Predicting Carbon Dioxide Emissions from Energy Consumption in China with Long Short-Term Memory and Support Vector Regression Models

Climate change is a pressing global issue that needs immediate attention. The primary cause of climate change is global warming resulting from the anthropogenic emissions of greenhouse gases (GHGs). The combustion of fuels required to meet the energy demand accelerates carbon emissions, contributing to the increase of ambient GHGs. In this study, we investigated the prediction of carbon dioxide (CO2, the most important GHG) emissions resulting from energy consumption in China using Long Short-Term Memory (LSTM) and Support Vector Regression (SVR), based on the energy consumption data and annual CO2 emissions per unit of energy data from 1965 to 2022. The results indicate that the LSTM model outperforms the others.