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

Area of Science:

• Environmental Science
• Urban Planning
• Data Science

Background:

• Understanding carbon dioxide (CO2) emissions is crucial for sustainable development.
• Previous studies faced limitations in discerning emission determinants and complex relationships.

Purpose of the Study:

• To identify and analyze factors influencing urban CO2 emissions using machine learning.
• To explore non-linear relationships and interaction effects on carbon emissions.

Main Methods:

• Utilized machine learning models to correlate urban CO2 emissions with socioeconomic indicators.
• Employed explainable methods for visualizing and interpreting model outputs.

Main Results:

• Identified dominant influences: fiscal policies, land use, energy consumption, industrial development, and urban transportation.
• Revealed complex, non-linear associations where most factors increase CO2 with rising values.
• Observed intricate interactive effects, with some pairings suppressing emissions at specific values.

Conclusions:

• A robust link between urban socioeconomic development and CO2 emissions in China requires further establishment.
• Differentiated, city-specific approaches are essential for developing effective low-carbon trajectories.