Prediction of China's Industrial Carbon Peak: Based on GDIM-MC Model and LSTM-NN Model

Abstract The industrial sector is the key area for China to achieve the carbon peaking goals, as it accounts for more than 65% and 70% of the national total energy consumption and carbon emissions. However, the discussion on the time and route of carbon peak in China in the existing literature is still quite different. In this study, we establish three scenarios and comprehensively used Monte Carlo simulation and LSTM Neural Network model to predict the evolution trends of China's industrial carbon emissions during 2020–2030. Firstly, the decomposition results of the Generalized Divisia Index Method shows that fixed assets investment is the most important factor for promoting and carbon intensity of investment is the key for reducing carbon emissions. Then, basing on the Monte Carlo dynamic simulation, we could draw the three kinds of carbon emissions route that it will peak in 2031 in the Baseline scenario, in the Green Development scenario (environmental policy improvement) and Technological Breakthrough scenario (green technology progress) will peak in 2027 and 2025, and under the LSTM Neural Network model, peak time will occur in 2028. Comparing the results of above predictions, China's industrial carbon emissions could peak by 2030(in GD scenario, 2027; TB scenario, 2025). Finally, we discuss the path of China's industrial carbon emissions reduction and provide a reference for the rational formulation of low-carbon regulatory policies in the future and the realization of sustainable development.