Forecast of China’s carbon emissions under the background of carbon neutrality

Climate change intensifies, so does the need to reduce carbon emissions to achieve the goal of being “carbon neutral” for China. This paper focuses on carbon emission prediction and constructs a comprehensive model integrating least absolute shrinkage and selection operator (LASSO), principal component analysis (PCA), support vector regression (SVR), and differential evolution-gray wolf optimization (DE-GWO). Firstly, LASSO is used for feature selection, and important information is extracted from various influencing factors to find out what have a great impact on carbon emission. Principal component analysis is used to extract the features of the remaining variables to avoid missing information caused by feature selection. Secondly, DE-GWO algorithm is used to optimize the parameters of SVR to improve the prediction accuracy. The scenario analysis and prediction algorithm are combined to predict China’s carbon emissions. The results show that (1) coal and oil consumption, plate glass, pig iron, and crude steel production are important factors affecting carbon emissions; (2) the use of PCA to comprehensively consider the impact of remaining factors on carbon emissions has a positive influence on carbon emissions prediction; and (3) DE-GWO optimized SVR has higher prediction accuracy than other algorithms.