Spatiotemporal Disparities and Key Drivers of Urban Sustainability Capacity in China

China’s rapid urbanization has driven a pronounced east–west sustainability schism, where affluent coastal corridors face cumulative pollution pressures, while interior regions grapple with ecological fragility and comparatively weaker governance capacity. To diagnose this divergence, we establish the Environmental Stressor Regulatory Capacity (ESRC) framework, integrating indicators across industrial emissions, resource intensity, economic innovation, and institutional resilience. Leveraging Chinese spatiotemporal data from 283 prefecture-level cities from 2003 to 2021, our multi-method analysis reveals three core findings: Dagum Gini decomposition indicates intensifying interregional inequality. Kernel density estimation identifies four distinct transition archetypes: eastern high-base consolidation, central relay diffusion, western polarization–correction, and northeastern asymmetric revitalization. Crucially, random forest regression highlights the high predictive salience of Regulatory Capacity for ESRC variation. These findings are consistent with institutional asymmetry as the key explanatory factor for why some Western regions remain locked in spatial traps. These results may inform targeted ecological compensation for critical zones to support SDG advancement with regional equity.