| Summary/Abstract |
The policy design of carbon dioxide (CO2) emission mitigation is a hotly debated topic in the context of “Carbon Peak and Carbon Neutrality” in China. This paper contributes to this debate by employing an unsupervised machine learning algorithm to uncover the CO2 emission typology based on the provincial emission data in China from 2000 to 2018 for a precise design of CO2 emission mitigation policy for heterogenous regional patterns. The results indicate that we can cluster the provinces into four CO2 emission patterns: the under-developed pattern, the coal-dominated pattern, the oil-dominated pattern, and the gas-dominated pattern. Notably, both the under-developed pattern and the coal-dominated pattern have a large amount of CO2 emission from fossil fuels, while the gas-dominated pattern could be regarded as the policy inclination as it relies more on low-carbon fuels. Moreover, we also reveal the transition routes of emission patterns from a dynamic perspective, which could help policymakers better understand the future trend of emission patterns in different regions. On the one hand, the CO2 emission mitigation policies could have specified priorities in different patterns, ensuring the feasibility during the process of policy implementation. On the other hand, establishing a national unified carbon trade market could facilitate efficient energy transition in China, and prevent carbon leakage cross different regions as well.
|