Deep Learning Model for Real‐Time Flood Forecasting in Fast‐Flowing Watershed

ABSTRACT The fast‐flowing watershed is characterized by rapid runoff and confluence, posing challenges for accurate flood prediction. We introduce three flood forecasting model structures, namely GRU‐ED, LSTM‐FED, and LSTM‐DSA to address this issue. Through application research in three representati...

Full description

Saved in:
Bibliographic Details
Main Authors: Fan Wang, Jie Mu, Cheng Zhang, Weiqi Wang, Wuxia Bi, Wenqing Lin, Dawei Zhang
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Journal of Flood Risk Management
Subjects:
Online Access:https://doi.org/10.1111/jfr3.70036
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849339549556146176
author Fan Wang
Jie Mu
Cheng Zhang
Weiqi Wang
Wuxia Bi
Wenqing Lin
Dawei Zhang
author_facet Fan Wang
Jie Mu
Cheng Zhang
Weiqi Wang
Wuxia Bi
Wenqing Lin
Dawei Zhang
author_sort Fan Wang
collection DOAJ
description ABSTRACT The fast‐flowing watershed is characterized by rapid runoff and confluence, posing challenges for accurate flood prediction. We introduce three flood forecasting model structures, namely GRU‐ED, LSTM‐FED, and LSTM‐DSA to address this issue. Through application research in three representative watersheds, we found that: First, as input information attenuates, the predictive ability of the models may decline with an extended lead time. The incorporation of a feedback mechanism effectively addresses this issue, resulting in an average 5% improvement in Nash efficiency and a significant 26.4% reduction in the interquartile range of relative peak error. Second, the performance of the model is influenced by various factors, including the watershed characteristics, sample size, and temporal resolution. Further investigation is required to determine the extent of their influence. The attention mechanism dynamically assigns weights to input data, significantly improving model performance, especially for larger catchments. This leads to an average increase in Nash efficiency of approximately 7.86% and a reduction in the interquartile range of relative peak error by about 30.7%. Finally, the proposed models demonstrate a high level of accuracy in flood forecasting within a specific lead time, offering an innovative deep learning‐based solution to the problem of fast‐flowing watershed flood forecasting.
format Article
id doaj-art-48f6a5ae12fd45deb1e6de8e495c773d
institution Kabale University
issn 1753-318X
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Journal of Flood Risk Management
spelling doaj-art-48f6a5ae12fd45deb1e6de8e495c773d2025-08-20T03:44:06ZengWileyJournal of Flood Risk Management1753-318X2025-03-01181n/an/a10.1111/jfr3.70036Deep Learning Model for Real‐Time Flood Forecasting in Fast‐Flowing WatershedFan Wang0Jie Mu1Cheng Zhang2Weiqi Wang3Wuxia Bi4Wenqing Lin5Dawei Zhang6National Key Laboratory of Water Disaster Prevention Hohai University Nanjing P. R. ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin Beijing P. R. ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin Beijing P. R. ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin Beijing P. R. ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin Beijing P. R. ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin Beijing P. R. ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin Beijing P. R. ChinaABSTRACT The fast‐flowing watershed is characterized by rapid runoff and confluence, posing challenges for accurate flood prediction. We introduce three flood forecasting model structures, namely GRU‐ED, LSTM‐FED, and LSTM‐DSA to address this issue. Through application research in three representative watersheds, we found that: First, as input information attenuates, the predictive ability of the models may decline with an extended lead time. The incorporation of a feedback mechanism effectively addresses this issue, resulting in an average 5% improvement in Nash efficiency and a significant 26.4% reduction in the interquartile range of relative peak error. Second, the performance of the model is influenced by various factors, including the watershed characteristics, sample size, and temporal resolution. Further investigation is required to determine the extent of their influence. The attention mechanism dynamically assigns weights to input data, significantly improving model performance, especially for larger catchments. This leads to an average increase in Nash efficiency of approximately 7.86% and a reduction in the interquartile range of relative peak error by about 30.7%. Finally, the proposed models demonstrate a high level of accuracy in flood forecasting within a specific lead time, offering an innovative deep learning‐based solution to the problem of fast‐flowing watershed flood forecasting.https://doi.org/10.1111/jfr3.70036data‐driven modelfast‐flowing watershedflood forecastingLSTM networks
spellingShingle Fan Wang
Jie Mu
Cheng Zhang
Weiqi Wang
Wuxia Bi
Wenqing Lin
Dawei Zhang
Deep Learning Model for Real‐Time Flood Forecasting in Fast‐Flowing Watershed
Journal of Flood Risk Management
data‐driven model
fast‐flowing watershed
flood forecasting
LSTM networks
title Deep Learning Model for Real‐Time Flood Forecasting in Fast‐Flowing Watershed
title_full Deep Learning Model for Real‐Time Flood Forecasting in Fast‐Flowing Watershed
title_fullStr Deep Learning Model for Real‐Time Flood Forecasting in Fast‐Flowing Watershed
title_full_unstemmed Deep Learning Model for Real‐Time Flood Forecasting in Fast‐Flowing Watershed
title_short Deep Learning Model for Real‐Time Flood Forecasting in Fast‐Flowing Watershed
title_sort deep learning model for real time flood forecasting in fast flowing watershed
topic data‐driven model
fast‐flowing watershed
flood forecasting
LSTM networks
url https://doi.org/10.1111/jfr3.70036
work_keys_str_mv AT fanwang deeplearningmodelforrealtimefloodforecastinginfastflowingwatershed
AT jiemu deeplearningmodelforrealtimefloodforecastinginfastflowingwatershed
AT chengzhang deeplearningmodelforrealtimefloodforecastinginfastflowingwatershed
AT weiqiwang deeplearningmodelforrealtimefloodforecastinginfastflowingwatershed
AT wuxiabi deeplearningmodelforrealtimefloodforecastinginfastflowingwatershed
AT wenqinglin deeplearningmodelforrealtimefloodforecastinginfastflowingwatershed
AT daweizhang deeplearningmodelforrealtimefloodforecastinginfastflowingwatershed