Carbon price point–interval forecasting based on two-layer decomposition and deep learning combined model using weight assignment

• Published in: Journal of cleaner production 2024-12, Vol.483, p.144124, Article 144124
• Main Authors: Cui, Xiwen, Niu, Dongxiao
• Format: Article
• Language: English
• Subjects: carbon; carbon markets; Carbon price; China; data collection; Decomposition model; energy costs; energy policy; entropy; geometry; Interval forecasting; natural gas; neural networks; petroleum; prediction; statistical analysis; Symplectic geometry mode decomposition; Variational mode decomposition
• ISSN: 0959-6526
• DOI: 10.1016/j.jclepro.2024.144124

With the intensification of global warming, the demand for carbon emissions reduction has gradually increased in various countries. Carbon price is crucial for promoting the activation of the carbon trading market and facilitating emissions reduction. However, the current carbon price has non-linear characteristics, large fluctuations, and high complexity, making accurate predictions challenging. To effectively predict the trends and the change of carbon price, this study proposed a hybrid deep learning point–interval prediction model. First, an improved variational mode decomposition–symplectic geometry mode decomposition (IVMD–SGMD) two-layer decomposition model was constructed to decompose the carbon prices into regular subsequences. Then, attention–temporal convolutional network–bidirectional gated recurrent unit (Attention-TCN-BiGRU) and Encoder–Decoder long short-term memory (LSTM) combined prediction models were constructed for the prediction of subsequences. The entropy method (EM) was used to assign weights to the predictions of two models to achieve model complementarity and a linear reconstruction of the models' results. Then the error correction was performed to obtain the final prediction results. This study conducted experiments on carbon prices in the Guangdong and Shenzhen markets. The mean absolute error (MAE) of the proposed model for the two datasets was reduced by 89.69% and 87.43% respectively lower than that for LSTM. To demonstrate the model's adaptability, prediction experiments conducted on natural gas and crude oil prices were employed, confirming its strong predictive accuracy in energy price forecasting. Based on the point prediction error, the interval prediction using the improved kernel density estimation (IKDE) provides more carbon market information for decision makers. The proposed model aids government energy policy formulation and fosters ongoing efforts to reduce carbon emissions. •Propose a point-interval carbon price forecasting model.•The carbon price data is decomposed using a two-layer decomposition model.•Deep learning combined models using weight assignment are used for point forecasting.•Error correction model is used to further improve forecasting accuracy.•Improved kernel density estimation is used for interval forecasting.