Multi-step carbon emissions forecasting using an interpretable framework of new data preprocessing techniques and improved grey multivariable convolution model

Abstract

As China stands at a critical juncture in its transition towards a low-carbon future, the precise prediction and analysis of provincial carbon emissions have emerged as paramount tasks. Focusing on forecasting in this intricate and vital domain, an updated grey multivariable convolution model is designed by employing the unified new-information-oriented accumulating generation operator (UNAGO) technique to process raw sequences. Equipped with UNAGO's hyper-parameters that enable the independent scaling effects and prioritize new information, the newly-designed model offers high flexibility and adaptability for handling complex provincial carbon emissions. Subsequently, four different restricted carbon emission sequences are utilized as case studies for validation purposes, and the new model's performance is scrutinized against five contrasting methods across three prediction forecasting horizons. Comparative experimental results reveal the new model's superior level of accuracy in predicting carbon emissions across four different provinces, with MAPE values of <4 % and 10 % in the in-sample and out-of-sample periods, respectively. Furthermore, rigorous evaluations with Diebold-Mariano (DM) and Probability Density Analysis (PDA) tests confirm the model's robust and general forecasting capabilities.