From Street Form to Spatial Justice: Explaining Urban Exercise Inequality via a Triadic SHAP-Informed Framework

2025-07-04

AI Summary

This study addresses spatial deprivation arising from inequitable distribution of physical activity opportunities across urban streets. Methodologically, it develops a street-scale physical activity deprivation quantification framework grounded in Lefebvre’s triadic theory of space (conceived–perceived–lived), integrating street-view imagery, social behavioral data, and street network topology. Leveraging graph neural networks, computer vision, and SHAP-based interpretable machine learning, it operationalizes spatial theory at the micro-scale for the first time, proposing a three-dimensional deprivation typology to classify inequality patterns. Results reveal that historic districts suffer primarily from conceived-space deficits—i.e., inadequate planning and infrastructure—whereas new developments exhibit pronounced perceived-space deprivation, reflecting poor experiential quality. Multiple deprivation clusters are identified; targeted interventions in these areas are projected to improve citywide street-level physical activity support by 14%. The study establishes a novel, empirically grounded paradigm for fine-grained diagnosis and precision governance of urban spatial justice.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Low Level & Physics-based Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Urban streets are essential public spaces that facilitate everyday physical activity and promote health equity. Drawing on Henri Lefebvre's spatial triad, this study proposes a conceptual and methodological framework to quantify street-level exercise deprivation through the dimensions of conceived (planning and structure), perceived (visual and sensory), and lived (practice and experiential) urban spaces. We integrate multi-source spatial data-including street networks, street-view imagery, and social media-using explainable machine learning (SHAP analysis) to classify streets by their dominant deprivation modes, forming a novel typology of spatial inequity. Results highlight significant differences across urban contexts: older city cores predominantly experience infrastructural constraints (conceived space), whereas new development areas suffer from experiential disengagement (lived space). Furthermore, by identifying spatial mismatches between population distribution and exercise intensity, our study reveals localized clusters of latent deprivation. Simulation experiments demonstrate that targeted improvements across spatial dimensions can yield up to 14% increases in exercise supportiveness. This research not only operationalizes Lefebvre's spatial theory at the street scale but also provides actionable insights and intervention guidelines, contributing to the broader goals of spatial justice and urban health equity.

Problem

• Quantify street-level exercise deprivation via urban space dimensions
• Classify streets by deprivation modes using explainable machine learning
• Identify spatial mismatches between population and exercise intensity

Innovation

• Triadic SHAP-informed framework for spatial justice
• Multi-source data integration via explainable machine learning
• Street typology based on deprivation modes classification