A comparative study of statistical and machine learning models on carbon dioxide emissions prediction of China

Abstract

Abstract The rapid growth of carbon dioxide (\({\text{C}\text{O}}_{2}\)) emissions is the primary cause of global warming, which not only poses a significant threat to human survival, but also has a profound impact on the global ecosystem. Consequently, it is crucial to accurately predict and effectively control \({\text{C}\text{O}}_{2}\) emissions in a timely manner to provide guidance for emission mitigation measures. This paper aims to select the best prediction model for near-real-time daily \({\text{C}\text{O}}_{2}\) emissions in China. The prediction models are based on univariate daily time-series data spanning January 1st, 2020 to September 30st, 2022. Six models are proposed, including three statistical models: Grey prediction (GM(1,1)), autoregressive integrated moving average (ARIMA) and seasonal autoregressive integrated moving average with exogenous factors (SARIMAX); and three machine learning models: artificial neural network (ANN), random forest (RF) and long short term memory (LSTM). The performance of these six models is evaluated using five criteria: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (\({\text{R}}^{2}\)). The results indicate that the three machine learning models outperform the three statistical models. Among them, the LSTM model demonstrates the best performance across all five criteria for daily \({\text{C}\text{O}}_{2}\) emissions prediction, with an MSE value of 3.5179e-04, an RMSE value of 0.0187, an MAE value of 0.0140, an MAPE value of 14.8291%, an \({\text{R}}^{2}\) value of 0.9844. Therefore, LSTM model is suggested as one of the most suitable models for near-real-time daily \({\text{C}\text{O}}_{2}\) emissions prediction based on the provided daily time series data. Finally, based on the study’s results, several policy recommendations are presented to various departments in China for reducing carbon emissions.