Understanding China's CO₂ emission drivers: Insights from random forest analysis and remote sensing data

Area of Science:

• Environmental Science
• Climate Change Research
• Urban Studies

Background:

• China is the world's largest carbon dioxide emitter, necessitating emission reduction strategies.
• Understanding the drivers of carbon emissions is crucial for effective environmental policy.

Purpose of the Study:

• To analyze the key driving factors of carbon emissions in Chinese cities.
• To compare the efficacy of different statistical models for emission analysis.

Main Methods:

• Utilized carbon emission data, thermal power station locations, and nighttime light data for 281 Chinese cities (2003-2019).
• Employed and compared multivariate linear regression and random forest models.
• Ranked the influence of various factors on carbon emissions using the random forest method.

Main Results:

• Random forest regression demonstrated superior accuracy over multivariate linear regression.
• Population, economic development, and industrialization were identified as the primary drivers of carbon emissions.
• The interplay between population and economic development accounted for 68.5% of carbon emissions, with regional differences observed.

Conclusions:

• Population growth's impact on carbon emissions may be less critical than previously thought, allowing for flexible fertility policies.
• Controlled urbanization can contribute to the development of efficient low-carbon cities.
• Accelerating industrialization to reach a turning point is recommended to manage inevitable carbon emission increases.