Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approaches
Abstract The optimal management of water resources depends on accurate and reliable streamflow prediction. Therefore, researchers have become interested in the development of hybrid approaches in recent years to enhance the performance of modeling techniques for predicting hydrological variables. In...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-05-01
|
| Series: | Applied Water Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s13201-023-01943-0 |
| _version_ | 1797806581663924224 |
|---|---|
| author | Farshad Ahmadi Mansour Tohidi Meysam Sadrianzade |
| author_facet | Farshad Ahmadi Mansour Tohidi Meysam Sadrianzade |
| author_sort | Farshad Ahmadi |
| collection | DOAJ |
| description | Abstract The optimal management of water resources depends on accurate and reliable streamflow prediction. Therefore, researchers have become interested in the development of hybrid approaches in recent years to enhance the performance of modeling techniques for predicting hydrological variables. In this study, hybrid models based on variational mode decomposition (VMD) and machine learning models such as random forest (RF) and K-star algorithm (KS) were developed to improve the accuracy of streamflow forecasting. The monthly data obtained between 1956 and 2017 at the Iranian Bibijan Abad station on the Zohreh River were used for this purpose. The streamflow data were initially decomposed into intrinsic modes functions (IMFs) using the VMD approach up to level eight to develop the hybrid models. The following step models the IMFs obtained by the VMD approach using the RF and KS methods. The ensemble forecasting result is then accomplished by adding the IMFs’ forecasting outputs. Other hybrid models, such as EDM-RF, EMD-KS, CEEMD-RF, and CEEMD-KS, were also developed in this research in order to assess the performance of VMD-RF and VMD-KS hybrid models. The findings demonstrated that data preprocessing enhanced standalone models’ performance, and those hybrid models developed based on VMD performed best in terms of increasing the accuracy of monthly streamflow predictions. The VMD-RF model is proposed as a superior method based on root mean square error (RMSE = 13.79), mean absolute error (MAE = 8.35), and Kling–Gupta (KGE = 0.89) indices. |
| first_indexed | 2024-03-13T06:09:26Z |
| format | Article |
| id | doaj.art-7dd0053840a1461ea708d114b44d206c |
| institution | Directory Open Access Journal |
| issn | 2190-5487 2190-5495 |
| language | English |
| last_indexed | 2024-03-13T06:09:26Z |
| publishDate | 2023-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Applied Water Science |
| spelling | doaj.art-7dd0053840a1461ea708d114b44d206c2023-06-11T11:22:01ZengSpringerOpenApplied Water Science2190-54872190-54952023-05-0113611810.1007/s13201-023-01943-0Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approachesFarshad Ahmadi0Mansour Tohidi1Meysam Sadrianzade2Department of Hydrology & Water Resources Engineering, Shahid Chamran University of AhvazDepartment of Civil Engineering, Ahvaz Branch, Islamic Azad UniversityDepartment of Civil Engineering-Water Resources Engineering and Management, Shoushtar Branch, Islamic Azad UniversityAbstract The optimal management of water resources depends on accurate and reliable streamflow prediction. Therefore, researchers have become interested in the development of hybrid approaches in recent years to enhance the performance of modeling techniques for predicting hydrological variables. In this study, hybrid models based on variational mode decomposition (VMD) and machine learning models such as random forest (RF) and K-star algorithm (KS) were developed to improve the accuracy of streamflow forecasting. The monthly data obtained between 1956 and 2017 at the Iranian Bibijan Abad station on the Zohreh River were used for this purpose. The streamflow data were initially decomposed into intrinsic modes functions (IMFs) using the VMD approach up to level eight to develop the hybrid models. The following step models the IMFs obtained by the VMD approach using the RF and KS methods. The ensemble forecasting result is then accomplished by adding the IMFs’ forecasting outputs. Other hybrid models, such as EDM-RF, EMD-KS, CEEMD-RF, and CEEMD-KS, were also developed in this research in order to assess the performance of VMD-RF and VMD-KS hybrid models. The findings demonstrated that data preprocessing enhanced standalone models’ performance, and those hybrid models developed based on VMD performed best in terms of increasing the accuracy of monthly streamflow predictions. The VMD-RF model is proposed as a superior method based on root mean square error (RMSE = 13.79), mean absolute error (MAE = 8.35), and Kling–Gupta (KGE = 0.89) indices.https://doi.org/10.1007/s13201-023-01943-0Central frequencyDecomposition levelNoiseSub-series |
| spellingShingle | Farshad Ahmadi Mansour Tohidi Meysam Sadrianzade Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approaches Applied Water Science Central frequency Decomposition level Noise Sub-series |
| title | Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approaches |
| title_full | Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approaches |
| title_fullStr | Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approaches |
| title_full_unstemmed | Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approaches |
| title_short | Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approaches |
| title_sort | streamflow prediction using a hybrid methodology based on variational mode decomposition vmd and machine learning approaches |
| topic | Central frequency Decomposition level Noise Sub-series |
| url | https://doi.org/10.1007/s13201-023-01943-0 |
| work_keys_str_mv | AT farshadahmadi streamflowpredictionusingahybridmethodologybasedonvariationalmodedecompositionvmdandmachinelearningapproaches AT mansourtohidi streamflowpredictionusingahybridmethodologybasedonvariationalmodedecompositionvmdandmachinelearningapproaches AT meysamsadrianzade streamflowpredictionusingahybridmethodologybasedonvariationalmodedecompositionvmdandmachinelearningapproaches |