The forecasting of carbon prices is critical to understand China unified carbon market dynamics. In this study, in order to reduce the noise and modal aliasing of carbon price sequence, a novel hybrid forecasting model is presented to predict carbon price in China unified carbon market. First, a three-stage algorithm that combines the improved complete ensemble empirical mode decomposition with adaptive noise (iCEEMDAN), variational mode decomposition (VMD), and reconstruction of fine-to-coarse (REC) data is proposed. Time series data are decomposed and reconstructed by this three-stage algorithm into three subsequences. Secondly, the model which combines the long short-term memory (LSTM) and convolutional neural networks (CNN) is utilized for prediction. Finally, the empirical results indicate that the prediction accuracy of this hybrid forecasting model is improved around 65 % higher than that of traditional LSTM. The proposed hybrid forecasting model can help the enterprises to make decisions facing non-linear, non-stationary and irregular carbon price more effectively. It is conducive to the implementation of energy conservation and emission reduction policies for the governments.