Lan-ting Zhou , Guan-lin Long , Can-can Hu , Kai Zhang
{"title":"Reservoir water level prediction using combined CEEMDAN-FE and RUN-SVM-RBFNN machine learning algorithms","authors":"Lan-ting Zhou , Guan-lin Long , Can-can Hu , Kai Zhang","doi":"10.1016/j.wse.2025.01.002","DOIUrl":null,"url":null,"abstract":"<div><div>Accurate prediction of water level changes in reservoirs is crucial for optimizing the operation of reservoir projects and ensuring their safety. This study proposed a method for reservoir water level prediction based on CEEMDAN-FE and RUN-SVM-RBFNN algorithms. By integrating the adaptive complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method and fuzzy entropy (FE) with the new and highly efficient Runge–Kuta optimizer (RUN), adaptive parameter optimization for the support vector machine (SVM) and radial basis function neural network (RBFNN) algorithms was achieved. Regression prediction was conducted on the two reconstructed sequences using SVM and RBFNN according to their respective features. This approach improved the accuracy and stability of predictions. In terms of accuracy, the combined model outperformed single models, with the determination coefficient, root mean square error, and mean absolute error values of 0.997 5, 0.241 8 m, and 0.161 6 m, respectively. In terms of stability, the model predicted more consistently in training and testing periods, with stable overall prediction accuracy and a better adaptive ability to complex datasets. The case study demonstrated that the combined prediction model effectively addressed the environmental factors affecting reservoir water levels, leveraged the strength of each predictive method, compensated for their limitations, and clarified the impacts of environmental factors on reservoir water levels.</div></div>","PeriodicalId":23628,"journal":{"name":"Water science and engineering","volume":"18 2","pages":"Pages 177-186"},"PeriodicalIF":3.7000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Water science and engineering","FirstCategoryId":"1087","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S167423702500002X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"WATER RESOURCES","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate prediction of water level changes in reservoirs is crucial for optimizing the operation of reservoir projects and ensuring their safety. This study proposed a method for reservoir water level prediction based on CEEMDAN-FE and RUN-SVM-RBFNN algorithms. By integrating the adaptive complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method and fuzzy entropy (FE) with the new and highly efficient Runge–Kuta optimizer (RUN), adaptive parameter optimization for the support vector machine (SVM) and radial basis function neural network (RBFNN) algorithms was achieved. Regression prediction was conducted on the two reconstructed sequences using SVM and RBFNN according to their respective features. This approach improved the accuracy and stability of predictions. In terms of accuracy, the combined model outperformed single models, with the determination coefficient, root mean square error, and mean absolute error values of 0.997 5, 0.241 8 m, and 0.161 6 m, respectively. In terms of stability, the model predicted more consistently in training and testing periods, with stable overall prediction accuracy and a better adaptive ability to complex datasets. The case study demonstrated that the combined prediction model effectively addressed the environmental factors affecting reservoir water levels, leveraged the strength of each predictive method, compensated for their limitations, and clarified the impacts of environmental factors on reservoir water levels.
期刊介绍:
Water Science and Engineering journal is an international, peer-reviewed research publication covering new concepts, theories, methods, and techniques related to water issues. The journal aims to publish research that helps advance the theoretical and practical understanding of water resources, aquatic environment, aquatic ecology, and water engineering, with emphases placed on the innovation and applicability of science and technology in large-scale hydropower project construction, large river and lake regulation, inter-basin water transfer, hydroelectric energy development, ecological restoration, the development of new materials, and sustainable utilization of water resources.