Authors: Zeyu Zhao, Xiaoshan Zhou, Fanxin Meng, Dongping Fang, Helen X. H. Bao
Year: 2026
Status: Under Review
PDF: Download
Research line: AI and computational methods for spatial analysis
Abstract
Urban flood resilience emerges from complex interactions among natural, built, and socio-economic systems, yet most recovery policies implicitly assume that resilience mechanisms are spatially uniform. To address this gap, this study develops a spatially explainable machine learning framework that integrates geographically weighted random forests with a novel Local Spatial TreeSHAP algorithm, enabling nonlinear resilience mechanisms to be identified and interpreted at the community scale. The framework is applied to 779 communities affected by the July 2023 extreme rainstorm in Beijing. Results reveal that resilience mechanisms exhibit substantially stronger spatial heterogeneity than the underlying physical and socio-economic conditions themselves, with SHAP-value spatial autocorrelation decreasing by 66.2% on average relative to predictor variables. This finding suggests that resilience is governed less by the absolute availability of resources than by the locally contingent ways in which those resources interact. Three distinct resilience regimes emerge across the urbanization gradient. Highly urbanized communities benefit from synergistic interactions among commercial infrastructure and accommodation services; transitional medium urbanized communities are constrained by infrastructure-development mismatches that create facility gaps despite continued urban expansion; and low urbanized communities are dominated by ecological and topographic thresholds, where adverse interactions between transportation and river-network structures undermine recovery capacity. Field investigations and interviews with 12 stakeholders corroborate these patterns. These findings challenge the spatial-uniformity assumption that underpins many existing disaster recovery frameworks and demonstrate that effective resilience governance requires mechanism-specific rather than indicator-specific interventions. By linking geographically weighted machine learning with locally grounded attribution analysis, the proposed framework provides a new pathway for uncovering spatially varying resilience mechanisms and translating them into place-based recovery strategies under increasing climate extremes.