Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in Beijing
Accurate runoff prediction is of great significance for flood prevention and mitigation, agricultural irrigation, and reservoir scheduling in watersheds. To address the strong non-linear and non-stationary characteristics of runoff series, a hybrid model of monthly runoff prediction, variational mod...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2023-09-01
|
| Series: | Journal of Water and Climate Change |
| Subjects: | |
| Online Access: | http://jwcc.iwaponline.com/content/14/9/3221 |
| _version_ | 1797202763053006848 |
|---|---|
| author | Shaolei Guo Yihao Wen Xianqi Zhang Haiyang Chen |
| author_facet | Shaolei Guo Yihao Wen Xianqi Zhang Haiyang Chen |
| author_sort | Shaolei Guo |
| collection | DOAJ |
| description | Accurate runoff prediction is of great significance for flood prevention and mitigation, agricultural irrigation, and reservoir scheduling in watersheds. To address the strong non-linear and non-stationary characteristics of runoff series, a hybrid model of monthly runoff prediction, variational mode decomposition (VMD)–long short-term memory (LSTM)–Transformer, is proposed. Firstly, VMD is used to decompose the runoff series into multiple modal components, and the sample entropy of each modal component is calculated and divided into high-frequency and low-frequency components. The LSTM model is then used to predict the high-frequency components and the transformer to predict the low-frequency components. Finally, the prediction results are summed to obtain the final prediction results. The Mann–Kendall trend test method is used to analyze the runoff characteristics of the Miyun Reservoir, and the constructed VMD–LSTM–Transformer model is used to forecast the runoff of the Miyun Reservoir. The prediction results are compared and evaluated with those of VMD–LSTM, VMD–Transformer, empirical mode decomposition (EMD)–LSTM–Transformer, and empirical mode decomposition (EMD)–LSTM models. The results show that the Nash–Sutcliffe efficiency coefficient (NSE) value of this model is 0.976, mean absolute error (MAE) is 0.206 × 107 m3, mean absolute percentage error (MAPE) is 0.381%, and root mean squared error (RMSE) is 0.411 × 107 m3, all of which are better than other models, indicating that the VMD–LSTM–Transformer model has higher prediction accuracy and can be applied to runoff prediction in the actual study area.
HIGHLIGHTS
The VMD–LSTM–Transformer model proposed in this paper achieves higher accuracy in monthly runoff prediction compared to other models.;
The VMD decomposition method used in the model improves the completeness and adequacy of time series decomposition.;
By using LSTM and Transformer models for different frequency components, the proposed model achieves better prediction accuracy.; |
| first_indexed | 2024-03-11T18:48:12Z |
| format | Article |
| id | doaj.art-b08373b18caa4af9a553e1cd803c5010 |
| institution | Directory Open Access Journal |
| issn | 2040-2244 2408-9354 |
| language | English |
| last_indexed | 2024-04-24T08:08:36Z |
| publishDate | 2023-09-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Journal of Water and Climate Change |
| spelling | doaj.art-b08373b18caa4af9a553e1cd803c50102024-04-17T08:33:05ZengIWA PublishingJournal of Water and Climate Change2040-22442408-93542023-09-011493221323610.2166/wcc.2023.257257Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in BeijingShaolei Guo0Yihao Wen1Xianqi Zhang2Haiyang Chen3 Water Conservancy College, North China University of Water Resources and Electric Power, Zhengzhou 450046, China Water Conservancy College, North China University of Water Resources and Electric Power, Zhengzhou 450046, China Water Conservancy College, North China University of Water Resources and Electric Power, Zhengzhou 450046, China Water Conservancy College, North China University of Water Resources and Electric Power, Zhengzhou 450046, China Accurate runoff prediction is of great significance for flood prevention and mitigation, agricultural irrigation, and reservoir scheduling in watersheds. To address the strong non-linear and non-stationary characteristics of runoff series, a hybrid model of monthly runoff prediction, variational mode decomposition (VMD)–long short-term memory (LSTM)–Transformer, is proposed. Firstly, VMD is used to decompose the runoff series into multiple modal components, and the sample entropy of each modal component is calculated and divided into high-frequency and low-frequency components. The LSTM model is then used to predict the high-frequency components and the transformer to predict the low-frequency components. Finally, the prediction results are summed to obtain the final prediction results. The Mann–Kendall trend test method is used to analyze the runoff characteristics of the Miyun Reservoir, and the constructed VMD–LSTM–Transformer model is used to forecast the runoff of the Miyun Reservoir. The prediction results are compared and evaluated with those of VMD–LSTM, VMD–Transformer, empirical mode decomposition (EMD)–LSTM–Transformer, and empirical mode decomposition (EMD)–LSTM models. The results show that the Nash–Sutcliffe efficiency coefficient (NSE) value of this model is 0.976, mean absolute error (MAE) is 0.206 × 107 m3, mean absolute percentage error (MAPE) is 0.381%, and root mean squared error (RMSE) is 0.411 × 107 m3, all of which are better than other models, indicating that the VMD–LSTM–Transformer model has higher prediction accuracy and can be applied to runoff prediction in the actual study area. HIGHLIGHTS The VMD–LSTM–Transformer model proposed in this paper achieves higher accuracy in monthly runoff prediction compared to other models.; The VMD decomposition method used in the model improves the completeness and adequacy of time series decomposition.; By using LSTM and Transformer models for different frequency components, the proposed model achieves better prediction accuracy.;http://jwcc.iwaponline.com/content/14/9/3221frequency division predictionlstmrunoff predictiontransformervmd |
| spellingShingle | Shaolei Guo Yihao Wen Xianqi Zhang Haiyang Chen Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in Beijing Journal of Water and Climate Change frequency division prediction lstm runoff prediction transformer vmd |
| title | Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in Beijing |
| title_full | Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in Beijing |
| title_fullStr | Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in Beijing |
| title_full_unstemmed | Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in Beijing |
| title_short | Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in Beijing |
| title_sort | monthly runoff prediction using the vmd lstm transformer hybrid model a case study of the miyun reservoir in beijing |
| topic | frequency division prediction lstm runoff prediction transformer vmd |
| url | http://jwcc.iwaponline.com/content/14/9/3221 |
| work_keys_str_mv | AT shaoleiguo monthlyrunoffpredictionusingthevmdlstmtransformerhybridmodelacasestudyofthemiyunreservoirinbeijing AT yihaowen monthlyrunoffpredictionusingthevmdlstmtransformerhybridmodelacasestudyofthemiyunreservoirinbeijing AT xianqizhang monthlyrunoffpredictionusingthevmdlstmtransformerhybridmodelacasestudyofthemiyunreservoirinbeijing AT haiyangchen monthlyrunoffpredictionusingthevmdlstmtransformerhybridmodelacasestudyofthemiyunreservoirinbeijing |