Understanding geodemographic distribution across neighbourhoods is essential for identifying socio-spatial differentiation in cities. Traditional geodemographic classification studies rely primarily on various census and socioeconomic data, offering limited insight into the street-level environments through which such differences are experienced and reproduced. In particular, the visual and perceptual dimensions of neighbourhoods remain largely absent from existing classification frameworks. This study advances geodemographic classification research by introducing street view imagery (SVI) as a novel source for capturing latent visual features linked to socio-spatial structure. We propose an automated machine learning framework that leverages 556 image-derived variables to predict socio-demographic groups. The framework is applied in ten UK cities, where a national model and local instances are developed to assess the extent to which visual– demographic relationships are place-dependent or generalizable. Results show that SVI has potential for capturing geodemographic patterns and enabling national-scale generalization. The local model achieves an accuracy ranging from 0.49 to 0.70, while the national model brings an accuracy of 0.62. Finally, cross-city transfer analysis reveals both shared and heterogeneous visual–demographic relationships across urban contexts. This study contributes a new street-level observational layer that complements traditional data sources and extends the methodological scope of geodemographics, while informing improvements to public spaces and supports policy objectives aimed at fostering inclusive neighbourhood environments.

Over the past three decades, nighttime light (NTL) has become one of the most widely used and powerful proxies for characterizing human activities. Despite the recent proliferation of available NTL data from both satellite- and ground-level sensors, intrinsic differences between these two observation approaches can result in distinct NTL brightness patterns (satellite-ground disagreement). Such disagreement, particularly its spatial heterogeneity, represents a critical yet largely overlooked issue in NTL studies, introducing uncertainty into the interpretation and application of NTL observations. Here, by incorporating SDGSAT-1 glimmer imagery and panoramic nighttime street view imagery with geospatial AI approaches, we present a spatially explicit, wall-to-wall investigation into satellite-ground disagreement across Singapore. Specifically, we characterized citywide disagreement and its variation across land-use types, analyzed contributing factors, and assessed its implications for NTL-based applications, reinforced by Monte Carlo-based uncertainty quantification and sensitivity analyses using independent observations from Singapore and Shenzhen, China. Our study revealed substantial and spatially heterogeneous satellite-ground disagreement across Singapore. Relative disagreement averaged 15% ± 13% citywide but reached 42% ± 12% in 13% of the city. Such pronounced heterogeneity was likewise evident across land-use types, with commercial areas standing out for consistently significant disagreement, where ground-level NTL brightness was 29% ± 26% higher than satellite-level NTL brightness. Building morphology, vegetation canopy cover, and sensor spectral response contributed to satellite-ground disagreement, suggestive of distinct mechanisms underlying the identified patterns. Applying satellite- and ground-level NTL data yielded relative differences of at least 115% and 83% in GDP estimation and NTL exposure inequality assessment, respectively. This study sheds new light on satellite-ground disagreement by moving beyond discrete comparisons toward a comprehensive analysis of its heterogeneity and implications, thereby establishing an empirical basis for integrating NTL observations and contributing to more reliable NTL-based applications and evidence-informed policies on sustainable urbanization.

Flooding is one of the most frequent and damaging natural hazards, increasingly intensified by rapid urbanization and extreme precipitation events. Accurate modelling of water accumulation and runoff in dense urban environments remains challenging due to complex geometries and the limitations of conventional surface-based representations. Most approaches require extensive LiDAR preprocessing before hydrological analysis. This study introduces a methodology for direct flood risk analysis on Aerial Laser Scanning (ALS) point clouds, avoiding intermediate surface reconstruction steps. The proposed approach enriches points with indicators of water accumulation and surface runoff potential. Water accumulation is estimated through elevation differences within a 100-m local neighbourhood to detect topographic depressions, while runoff potential is derived from three geometric descriptors (verticality, planarity, and scattering) that describe the capacity of urban structures to channel or obstruct water flow. The method was evaluated using open ALS datasets from three cities with contrasting urban morphologies: Vigo (Spain), Rotterdam (The Netherlands), and Hong Kong (China). Results demonstrate the capacity of the enriched point clouds to identify flood-prone urban features such as low-lying harbour areas, semi-tunnels, and urban canyons, as well as runoff pathways including sloped roofs, stairways, ramps, and road surfaces. The resulting point-level risk representation shows strong agreement with historical flood events and traditional multi-criteria assessments. By using LiDAR point clouds as an analytical medium, the framework enables intuitive 3D flood risk mapping while preserving their geometric richness.

Data integration is a significant technical challenge that hinders the full implementation of Urban Digital Twins (UDTs). Given their data-driven nature, UDTs rely on the integration of heterogeneous data sources, schemas, and structures. This process is inherently complex due to the diversity of techniques and systems involved. Furthermore, with the emergence of UDTs, the focus has shifted from acquiring new data through sensors to exploring how existing data can be integrated, restructured, and connected to meet the evolving requirements of digital twins. In this context, we raise fundamental questions about data integration within UDTs. Building on a previously proposed conceptual framework defining levels of data integration, this study gathers insights from practitioners actively engaged in UDT implementations. The aim is to understand how these conceptual integration levels are applied in practice, how they are selected across the UDT lifecycle, what tools support their implementation, and how they enable effective integration depending on the availability and nature of the data. By aligning theoretical frameworks with practical implementations, this research aims to enhance the effectiveness and adoption of scalable and flexible data integration strategies in the development, use, and maintenance of UDTs. The findings highlight the relevance of data integration levels for UDT practitioners, demonstrating that they were able to identify which levels are involved in their projects. Additionally, the results provide insights into how each level of integration is commonly applied across different stages of the lifecycle, as well as the tools and methods associated with each level.