Ensemble framework for daily carbon dioxide emissions forecasting based on the signal decomposition–reconstruction model

Abstract

The accurate prediction of daily carbon dioxide (CO2) emissions is crucial for grasping the real-time dynamics of CO2 emissions and formulating emission reduction policies. The use of the artificial intelligence model in CO2 emissions prediction has frequently been reported; however, research on the signal decomposition–reconstruction prediction model has rarely been conducted. Daily CO2 emissions are heavily influenced by human activities and show strong non-stationarity, potentially preventing a single artificial intelligence model from yielding satisfactory prediction results. To improve the accuracy of daily CO2 emissions prediction, we propose an ensemble framework based on signal decomposition–reconstruction model for predicting daily CO2 emissions. Our proposed ensemble frameworkis tested on real-world data from 14 regions. The research results show that in predicting daily industrial CO2 emissions, the coefficient of determination (R2) of our proposed model exceeds 0.96, the mean absolute percentage error (MAPE) and root mean square error (RMSE) values are better than those of other models. MAPE is generally within 20% for different forecast lead times. For another kind of CO2 emissions data, our proposed ensemble framework has also demonstrated robust prediction performance for daily ground transport CO2 emissions data, with an R2 exceeding 0.9 in most cases, and a MAPE within 17% for different forecast lead times. This study highlights the efficiency of the proposed model in addressing the issue of daily CO2 emissions prediction. It also provides a method for predicting hourly and annual CO2 emissions.