Monthly Runoff Prediction Based on STL-CEEMDAN-LSTM Model
According to the nonlinear and non-stationary characteristics of monthly runoff sequences, the quadratic decomposition method was combined with machine learning to construct a model for predicting monthly runoff. This model uses a seasonal trend decomposition procedure based on loess (STL) to decomp...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Pearl River
2024-01-01
|
| Series: | Renmin Zhujiang |
| Subjects: | |
| Online Access: | http://www.renminzhujiang.cn/thesisDetails?columnId=77779662&Fpath=home&index=0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530204474834944 |
|---|---|
| author | WANG Hai SHEN Yanqing QI Shansheng PAN Hongzhong HUO Jianzhen WANG Zhance |
| author_facet | WANG Hai SHEN Yanqing QI Shansheng PAN Hongzhong HUO Jianzhen WANG Zhance |
| author_sort | WANG Hai |
| collection | DOAJ |
| description | According to the nonlinear and non-stationary characteristics of monthly runoff sequences, the quadratic decomposition method was combined with machine learning to construct a model for predicting monthly runoff. This model uses a seasonal trend decomposition procedure based on loess (STL) to decompose the measured monthly runoff sequence into trend terms, seasonal terms, and residual terms with different frequencies. The complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm was then applied to decompose the residual terms to obtain intrinsic mode functions (IMFs) of different frequency components. Finally, the trend term, seasonal term, and each modal component IMF were used as inputs for the long short term memory network (LSTM) for training and prediction. The model was validated with measured monthly runoff data from Tangnaihai hydrological station in the upper reaches of the Yellow River and was compared and analyzed with other models. The results show that the STL-CEEMDAN-LSTM prediction model has a good simulation effect. The Nash Sutcliffe efficiency (NSE), root mean square error (RMSE), and R<sup>2</sup> in the model prediction period are 0.813, 239.02, and 0.810, respectively, with the prediction accuracy better than the single model and the primary decomposition model. The secondary decomposition of STL-CEEMDAN can effectively improve the prediction accuracy of the model. |
| format | Article |
| id | doaj-art-4986a597db3a4ea284ffdbad19dc089a |
| institution | Kabale University |
| issn | 1001-9235 |
| language | zho |
| publishDate | 2024-01-01 |
| publisher | Editorial Office of Pearl River |
| record_format | Article |
| series | Renmin Zhujiang |
| spelling | doaj-art-4986a597db3a4ea284ffdbad19dc089a2025-01-15T03:08:27ZzhoEditorial Office of Pearl RiverRenmin Zhujiang1001-92352024-01-0111177779662Monthly Runoff Prediction Based on STL-CEEMDAN-LSTM ModelWANG HaiSHEN YanqingQI ShanshengPAN HongzhongHUO JianzhenWANG ZhanceAccording to the nonlinear and non-stationary characteristics of monthly runoff sequences, the quadratic decomposition method was combined with machine learning to construct a model for predicting monthly runoff. This model uses a seasonal trend decomposition procedure based on loess (STL) to decompose the measured monthly runoff sequence into trend terms, seasonal terms, and residual terms with different frequencies. The complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm was then applied to decompose the residual terms to obtain intrinsic mode functions (IMFs) of different frequency components. Finally, the trend term, seasonal term, and each modal component IMF were used as inputs for the long short term memory network (LSTM) for training and prediction. The model was validated with measured monthly runoff data from Tangnaihai hydrological station in the upper reaches of the Yellow River and was compared and analyzed with other models. The results show that the STL-CEEMDAN-LSTM prediction model has a good simulation effect. The Nash Sutcliffe efficiency (NSE), root mean square error (RMSE), and R<sup>2</sup> in the model prediction period are 0.813, 239.02, and 0.810, respectively, with the prediction accuracy better than the single model and the primary decomposition model. The secondary decomposition of STL-CEEMDAN can effectively improve the prediction accuracy of the model.http://www.renminzhujiang.cn/thesisDetails?columnId=77779662&Fpath=home&index=0runoff predictionupper reaches of the Yellow Rivermodal decompositionneural networks for short and long-term memory |
| spellingShingle | WANG Hai SHEN Yanqing QI Shansheng PAN Hongzhong HUO Jianzhen WANG Zhance Monthly Runoff Prediction Based on STL-CEEMDAN-LSTM Model Renmin Zhujiang runoff prediction upper reaches of the Yellow River modal decomposition neural networks for short and long-term memory |
| title | Monthly Runoff Prediction Based on STL-CEEMDAN-LSTM Model |
| title_full | Monthly Runoff Prediction Based on STL-CEEMDAN-LSTM Model |
| title_fullStr | Monthly Runoff Prediction Based on STL-CEEMDAN-LSTM Model |
| title_full_unstemmed | Monthly Runoff Prediction Based on STL-CEEMDAN-LSTM Model |
| title_short | Monthly Runoff Prediction Based on STL-CEEMDAN-LSTM Model |
| title_sort | monthly runoff prediction based on stl ceemdan lstm model |
| topic | runoff prediction upper reaches of the Yellow River modal decomposition neural networks for short and long-term memory |
| url | http://www.renminzhujiang.cn/thesisDetails?columnId=77779662&Fpath=home&index=0 |
| work_keys_str_mv | AT wanghai monthlyrunoffpredictionbasedonstlceemdanlstmmodel AT shenyanqing monthlyrunoffpredictionbasedonstlceemdanlstmmodel AT qishansheng monthlyrunoffpredictionbasedonstlceemdanlstmmodel AT panhongzhong monthlyrunoffpredictionbasedonstlceemdanlstmmodel AT huojianzhen monthlyrunoffpredictionbasedonstlceemdanlstmmodel AT wangzhance monthlyrunoffpredictionbasedonstlceemdanlstmmodel |