Exploring the regional characteristics of inter-provincial CO₂ emissions in China: An improved fuzzy clustering analysis based on particle swarm optimization

• Published in: Applied energy 2012-04, Vol.92, p.552-562
• Main Authors: Yu, Shiwei, Wei, Yi-Ming, Fan, Jingli, Zhang, Xian, Wang, Ke
• Format: Article
• Language: English
• Subjects: algorithms; Applied sciences; carbon dioxide; cluster analysis; emissions factor; Energy; Exact sciences and technology; greenhouse gas emissions; issues and policy
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2011.11.068

The better to explore the regional characteristics of inter-provincial CO₂ emissions and the rational distribution of the reduction of emission intensity reduction in China, this paper proposes an improved PSO-FCM clustering algorithm. This method can obtain the optimal cluster number and membership grade values by utilizing the global capacity of Particle Swarm Optimization (PSO) on Fuzzy C-means (FCM). The clustering results of CO₂ emissions indicate that the 30 provinces of China are divided into five clusters and each has its own significant characteristics. Compared with other clustering methods, the results of PSO-FCM are more explanatory. The most important indicators affecting regional emission characteristics are CO₂ emission intensity and per capita emissions, whereas CO₂ emission per unit of energy is not obvious in clustering. Furthermore, some policy recommendations on setting emission reduction targets according to the emission characteristics of different clusters are made.