Multi‐step‐ahead flood forecasting using an improved BiLSTM‐S2S model
(2022) In Journal of Flood Risk Management 15(4).- Abstract
- Rainfall–runoff modeling is a complex hydrological issue that still has room for improvement. This study developed a coupled bidirectional long short-term memory (LSTM) with sequence-to-sequence (Seq2Seq) learning (BiLSTM-Seq2seq) model to simulate multi-step-ahead runoff for flood events. The bidirectional LSTM with Seq2Seq learning (LSTM-Seq2Seq) and multilayer perceptron (MLP) was set as benchmarks. The results show that: (1) root mean absolute error is reduced by approximately 19% up to 27%, and the Nash–Sutcliffe coefficient of efficiency is improved by 14% up to 34% for 6-h-ahead runoff prediction for BiLSTM-Seq2Seq compared LSTM-Seq2Seq and MLP; (2) The BiLSTM-Seq2Seq model has good performance not only for one-peak flood events but... (More)
- Rainfall–runoff modeling is a complex hydrological issue that still has room for improvement. This study developed a coupled bidirectional long short-term memory (LSTM) with sequence-to-sequence (Seq2Seq) learning (BiLSTM-Seq2seq) model to simulate multi-step-ahead runoff for flood events. The bidirectional LSTM with Seq2Seq learning (LSTM-Seq2Seq) and multilayer perceptron (MLP) was set as benchmarks. The results show that: (1) root mean absolute error is reduced by approximately 19% up to 27%, and the Nash–Sutcliffe coefficient of efficiency is improved by 14% up to 34% for 6-h-ahead runoff prediction for BiLSTM-Seq2Seq compared LSTM-Seq2Seq and MLP; (2) The BiLSTM-Seq2Seq model has good performance not only for one-peak flood events but also for multi-peak flood events; and (3) BiLSTM-Seq2Seq can mitigate the time-delay problem and time lag is shortened by 39% up to 69% in comparison to LSTM-Seq2Seq and MLP. These results suggest that the time-delay problem can be mitigated by BiLSTM-Seq2Seq, which has excellent potential in time series predictions in the hydrological field. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/5ca7384c-6b87-4540-8b04-a368744216a9
- author
- Cao, Qing ; Zhang, Hanchen ; Zhu, Feilin ; Hao, Zhenchun and Yuan, Feifei LU
- publishing date
- 2022-12-01
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Journal of Flood Risk Management
- volume
- 15
- issue
- 4
- publisher
- Blackwell Publishing
- external identifiers
-
- scopus:85131730131
- ISSN
- 1753-318X
- DOI
- 10.1111/jfr3.12827
- language
- English
- LU publication?
- no
- id
- 5ca7384c-6b87-4540-8b04-a368744216a9
- date added to LUP
- 2024-12-16 20:28:50
- date last changed
- 2025-04-04 14:39:37
@article{5ca7384c-6b87-4540-8b04-a368744216a9, abstract = {{Rainfall–runoff modeling is a complex hydrological issue that still has room for improvement. This study developed a coupled bidirectional long short-term memory (LSTM) with sequence-to-sequence (Seq2Seq) learning (BiLSTM-Seq2seq) model to simulate multi-step-ahead runoff for flood events. The bidirectional LSTM with Seq2Seq learning (LSTM-Seq2Seq) and multilayer perceptron (MLP) was set as benchmarks. The results show that: (1) root mean absolute error is reduced by approximately 19% up to 27%, and the Nash–Sutcliffe coefficient of efficiency is improved by 14% up to 34% for 6-h-ahead runoff prediction for BiLSTM-Seq2Seq compared LSTM-Seq2Seq and MLP; (2) The BiLSTM-Seq2Seq model has good performance not only for one-peak flood events but also for multi-peak flood events; and (3) BiLSTM-Seq2Seq can mitigate the time-delay problem and time lag is shortened by 39% up to 69% in comparison to LSTM-Seq2Seq and MLP. These results suggest that the time-delay problem can be mitigated by BiLSTM-Seq2Seq, which has excellent potential in time series predictions in the hydrological field.}}, author = {{Cao, Qing and Zhang, Hanchen and Zhu, Feilin and Hao, Zhenchun and Yuan, Feifei}}, issn = {{1753-318X}}, language = {{eng}}, month = {{12}}, number = {{4}}, publisher = {{Blackwell Publishing}}, series = {{Journal of Flood Risk Management}}, title = {{Multi‐step‐ahead flood forecasting using an improved BiLSTM‐S2S model}}, url = {{http://dx.doi.org/10.1111/jfr3.12827}}, doi = {{10.1111/jfr3.12827}}, volume = {{15}}, year = {{2022}}, }