首页|A Hybrid Daily Carbon Emission Prediction Model Combining CEEMD, WD and LSTM
A Hybrid Daily Carbon Emission Prediction Model Combining CEEMD, WD and LSTM
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
Springer Nature
In order to improve the short-term prediction accuracy of carbon emissions， a new hybrid daily carbon emission prediction model is proposed in this paper， and secondary decomposition is introduced for carbon emission prediction for the first time。 First， the data is decomposed into several IMFs by complementary ensemble empirical mode decomposition (CEEMD)。 Then， the IMF_1 is decomposed again by wavelet decomposition (WD)， and the rest IMFs are reconstructed according to the sample entropy (SE)。 Finally， Long Shor Term Memory (LSTM) is used to predict daily carbon emission。 In order to verify the validity of the model， the daily carbon emission data of China， United States (US) and World are used for empirical analysis。 In the performance comparison experiment， CEEMD-WD-LSTM model proposed in this paper has the best performance among all comparison models， and secondary decomposition of carbon emissions significantly improves the MAPE， R~2 and RMSE。 The results show that the model proposed in this paper is effective and robust， and can predict daily carbon emissions more accurately。
Daily carbon emission predictionCEEMDWDLSTMSE
Xing Zhang、Wensong Zhang
展开 >
Sinounited Investment Group Corporation Limited, Beijing 102611, China
School of Economics and Management, Beijing Jiaotong University, Beijing 100044, China
NETL
Springer Nature
