Identification of the key factors affecting Chinese carbon intensity and their historical trends using random forest algorithm

doi:10.1007/s11442-020-1753-4

Abstract

Abstract:

The Chinese government ratified the Paris Climate Agreement in 2016. Accordingly, China aims to reduce carbon dioxide emissions per unit of gross domestic product (carbon intensity) to 60%-65% of 2005 levels by 2030. However, since numerous factors influence carbon intensity in China, it is critical to assess their relative importance to determine the most important factors. As traditional methods are inadequate for identifying key factors from a range of factors acting in concert, machine learning was applied in this study. Specifically, random forest algorithm, which is based on decision tree theory, was employed because it is insensitive to multicollinearity, is robust to missing and unbalanced data, and provides reasonable predictive results. We identified the key factors affecting carbon intensity in China using random forest algorithm and analyzed the evolution in the key factors from 1980 to 2017. The dominant factors affecting carbon intensity in China from 1980 to 1991 included the scale and proportion of energy-intensive industry, the proportion of fossil fuel-based energy, and technological progress. The Chinese economy developed rapidly between 1992 and 2007; during this time, the effects of the proportion of service industry, price of fossil fuel, and traditional residential consumption on carbon intensity increased. Subsequently, the Chinese economy entered a period of structural adjustment after the 2008 global financial crisis; during this period, reductions in emissions and the availability of new energy types began to have effects on carbon intensity, and the importance of residential consumption increased. The results suggest that optimizing the energy and industrial structures, promoting technological advancement, increasing green consumption, and reducing emissions are keys to decreasing carbon intensity within China in the future. These approaches will help achieve the goal of reducing carbon intensity to 60%-65% of the 2005 level by 2030.

Key words: machine learning, random forest, carbon intensity, key factors, China

TANG Zhipeng, MEI Ziao, LIU Weidong, XIA Yan. Identification of the key factors affecting Chinese carbon intensity and their historical trends using random forest algorithm[J].Journal of Geographical Sciences, 2020, 30(5): 743-756.

Figures/Tables 5

Table 1

Table 2

Figure 1

Table 3

Figure 2

References 30

[1]	Breiman L , 1996. Bagging predictors. Machine Learning, 24(2):123-140.
[2]	Breiman L , 2001. Random forests. Machine Learning, 45(1):5-32. doi: 10.1023/A:1010933404324
[3]	Breiman L, Friedman J, Stone C J et al., 1984. Classification and Regression Trees. UK: Chapman & Hall/CRC.
[4]	Cao Z F , 2014. Study on optimization of random forests algorithm [D]. Beijing: Capital University of Economics and Business. (in Chinese)
[5]	Chen K, Zhu Y , 2007. A summary of machine learning and related algorithms. Statistics and Information Forum, 22(5):105-112. (in Chinese)
[6]	Dong M, Xu Z Y, Li C F , 2018. The impact of carbon intensity restriction on welfare of urban and rural residents: An analysis based on CGE model. China Population, Resources and Environment, 28(2):94-105. (in Chinese)
[7]	Ebohon O J, Ikeme A J , 2006. Decomposition analysis of CO₂ emission intensity between oil-producing and non-oil-producing sub-Saharan African countries. Energy Policy, 34(18):3599-3611.
[8]	Fan J, Liao H, Liang Q M et al., 2013. Residential carbon emission evolutions in urban-rural divided China: An end-use and behavior analysis. Applied Energy, 101:323-332.
[9]	Fan Y, Liu L C, Wu G , et al., 2007. Changes in carbon intensity in China: Empirical findings from 1980-2003. Ecological Economics, 62(3/4):683-691.
[10]	Feng Y, Zhu L Y, Zhang D H , 2017. Spatial and econometric analysis of effect of industrial structure adjustment on carbon intensity in China. Soft Science, 31(7):11-15. (in Chinese)
[11]	Gingrich S, Kušková P, Steinberger J K , 2011. Long-term changes in CO₂ emissions in Austria and Czechoslovakia: Identifying the drivers of environmental pressures. Energy Policy, 39(2):535-543. doi: 10.1016/j.enpol.2010.10.006 pmid: 21461052
[12]	Greening L A, Ting M, Krackler T J , 2001. Effects of changes in residential end-uses and behavior on aggregate carbon intensity: Comparison of 10 OECD countries for the period 1970 through 1993. Energy Economics, 23(2):153-178.
[13]	Huang J, Ding G , 2014. A research on the threshold effect of the impact of technical progress on carbon intensity. Science & Technology Progress and Policy, 31(18):22-26. (in Chinese)
[14]	Iverson L R, Prasad A M, Matthews S N et al., 2008. Estimating potential habitat for 134 eastern US tree species under six climate scenarios. Forest Ecology and Management, 254(3):390-406. doi: 10.1016/j.foreco.2007.07.023
[15]	Kohavi R, Foster P , 1998. Special issue on application of machine learning and the knowledge discovery process. Journal of Machine learning, 30(2):271-274. doi: 10.1023/A:1017181826899
[16]	Li H, Wang L, Shen L et al., 2012. Study of the potential of low carbon energy development and its contribution to realize the reduction target of carbon intensity in China. Energy Policy, 41:393-401. doi: 10.1016/j.enpol.2011.10.061
[17]	Peng X, Cui H R , 2016. Research on the effects of energy structure adjustment in China on carbon intensity. Journal of Dalian University of Technology (Social Sciences), 37(1):11-16. (in Chinese)
[18]	Stern D, Jotzo F , 2010. How ambitious are China and India’s emissions intensity targets? Energy Policy, 38(11):6776-6783.
[19]	Tong J P, Chen G D, Yang Z Y et al., 2017. Threshold effects of household consumption level on residential carbon emissions. Journal of Arid Land Resources and Environment, 31(1):38-43. (in Chinese)
[20]	Voigt S, Cian E, Schymura M et al., 2014. Energy intensity developments in 40 major economies: Structural change or technology improvement? Energy Economics, 41:47-62. doi: 10.1016/j.eneco.2013.10.015
[21]	Wang S H, Yu W Y , 2013. Sensitivity analysis of primary energy consumption structural change and carbon intensity. Resources Science, 35(7):1438-1446. (in Chinese)
[22]	Xu H, Wang H , 2016. The impact of industrial structure adjustment on China’s carbon intensity goal: The outlook of 2020. Science and Technology Management Research, 36(13):232-236. (in Chinese)
[23]	Yan Z M, Deng X L, Yang Z M , 2017. The impact of heterogeneous technological innovation on carbon intensity: A global evidence based on patent statistics. Journal of Beijing Institute of Technology (Social Sciences Edition), 19(1):20-27. (in Chinese)
[24]	You H Y, Wu C F , 2014. Analysis of carbon emission efficiency and optimization of low carbon for agricultural land intensive use. Transactions of the Chinese Society of Agricultural Engineering, 30(2):224-234. (in Chinese)
[25]	Yuan J, Hou Y, Xu M , 2012. China’s 2020 carbon intensity target: Consistency, implementations, and policy implications. Renewable and Sustainable Energy Reviews, 16(7):4970-4981.
[26]	Zhang M, Gan C L, Chen Y R et al., 2016. Carbon emission efficiency and optimization of low carbon for construction land development intensity in China according to provincial panel data. Resources Science, 38(2):265-275. (in Chinese)
[27]	Zhang Y G , 2009. Structural decomposition analysis of sources of decarbonizing economic development in China: 1992-2006. Ecological Economics, 68(8/9):2399-2405.
[28]	Zhang Y G , 2010. Economic development pattern change impact on China’s carbon intensity. Economic Research Journal, ( 4):120-133. (in Chinese)
[29]	Zhu F F, Zhou L, Mo L P et al., 2015. A scientific study of establishing statistical index system. Statistical Theory and Practice, ( 11):8-12. (in Chinese)
[30]	Zhu Z Y, Miao J J, Cui W , 2016. Analysis of carbon emission efficiency for urban construction land intensive use. Areal Research and Development, 35(3):98-103. (in Chinese) doi: 10.1021/acs.est.8b01873 pmid: 29687709

Carbon intensity index number	1	2	3	4	5	6	7	8
Gini coefficient reduction	0.701	0.613	0.577	0.576	0.572	0.571	0.562	0.560
Carbon intensity index number	9	10	11	12	13	14	15	16
Gini coefficient reductions	0.504	0.462	0.449	0.380	0.376	0.372	0.371	0.365
Carbon intensity index number	17	18	19	20	21	22	23	24
Gini coefficient reductions	0.362	0.341	0.327	0.283	0.241	0.185	0.177	0.176
Carbon intensity index number	25	26	27	28	29	30	31	32
Gini coefficient reductions	0.170	0.165	0.156	0.152	0.151	0.151	0.140	0.103
Carbon intensity index number	33	34	35	36	37	38	39	40
Gini coefficient reductions	0.075	0.069	0.069	0.067	0.067	0.066	0.064	0.050
Carbon intensity index number	41	42	43	44	45	46	47	48
Gini coefficient reductions	0.050	0.049	0.035	0.034	0.034	0.034	0.034	0.033
Carbon intensity index number	49	50	51	52	53	54	55	56
Gini coefficient reductions	0.031	0.029	0.028	0.027	0.026	0.025	0.020	0.011

Category/Year	1980	...	2000	...	2010	...	2016	2017
Proportion of fossil energy	3	...	0	...	1	...	1	2
Price of fossil energy	0	...	0	...	0	...	0	0
Proportion of renewable energy (hydropower and biogas)	0	...	0	...	0	...	0	1
Proportion of new energy	0	...	0	...	1	...	3	2
Scale or proportion of energy-intensive industry	8	...	7	...	6	...	7	4
Proportion of service industry	0	...	1	...	2	...	2	2
Technological progress	8	...	6	...	4	...	6	5
Traditional consumption of residents	3	...	8	...	6	...	2	4
New consumption of residents	0	...	0	...	2	...	1	2
Total	22	...	22	...	22	...	22	22