Application study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin

Floods are often caused by short-term heavy rainfall. An Integrated Flood Analysis System (IFAS) model is good at runoff simulation and a Long Short-Term Memory (LSTM) model is good at learning massive data and realizing rainfall forecast. In this paper, the applicability of the IFAS model to runoff...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yue-Chao Chen, Jia-Jia Gao, Zhao-Hui Bin, Jia-Zhong Qian, Rui-Liang Pei, Hua Zhu
Formato: article
Lenguaje:EN
Publicado: IWA Publishing 2021
Materias:
Acceso en línea:https://doaj.org/article/d7a6a546d17a464dbe2282f9e8308b26
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:d7a6a546d17a464dbe2282f9e8308b26
record_format dspace
spelling oai:doaj.org-article:d7a6a546d17a464dbe2282f9e8308b262021-11-05T17:51:31ZApplication study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin1464-71411465-173410.2166/hydro.2021.035https://doaj.org/article/d7a6a546d17a464dbe2282f9e8308b262021-09-01T00:00:00Zhttp://jh.iwaponline.com/content/23/5/1098https://doaj.org/toc/1464-7141https://doaj.org/toc/1465-1734Floods are often caused by short-term heavy rainfall. An Integrated Flood Analysis System (IFAS) model is good at runoff simulation and a Long Short-Term Memory (LSTM) model is good at learning massive data and realizing rainfall forecast. In this paper, the applicability of the IFAS model to runoff simulation in the Tokachi River basin and the LSTM model to forecast hourly rainfall was studied, and the accuracy of flood prediction was also studied by inputting the optimal rainfall data forecasted by the LSTM model into the IFAS model. The research results show that the IFAS model can accurately simulate the runoff process in the Tokachi River basin. In the calibration period and the verification period, the Nash–Sutcliffe Efficiency coefficient (NSE) of all simulation results are above 0.75; the LSTM model can achieve forecast hourly rainfall with high precision, the NSE of best forecast results is 0.86; the IFAS model can achieve flood prediction with high precision by using the optimal rainfall data forecasted by the LSTM model, the NSE of simulation result is 0.81. The above conclusions show that it is of great significance to combine the hourly rainfall forecasted by the LSTM model with the IFAS model for flood prediction. HIGHLIGHTS The Integrated Flood Analysis System (IFAS) model can accurately simulate runoff in the Tokachi River basin.; The Long Short-Term Memory (LSTM) model can achieve high-precision hourly rainfall forecast.; The combination of the optimal hourly rainfall predicted by the LSTM model and the calibrated IFAS model can achieve high-precision runoff simulation, which makes a beneficial exploration for the realization of flood forecasting.;Yue-Chao ChenJia-Jia GaoZhao-Hui BinJia-Zhong QianRui-Liang PeiHua ZhuIWA Publishingarticleflood predictionifas modellstm modelrainfall and runoff simulationtokachi river basinInformation technologyT58.5-58.64Environmental technology. Sanitary engineeringTD1-1066ENJournal of Hydroinformatics, Vol 23, Iss 5, Pp 1098-1111 (2021)
institution DOAJ
collection DOAJ
language EN
topic flood prediction
ifas model
lstm model
rainfall and runoff simulation
tokachi river basin
Information technology
T58.5-58.64
Environmental technology. Sanitary engineering
TD1-1066
spellingShingle flood prediction
ifas model
lstm model
rainfall and runoff simulation
tokachi river basin
Information technology
T58.5-58.64
Environmental technology. Sanitary engineering
TD1-1066
Yue-Chao Chen
Jia-Jia Gao
Zhao-Hui Bin
Jia-Zhong Qian
Rui-Liang Pei
Hua Zhu
Application study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin
description Floods are often caused by short-term heavy rainfall. An Integrated Flood Analysis System (IFAS) model is good at runoff simulation and a Long Short-Term Memory (LSTM) model is good at learning massive data and realizing rainfall forecast. In this paper, the applicability of the IFAS model to runoff simulation in the Tokachi River basin and the LSTM model to forecast hourly rainfall was studied, and the accuracy of flood prediction was also studied by inputting the optimal rainfall data forecasted by the LSTM model into the IFAS model. The research results show that the IFAS model can accurately simulate the runoff process in the Tokachi River basin. In the calibration period and the verification period, the Nash–Sutcliffe Efficiency coefficient (NSE) of all simulation results are above 0.75; the LSTM model can achieve forecast hourly rainfall with high precision, the NSE of best forecast results is 0.86; the IFAS model can achieve flood prediction with high precision by using the optimal rainfall data forecasted by the LSTM model, the NSE of simulation result is 0.81. The above conclusions show that it is of great significance to combine the hourly rainfall forecasted by the LSTM model with the IFAS model for flood prediction. HIGHLIGHTS The Integrated Flood Analysis System (IFAS) model can accurately simulate runoff in the Tokachi River basin.; The Long Short-Term Memory (LSTM) model can achieve high-precision hourly rainfall forecast.; The combination of the optimal hourly rainfall predicted by the LSTM model and the calibrated IFAS model can achieve high-precision runoff simulation, which makes a beneficial exploration for the realization of flood forecasting.;
format article
author Yue-Chao Chen
Jia-Jia Gao
Zhao-Hui Bin
Jia-Zhong Qian
Rui-Liang Pei
Hua Zhu
author_facet Yue-Chao Chen
Jia-Jia Gao
Zhao-Hui Bin
Jia-Zhong Qian
Rui-Liang Pei
Hua Zhu
author_sort Yue-Chao Chen
title Application study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin
title_short Application study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin
title_full Application study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin
title_fullStr Application study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin
title_full_unstemmed Application study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin
title_sort application study of ifas and lstm models on runoff simulation and flood prediction in the tokachi river basin
publisher IWA Publishing
publishDate 2021
url https://doaj.org/article/d7a6a546d17a464dbe2282f9e8308b26
work_keys_str_mv AT yuechaochen applicationstudyofifasandlstmmodelsonrunoffsimulationandfloodpredictioninthetokachiriverbasin
AT jiajiagao applicationstudyofifasandlstmmodelsonrunoffsimulationandfloodpredictioninthetokachiriverbasin
AT zhaohuibin applicationstudyofifasandlstmmodelsonrunoffsimulationandfloodpredictioninthetokachiriverbasin
AT jiazhongqian applicationstudyofifasandlstmmodelsonrunoffsimulationandfloodpredictioninthetokachiriverbasin
AT ruiliangpei applicationstudyofifasandlstmmodelsonrunoffsimulationandfloodpredictioninthetokachiriverbasin
AT huazhu applicationstudyofifasandlstmmodelsonrunoffsimulationandfloodpredictioninthetokachiriverbasin
_version_ 1718444131103014912