Changli Li, Zheng Han, Yange Li, Ming Li, Weidong Wang, Ningsheng Chen, Guisheng Hu
{"title":"基于数据驱动和回波状态网络的溃坝洪水波浪传播特性预测","authors":"Changli Li, Zheng Han, Yange Li, Ming Li, Weidong Wang, Ningsheng Chen, Guisheng Hu","doi":"10.2166/hydro.2023.035","DOIUrl":null,"url":null,"abstract":"Abstract The computational prediction of wave propagation in dam-break floods is a long-standing problem in hydrodynamics and hydrology. We show that a reservoir computing echo state network (RC-ESN) that is well-trained on a minimal amount of data can accurately predict the long-term dynamic behavior of a one-dimensional dam-break flood. We solve the de Saint-Venant equations for a one-dimensional dam-break flood scenario using the Lax–Wendroff numerical scheme and train the RC-ESN model. The results demonstrate that the RC-ESN model has good prediction ability, as it predicts wave propagation behavior 286 time-steps ahead with a root mean square error smaller than 0.01, outperforming the conventional long short-term memory (LSTM) model, which only predicts 81 time-steps ahead. We also provide a sensitivity analysis of prediction accuracy for RC-ESN's key parameters such as training set size, reservoir size, and spectral radius. Results indicate that the RC-ESN is less dependent on training set size, with a medium reservoir size of 1,200–2,600 sufficient. We confirm that the spectral radius has a complex influence on the prediction accuracy and currently recommend a smaller spectral radius. Even when the initial flow depth of the dam break is changed, the prediction horizon of RC-ESN remains greater than that of LSTM.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"14 9","pages":"0"},"PeriodicalIF":2.2000,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Data-driven and echo state network-based prediction of wave propagation behavior in dam-break flood\",\"authors\":\"Changli Li, Zheng Han, Yange Li, Ming Li, Weidong Wang, Ningsheng Chen, Guisheng Hu\",\"doi\":\"10.2166/hydro.2023.035\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract The computational prediction of wave propagation in dam-break floods is a long-standing problem in hydrodynamics and hydrology. We show that a reservoir computing echo state network (RC-ESN) that is well-trained on a minimal amount of data can accurately predict the long-term dynamic behavior of a one-dimensional dam-break flood. We solve the de Saint-Venant equations for a one-dimensional dam-break flood scenario using the Lax–Wendroff numerical scheme and train the RC-ESN model. The results demonstrate that the RC-ESN model has good prediction ability, as it predicts wave propagation behavior 286 time-steps ahead with a root mean square error smaller than 0.01, outperforming the conventional long short-term memory (LSTM) model, which only predicts 81 time-steps ahead. We also provide a sensitivity analysis of prediction accuracy for RC-ESN's key parameters such as training set size, reservoir size, and spectral radius. Results indicate that the RC-ESN is less dependent on training set size, with a medium reservoir size of 1,200–2,600 sufficient. We confirm that the spectral radius has a complex influence on the prediction accuracy and currently recommend a smaller spectral radius. Even when the initial flow depth of the dam break is changed, the prediction horizon of RC-ESN remains greater than that of LSTM.\",\"PeriodicalId\":54801,\"journal\":{\"name\":\"Journal of Hydroinformatics\",\"volume\":\"14 9\",\"pages\":\"0\"},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2023-11-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Hydroinformatics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2166/hydro.2023.035\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hydroinformatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2166/hydro.2023.035","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
Data-driven and echo state network-based prediction of wave propagation behavior in dam-break flood
Abstract The computational prediction of wave propagation in dam-break floods is a long-standing problem in hydrodynamics and hydrology. We show that a reservoir computing echo state network (RC-ESN) that is well-trained on a minimal amount of data can accurately predict the long-term dynamic behavior of a one-dimensional dam-break flood. We solve the de Saint-Venant equations for a one-dimensional dam-break flood scenario using the Lax–Wendroff numerical scheme and train the RC-ESN model. The results demonstrate that the RC-ESN model has good prediction ability, as it predicts wave propagation behavior 286 time-steps ahead with a root mean square error smaller than 0.01, outperforming the conventional long short-term memory (LSTM) model, which only predicts 81 time-steps ahead. We also provide a sensitivity analysis of prediction accuracy for RC-ESN's key parameters such as training set size, reservoir size, and spectral radius. Results indicate that the RC-ESN is less dependent on training set size, with a medium reservoir size of 1,200–2,600 sufficient. We confirm that the spectral radius has a complex influence on the prediction accuracy and currently recommend a smaller spectral radius. Even when the initial flow depth of the dam break is changed, the prediction horizon of RC-ESN remains greater than that of LSTM.
期刊介绍:
Journal of Hydroinformatics is a peer-reviewed journal devoted to the application of information technology in the widest sense to problems of the aquatic environment. It promotes Hydroinformatics as a cross-disciplinary field of study, combining technological, human-sociological and more general environmental interests, including an ethical perspective.