Exploring influential factors of CO2 emissions in China's cities using machine learning techniques.

Abstract

The precise and exhaustive discernment of factors influencing CO2 emissions underpins the advancement toward sustainable, low-carbon development. Although numerous studies have probed the correlation between predetermined proxy variables and carbon emissions, methodological constraints have often led to an inability to effectively discern carbon emission determinants among numerous potential variables or unravel complex, non-linear relationships, and interaction effects. To redress these research gaps, this research utilized machine learning models to correlate urban CO2 emissions with socioeconomic indicators. The model outputs were then visualized and interpreted using explainable methods. The findings indicated that the model successfully identified a comprehensive array of dominant influences on urban CO2 emissions, principally associated with local fiscal policies, land use, energy consumption, industrial development, and urban transportation. The findings further revealed a complex non-linear association between these factors and urban CO2 emissions; however, the majority of these variables displayed a prevalent propensity to intensify carbon emissions in correspondence with an increase in sample value. Additionally, these factors exhibited a complex interactive influence on urban CO2 emissions, with distinct pairings producing a suppressive effect exclusively at specific combination of sample values. Consequently, this research posited that a robust correlation between urban socioeconomic development and CO2 emissions in China remains to be established. Given the varied impacts of these influencing factors across different cities, a differentiated approach to development should be adopted when charting low-carbon trajectories.