Analysis of Spatiotemporal Evolution Characteristics and Driving Factors of Carbon Emission Prediction in China—A Study Based on ARIMA-BP Neural Network Algorithm postprint

Abstract: Based on the energy consumption data of 30 provinces in China from 2000 to 2021, the total carbon emissions of 30 provinces in China from 2000 to 2035 were measured and predicted based on the ARIMA model and BP neural network model. The results show that: (1) From 2000 to 2035, China’s total carbon emissions will increase year by year, but the growth rate of carbon emissions will gradually decrease; The carbon emission structure is "secondary industry> residents’ daily life> tertiary industry >primary industry", the secondary industry and residents’ living carbon growth rate is relatively fast, and the change trend of the primary industry and the tertiary industry is small. (2) The spatial distribution of carbon emissions in various provinces in China presents a typical distribution pattern of "eastern>central>western" and "northern >south", and the carbon emission center has a tendency to move to the northwest. (3) The carbon emissions of the regions with higher levels of digital economy, industrial structure and new productivity are relatively small, which has a significant group difference effect. (4) The energy consumption intensity effect is the main factor driving the continuous growth of carbon emissions, the per capita GDP and energy consumption structure effect are the main factors inhibiting carbon emissions, and the impact of industrial structure and population scale effect is relatively small. Based on the research conclusions, policy suggestions are put forward from the aspects of energy structure, industrial structure, new quality productivity and digital economy.