Evaluating Provincial Resilience to Climate Change in China Using a Hybrid <scp>ANP</scp> ‐ <scp>ANN</scp> ‐ <scp>PROMETHEE</scp> ‐ <scp>GAIA</scp> Framework

ABSTRACT The increasing frequency and severity of climate‐induced disruptions necessitate robust methodologies for assessing regional resilience. This study introduces a hybrid analytical framework integrating the Analytic Network Process (ANP), Artificial Neural Networks (ANN) and PROMETHEE‐GAIA to systematically evaluate climate resilience across Chinese provinces. Resilience is assessed through three dimensions: exposure, sensitivity and adaptive capacity, each comprising multiple sub‐criteria informed by expert inputs and literature review. ANP models the interdependencies among resilience factors, while ANN validates the assigned weights, ensuring methodological robustness. PROMETHEE‐GAIA ranks provincial resilience levels, providing insightful visualisations of resilience trade‐offs. The findings reveal substantial regional disparities: coastal provinces such as Jiangsu and Zhejiang exhibit higher resilience due to advanced infrastructure, economic robustness and effective governance, while inland regions like Qinghai and Gansu demonstrate heightened vulnerabilities due to limited adaptive capacity and economic dependencies on climate‐sensitive sectors. The study provides a replicable framework for resilience assessments globally, offering actionable insights for policymakers to enhance climate adaptation strategies and equitable resource allocation.