduce the concept of map-matching anomaly as a systematic mismatch between cycling traces and the road network data model to which the traces are expected to be matched. Contrary to sporadic map-matching errors, anomalies will recurrently occur for similar traces and will therefore accumulate at specific locations. This paper proposes a methodology to support the systematic and large-scale identification of map-matching anomalies in urban environments and discusses how knowledge about these anomalies can help cities uncover novel and actionable insights about cycling behaviour. The proposed methodology achieved 84% precision in identifying locations prone to map-matching anomalies. We identified several cases where the OSM road network was incorrect or incomplete. We also identified several locations where a deeper intervention is needed to improve the road network infrastructure.

Research on environmental justice has revealed that various hazards can be created by deleterious planning decisions. Multihazard exposure, or the co-location of two or more hazards in a neighborhood, has been little studied to date. We examine heat and air pollution across the census block groups (CBGs) of 55 US cities to evaluate the distribution and sources of inequities in multihazard exposure. The study combines measures of temperature from a volunteer science campaign; air pollution from remote sensing; street density and tree canopy as hazard-driving infrastructure; and demographics. On average, heat and air pollution were moderately correlated across the CBGs of a city ( r ¯ = . 34 ), but this measure of multihazard exposure varied substantially. Multihazard exposure was greatest in cities where neighborhoods with high street density often lacked tree canopy. In those same cities, low-income communities tended to live in neighborhoods with greater hazard-driving infrastructure. Cities with less coincidence between high street density and low canopy coverage, however, had less multihazard exposure and, in turn, fewer inequities. Consequently, multihazard exposure was inequitably concentrated in low-income communities in most, but not all, cities. The results implicate a two-step process for how multihazard exposure emerges in a city. First, discrete decisions begin to create exposures in certain neighborhoods. These then create the basis for circumstances and decisions that further concentrate hazards in communities inhabited by marginalized populations.

Three-dimensional (3D) building models offer visual representation, interaction, analysis, and exploration of urban environment analysis. However, most cities in the United Kingdom (UK) do not have open building 3D model datasets. This study used large-scale high-density airborne LiDAR point clouds to produce 3D building models for Glasgow City. We proposed an open-source and efficient data analysis workflow that integrated a weakly supervised deep learning point cloud classification algorithm and a data-driven 3D model reconstruction method. The Glasgow 3D building model datasets include building footprints with height attributes and 3D models in the level of detail 1 (LoD1) and LoD2. The cross-reference results show that our building footprint aligned well with UK Ordnance Survey data (intersection over union of 82.67% for overlay, R = 0.93 and RMSE = 1.84 m for building height). Building models well represent outer shell features with an average RMSE = 0.54 m for the distance between point clouds and reconstructed models. This accurate 3D building model data can be used in multiple environmental applications for Glasgow, and the open-source data generation workflow can be extended to other major cities for similar applications.

Internally displaced people (IDPs) who fled conflict zones in Donetsk and Luhansk beginning in 2013 relocated to other cities in Ukraine. Their Russian-language preference can be quantitatively and qualitatively observed and measured in the urban textual environment, or linguistic landscape (LL) of Kyiv, the bilingual Ukrainian capital. This study examines the LL at a city-wide scale, leveraging Google Street View imagery with deep learning text detection, recognition, and script identification, alongside geospatial tools for large-scale analysis. The approach enables systematic, reproducible mapping of machine-detectable public-facing signage along road networks, supporting analysis of spatial and temporal associations between population relocation and LL change. Analyses at the administrative and road network levels reveal differing language preferences between primary and residential roads. Results indicate clustering of the Russian keyword ‘аренда’ (rent) near IDP relocation sites during the relocation period and an observable increase in Ukrainian-language preference after the implementation of the 2019 language policy.

The growing emphasis on walkable environments underscores the need to understand how streetscapes influence pedestrian perception, yet the specific threshold intervals at which these effects become significant remain underexplored. This study proposes a workable framework that integrates immersive VR, wearable biosensors, and machine-learning algorithms to identify refined thresholds and further advance evidence-based urban design. Initial steps involved identifying key streetscape elements across different street types, for example, sidewalk width, interface permeability, utility area width, and cycle parking, as informed by literature and existing guidelines. This was followed by constructing 251 VR streetscape scenes, through which subjective evaluations were collected from 185 participants to establish streetscapes’ preliminary thresholds. Subsequently, wearable biosensors and a window-based change point detection algorithm were employed to determine refined threshold intervals, the results of which informed actionable guidelines for street design. The framework integrates human-centered analytical tools to systematically quantify refined streetscapes’ thresholds and translates them into evidence-based guidelines for urban design, offering a replicable pathway for optimizing streetscape quality. Overall, the study provides quantitative insights and actionable design guidance that advance the broader agenda of evidence-based and human-centered urban design.

Architecture, engineering, and construction have increasingly integrated automated tools and digital approaches for urban analysis and design. Many of these approaches are tailored towards either urban Design or urban Science, despite both being central to our understanding of cities. The separation between these two core aspects of urban development introduces multidisciplinary challenges when addressing the consequences of urban phenomena. We propose the paradigm of Semantic Urban Elements (SUEs) to combine Science-based and Design-based knowledge about potential solutions to complex urban issues, integrating advances in scientific and design thinking about such solutions using formal, open knowledge representation frameworks. We first present current problems by briefly discussing the relevant state of the art in urban Science and urban Design. Second, we derive the key characteristics that a combined urban Design+Science approach would require. We then posit a definition of SUEs and provide an illustrative example, followed by a contextualization of our proposition and evaluate existing work through the lens of our proposed paradigm. The novel SUEs method is an enabling infrastructure that supports iterative, evidence-informed design exploration and transparent evaluation. In this way, SUEs responds to the digital revolution in urban quantification by integrating Design and Science and provides the necessary framing lens to tackle different challenges in cities in a way that benefit cities, humans, and their future, considering their mutual relationships.

Urban housing conflicts are increasingly shaping the social and spatial dynamics of cities, yet they remain difficult to analyze systematically due to their multi-actor complexity and fragmented representation across textual and spatial data. Existing studies tend to focus on either narrative or spatial aspects, rarely capturing the structural, temporal, and geographic dimensions of these conflicts in an integrated way. This paper addresses this gap by proposing a reproducible methodological framework that combines Large Language Models (LLMs), graph databases, and Geographic Information Systems (GIS) to analyze housing conflicts in Montréal between 2001 and 2024. The study aims to demonstrate how urban housing conflicts can be systematically extracted, classified, and analyzed across time and space using AI-based methods, and how their structural patterns reflect underlying socio-political dynamics. The resulting framework offers new insights into the evolution of conflicts linked to gentrification, economic vulnerability, and shifting governance, while contributing a replicable, scalable methodology for studying complex urban phenomena at the intersection of AI, spatial analysis, and social science.

Understanding how nitrogen dioxide (NO₂) varies both within and across cities is essential for assessing urban health inequalities, yet the joint influence of city size and internal structure remains poorly quantified. While it is expected that agglomeration size increases NO₂ concentrations and that distance from major urban activities reduces them, the magnitude and form of their combined effect have not been established. Our objective is to move beyond city-specific local context effects and to characterize the general structural form of NO₂ distributions, understood as their systematic variation with distance from the center across cities of different sizes. Using both ground monitoring stations and satellite data for 378 European Functional Urban Areas, we estimate parallel models for each measurement type and show that the same structural relationships hold in both cases. We find that NO₂ concentrations increase with population size as a power law (with an exponent between 0.14 and 0.22) and decrease with distance from the city center (with an exponent between −0.12 and −0.18), with consistent results across measurement types and robust to local and regional controls. These effects combine into a scalable radial profile, where the total air pollution over a city is proportional to (N/r)^0.16, which generalizes the spatial distribution of NO₂ in European cities. This formulation clarifies how total and per-capita pollution depend on the extent to which pollution is integrated and provides a simple framework for evaluating the health implications of urban growth.

Income-based unequal access to schooling threatens inclusive urban growth and fair education in the rapidly urbanizing Global South, but measuring it remains difficult due to limited data. This study addresses the issue by using a new multi-source data method, analyzing the residence-school relationship of over one million students through mobile phone population mobility data in Chinese megacities. We reveal a complex pattern of inequality: students at top schools travel long distances, while lower-quality schools cluster low-income students in isolated groups. Top schools, although showing greater income diversity within their student bodies, are still predominantly attended by high-income students. Segregation decreases from primary to high-school levels, driven by the shift from proximity-based school districting to merit-based admission. However, urban expansion, despite the increase in school provisioning, reproduces these inequalities and segregation instead of solving them. This paper validates the Effectively Maintained Inequality theory in the Global South context and provides empirical evidence on unequal access to schooling in urban China.

Connected vehicle (CV) data are increasingly available and widely used in transportation engineering for traffic monitoring, safety analysis, and infrastructure planning. However, the representativeness of CV data in general urban mobility analysis remains underexplored, raising concerns about potential biases between observed mobility patterns in CV data and actual travel behaviors, particularly across different demographic and socioeconomic groups. This study compares Wejo connected vehicle (CV) data with SafeGraph mobile phone records covering boarder population to reveal the representativeness of connected vehicle data in the context of urban mobility analysis. Using entropy-based measures of destination income diversity and normalized inter-neighborhood interaction strength, we examine how each dataset reflects mobility structures across income groups in San Antonio, Texas. Results show that SafeGraph data capture more multimodal and socially integrative travel behaviors, particularly among low-income communities, while Wejo data primarily reflect routine, vehicle-based movements concentrated among higher-income users. Interaction patterns in the CV data are more spatially clustered, with stronger flows observed within affluent neighborhoods. These differences underscore the behavioral and demographic selectivity embedded in CV data and point to important limitations when using such data to analyze mobility-based segregation. The findings contribute to ongoing efforts to evaluate the representativeness of emerging mobility datasets and their implications for urban spatial analysis.

To balance growing single-family housing demand with the pursuit of compact development goals, the design of single-family subdivisions plays a crucial role. Despite emerging efforts to develop alternative zoning approaches and subdivision optimization methods, a key gap remains in the lack of a systematic understanding of the quantitative relationship between distinct zoning parameters and compact single-family subdivision outcomes, as well as the relative differences inherent in these relationships. In response, this study quantifies these relationships through a five-stage research design, in which building coverage ratio (BCR) and housing density are used to measure single-family subdivision compactness, and a Quasi-Monte Carlo Subdivision Simulator (QMCSS) is developed and calibrated with real-world data to simulate a wide range of single-family subdivision samples. The generated samples and associated compactness measurements are then used to fit both univariable and multivariable models. The results reveal nuanced insights into the relative effects of key zoning parameters across both linear and nonlinear models. For example, parcel width exerts the strongest influence on housing density, while side setbacks contribute most to variations in BCR. Collectively, the findings contribute new quantitative evidence to the literature and shed light on the development of finer-grained, data-informed zoning approaches for promoting compact single-family development in American contexts and comparable regulatory settings.