Identifying influencing factors and characterizing key issues in urban sustainable development capacity through machine learning

Abstract

In response to the United Nations Sustainable Development Goals and China’s “Dual Carbon” Goals (DCGs means the goals of “Carbon Peak and carbon neutrality”), this paper from the perspective of the construction of China’s Innovation Demonstration Zones for Sustainable Development Agenda (IDZSDAs), combines carbon emission-related metrics to construct a comprehensive assessment system for Urban Sustainable Development Capacity (USDC). After obtaining USDC assessment results through the assessment system, an approach combining Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest (RF) based on machine learning is proposed for identifying influencing factors and characterizing key issues. Combining Coupling Coordination Degree (CCD) analysis, the study further summarizes the systemic patterns and future directions of urban sustainable development. A case study on the IDZSDAs from 2015 to 2022 reveals that: (1) the combined identification method based on machine learning and CCD models effectively quantifies influencing factors and key issues in the urban sustainable development process; (2) the correspondence between influencing factors and key subsystems identified by the LASSO-RF combination model is generally consistent with the development situations in various cities; and (3) the machine learning-based combined recognition method is scalable and dynamic. It enables decision-makers to accurately identify influencing factors and characterize key issues based on actual urban development needs.