Quantifying Urban Ecosystem Services for Community-Level Planning: A Machine Learning Framework for Service Quality Optimization in Wuhan

Urban ecosystem services (ES) are increasingly recognized as critical determinants of residents’ quality of life and well-being. This study proposes a novel demand-supply matching framework that integrates ES concepts into community-level planning and service evaluation. Using 371 resident surveys across 10 communities in Wuhan, China, we identify key environmental elements contributing to perceived service quality. We combine a random forest algorithm to rank environmental feature importance with a Multinomial Logit (MNL) model to quantify their impacts. Results reveal that community autonomy, neighborhood relationships, environmental civilization, security monitoring, and digital infrastructure (e.g., optical fiber) are central to enhancing service quality. While provisioning and regulating services—like safety and infrastructure—are relatively well-established, cultural services such as social cohesion and civic participation remain under-supported. Our findings highlight the heterogeneity of residents’ environmental expectations and offer practical pathways to integrate ES thinking into community planning and budget allocation. The proposed data-driven approach helps bridge ecological theory with operational urban management.