Urbanization often exacerbates psychological stress, partly due to a lack of psychological connection to urban spaces. While place attachment — the multidimensional bond between individuals and their surroundings — is known to benefit well-being, its specific influence on restorative perceptions at city or regional scale remains underexplored. This study introduces an innovative framework to investigate how place attachment levels affect restoration perception by analysing links between visual features, restorative qualities, and outcomes. Using street-level imagery, a survey (n = 547) was conducted in Hong Kong to gather restorative perceptions from residents with varied attachment levels. Machine learning models were then trained on this data and 25,194 street view images to map attachment variations at a regional scale. The research identifies key differences in restorative perceptions between populations with different place attachment levels, analysing survey-based variations, feature importance in machine learning, spatial disparities, and pathway relationships. The findings highlight the significant role of place attachment in contributing to restorative experiences, with high place attachment individuals showing stronger psychological recovery in urban environments. Moreover, spatial differences between high- and low-PA groups are greater in suburban areas. While high-attachment residents derive restoration from greenery, symbolic features, and high design qualities, low-attachment groups derive restoration from structural elements (e.g., roads and walls) that provide clear scope and spatial legibility. These insights offer perspectives on planning principles that foster a deeper connection to place. They propose tiered strategies tailored to the distinct needs of new developments versus historical districts, potentially supporting citizens’ long-term psychological well-being.

Multimodal large language models (MLLMs) are increasingly deployed for urban informatics applications, from objective built environment attribute extraction to subjective assessments. However, do MLLMs apply the same standards across regions while executing these urban-related tasks? Are MLLMs reliable and neutral judges? Do they adapt without criticizing, raising concerns about equitable deployment and further hidden bias? Here, we present a geographic red-teaming framework for diagnosing geographic biases in MLLMs applied to image object detection and urban visual perception. Using annotated imagery from more than 200 cities as a standardized benchmark, we demonstrate that MLLMs exhibit significant geographic disparities in both object detection accuracy and perceptual assessments across different regions. Quantitatively, perceptual scores for attributes such as Wealthy and Beautiful dropped by an average of 80% for African cities after geo-referencing, whereas regions such as Asia and North America showed score increases of 26%. A spatial-scale sensitivity test further showed that coordinates, city, country, and continent information produced broadly similar directional shifts, while combined geographic cues generated the strongest perceptual changes. Among the multiple state-of-the-art models, GPT-4o showed the lowest perceptual bias. Our geographic red-teaming stress-tests MLLM performance across underrepresented urban environments, revealing consistent patterns of bias that mirror training-data imbalances. We also provide quantitative metrics for measuring geographic equity in model outputs and establish recommendations for responsible MLLM deployment in urban research. These findings highlight critical limitations in current multimodal AI systems and demonstrate the urgent need for geographically inclusive model development to prevent the perpetuation of urban inequalities through automated analysis systems.

Human–environment interactions, a classic topic in geography, suggest that individuals and their environments might shape each other. Yet the specific mechanisms underlying these interactions regarding human personality traits have not been explored. This study examines the associations between human Big Five personality traits and built environment characteristics derived from street view imagery across four cities in Texas, United States, providing a descriptive foundation for understanding these complex human–environment dynamics. By integrating fine-resolution self-reported personality assessments with computer vision analysis of urban environments, we identified significant spatial clustering of personality traits at the ZIP code level. Our regression analyses reveal that built environment features and socioeconomic characteristics explain substantial variance in personality distributions, with Openness showing the strongest model fit (R2 = 0.47), followed by Agreeableness, Conscientiousness, Extraversion, and Neuroticism. Grouped built environment categories, socioeconomic factors, and demographic composition showed trait-specific patterns of association. These findings illustrate how personality traits could be associated with physical spaces at a smaller geographic scale than previously examined. Our results provide empirical evidence for understanding the link between psychological characteristics and environmental features, which can potentially enrich geography studies from a human-centered perspective.

Urban streets constitute essential everyday health infrastructure within the outdoor built environment, yet their potential to support physical activity remains unevenly realized. Current assessments prioritize formal sports facilities or rely on coarse, area-level metrics, leaving street-level differences in exercise supportiveness less visible. To address this gap, this study develops a theory-informed analytical framework for examining modelled exercise-supportiveness deficits across street networks. We employ Henri Lefebvres spatial triad as an interpretive lens, conceptualizing urban space as a contradictory and co-productive unity of three interconnected dimensions: Conceived Space (representations of space), Perceived Space (spatial practice), and Lived Space (spaces of representation). Drawing on the research agenda of Critical Quantitative Geography, these dimensions provide a vocabulary for organizing evidence on planned form, visible street conditions, and everyday activity traces. SHAP is then used to examine how the resulting indicator groups are associated with exercise intensity. Using Shenzhen as a case study, the analysis shows that conceived-space indicators account for the largest share of grouped SHAP attribution, while perceived and lived indicators reveal important local low-supportiveness patterns across development contexts. Grouped SHAP attributions are then used to construct a seven-mode diagnostic typology that identifies which C/P/L readings are associated with lower modelled street-level exercise supportiveness. Furthermore, a bivariate spatial association analysis identifies clusters where high population density coincides with low recorded street-level exercise intensity, highlighting locations for closer planning assessment. The framework combines machine-learning attribution with spatial-theoretical interpretation to examine health-supportive everyday movement environments at the street-segment scale.

Amidst ongoing urbanisation, understanding how various urban elements contribute to stress reduction and well-being is increasingly crucial. However, existing research has prioritized natural elements, reinforcing a nature-urban dichotomy that overlooks the restorative potential of the built environment itself. This systematic review examines the restorative value of urban environments through quantitative studies from 2010 to 2024, exploring the effects on cognitive, affective, and physiological outcomes. Following the Synthesis Without Meta-analysis (SWiM) reporting guideline, it narratively synthesises findings from 50 quantitative human studies, identified through PRISMA-referenced screening of peer-reviewed articles that report associations between urban environmental characteristics and restorative outcomes. Results indicate urban spaces with integrated greenery are more often linked to higher perceived restorativeness and short-term psychological benefits than predominantly grey comparators. Several built environment characteristics, including architectural façade design, design quality, service facilities, and street-scale vegetation, were positively associated with restoration. Psycho-environmental characteristics (e.g., serenity, prospect, refuge) and person–place relationships further shape restorative experiences. Future research should focus more on various urban settings—high-density neighbourhoods, historical districts, and waterfronts—and compare similarities and differences in their restorative mechanisms. The review identifies emerging neuro-urbanism and big-data approaches as transformative tools; despite current methodological limitations, they radically expand the potential to clarify mechanisms and enhance generalisability. Based on the evidence extracted from the 50 studies, an evidence-informed, hypothesis-generating conceptual framework is proposed to map the observed associations between urban environment attributes, restorative value, and health and well-being. The framework organises current associational evidence and identifies testable pathways for future research rather than depicting confirmed causal chains.