J. J. Fang, Linshan Yang, Xiaohu Wen, Weide Li, Haijiao Yu, Ting Zhou
{"title":"基于深度学习的混合方法,用于中国西北干旱地区多时段河水流量预测","authors":"J. J. Fang, Linshan Yang, Xiaohu Wen, Weide Li, Haijiao Yu, Ting Zhou","doi":"10.2166/nh.2024.124","DOIUrl":null,"url":null,"abstract":"\n \n Accurate streamflow prediction is crucial for effective water resource management. However, reliable prediction remains a considerable challenge because of the highly complex, non-stationary, and non-linear processes that contribute to streamflow at various spatial and temporal scales. In this study, we utilized a convolutional neural network (CNN)–Transformer–Long short-term memory (LSTM) (CTL) model for streamflow prediction, which replaced the embedding layer with a CNN layer to extract partial hidden features, and added a LSTM layer to extract correlations on a temporal scale. The CTL model incorporated Transformer's ability to extract global information, CNN's ability to extract hidden features, and LSTM's ability to capture temporal correlations. To validate its effectiveness, we applied it for streamflow prediction in the Shule River basin in northwest China across 1-, 3-, and 6-month horizons and compared its performance with Transformer, CNN, LSTM, CNN–Transformer, and Transformer–LSTM. The results demonstrated that CTL outperformed all other models in terms of predictive accuracy with Nash–Sutcliffe coefficient (NSE) values of 0.964, 0.912, and 0.856 for 1-, 3-, 6-month ahead prediction. The best results among the five comparative models were 0.908, 0.824, and 0.778, respectively. This indicated that CTL is an outstanding alternative technique for streamflow prediction where surface data are limited.","PeriodicalId":55040,"journal":{"name":"Hydrology Research","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A deep learning-based hybrid approach for multi-time-ahead streamflow prediction in an arid region of Northwest China\",\"authors\":\"J. J. Fang, Linshan Yang, Xiaohu Wen, Weide Li, Haijiao Yu, Ting Zhou\",\"doi\":\"10.2166/nh.2024.124\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n \\n Accurate streamflow prediction is crucial for effective water resource management. However, reliable prediction remains a considerable challenge because of the highly complex, non-stationary, and non-linear processes that contribute to streamflow at various spatial and temporal scales. In this study, we utilized a convolutional neural network (CNN)–Transformer–Long short-term memory (LSTM) (CTL) model for streamflow prediction, which replaced the embedding layer with a CNN layer to extract partial hidden features, and added a LSTM layer to extract correlations on a temporal scale. The CTL model incorporated Transformer's ability to extract global information, CNN's ability to extract hidden features, and LSTM's ability to capture temporal correlations. To validate its effectiveness, we applied it for streamflow prediction in the Shule River basin in northwest China across 1-, 3-, and 6-month horizons and compared its performance with Transformer, CNN, LSTM, CNN–Transformer, and Transformer–LSTM. The results demonstrated that CTL outperformed all other models in terms of predictive accuracy with Nash–Sutcliffe coefficient (NSE) values of 0.964, 0.912, and 0.856 for 1-, 3-, 6-month ahead prediction. The best results among the five comparative models were 0.908, 0.824, and 0.778, respectively. This indicated that CTL is an outstanding alternative technique for streamflow prediction where surface data are limited.\",\"PeriodicalId\":55040,\"journal\":{\"name\":\"Hydrology Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2024-01-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Hydrology Research\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.2166/nh.2024.124\",\"RegionNum\":4,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Environmental Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hydrology Research","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.2166/nh.2024.124","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Environmental Science","Score":null,"Total":0}
A deep learning-based hybrid approach for multi-time-ahead streamflow prediction in an arid region of Northwest China
Accurate streamflow prediction is crucial for effective water resource management. However, reliable prediction remains a considerable challenge because of the highly complex, non-stationary, and non-linear processes that contribute to streamflow at various spatial and temporal scales. In this study, we utilized a convolutional neural network (CNN)–Transformer–Long short-term memory (LSTM) (CTL) model for streamflow prediction, which replaced the embedding layer with a CNN layer to extract partial hidden features, and added a LSTM layer to extract correlations on a temporal scale. The CTL model incorporated Transformer's ability to extract global information, CNN's ability to extract hidden features, and LSTM's ability to capture temporal correlations. To validate its effectiveness, we applied it for streamflow prediction in the Shule River basin in northwest China across 1-, 3-, and 6-month horizons and compared its performance with Transformer, CNN, LSTM, CNN–Transformer, and Transformer–LSTM. The results demonstrated that CTL outperformed all other models in terms of predictive accuracy with Nash–Sutcliffe coefficient (NSE) values of 0.964, 0.912, and 0.856 for 1-, 3-, 6-month ahead prediction. The best results among the five comparative models were 0.908, 0.824, and 0.778, respectively. This indicated that CTL is an outstanding alternative technique for streamflow prediction where surface data are limited.
期刊介绍:
Hydrology Research provides international coverage on all aspects of hydrology in its widest sense, and welcomes the submission of papers from across the subject. While emphasis is placed on studies of the hydrological cycle, the Journal also covers the physics and chemistry of water. Hydrology Research is intended to be a link between basic hydrological research and the practical application of scientific results within the broad field of water management.