Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China

Reliable flood forecasting can provide a scientific basis for flood risk assessment and water resources management, and the Taihu water level forecasting with high precision is essential for flood control in the Taihu Basin. To increase the prediction accuracy, a coupling model (DWT-iNARX) is establ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Feiqing Jiang, Zengchuan Dong, Zeng'an Wang, Yiqing Zhu, Moyang Liu, Yun Luo, Tianyan Zhang
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	discrete wavelet transformation improved narx network monte carlo simulations probabilistic forecast taihu lake water level prediction Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/269ea5781c8a47049395b0ffac938aa9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:269ea5781c8a47049395b0ffac938aa9
record_format	dspace
spelling	oai:doaj.org-article:269ea5781c8a47049395b0ffac938aa92021-11-05T19:07:56ZFlood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China2040-22442408-935410.2166/wcc.2021.019https://doaj.org/article/269ea5781c8a47049395b0ffac938aa92021-09-01T00:00:00Zhttp://jwcc.iwaponline.com/content/12/6/2674https://doaj.org/toc/2040-2244https://doaj.org/toc/2408-9354Reliable flood forecasting can provide a scientific basis for flood risk assessment and water resources management, and the Taihu water level forecasting with high precision is essential for flood control in the Taihu Basin. To increase the prediction accuracy, a coupling model (DWT-iNARX) is established by combining the discrete wavelet transformation (DWT) with improved nonlinear autoregressive with exogenous inputs network (iNARX), for predicting the daily Taihu water level during the flood season under different forecast periods. And the DWT-iNARX model is compared with the back-propagation neural network (BP) and iNARX models to assess its capability in prediction. Meanwhile, we propose an uncertainty analysis method based on Monte Carlo simulations (MCS) for quantifying model uncertainty and performing probabilistic water level forecast. The results show that three models achieve good simulation results with higher accuracy when the forecast period is short, such as 1–3 days. In overall performance, iNARX and DWT-iNARX models show superiority in comparison with the BP model, while the DWT-iNARX model yields the best performance among all the other models. The research results can provide a certain reference for the water level forecast of the Taihu Lake. HIGHLIGHTS This study investigates a new data-mining-based model, which incorporates the discrete wavelet transformation and improved nonlinear autoregressive with exogenous inputs network, for flood forecasting in different forecast periods.; This study proposes an uncertainty analysis method framework based on Monte Carlo simulations for quantifying model uncertainty and performing probabilistic water level forecast.;Feiqing JiangZengchuan DongZeng'an WangYiqing ZhuMoyang LiuYun LuoTianyan ZhangIWA Publishingarticlediscrete wavelet transformationimproved narx networkmonte carlo simulationsprobabilistic forecasttaihu lakewater level predictionEnvironmental technology. Sanitary engineeringTD1-1066Environmental sciencesGE1-350ENJournal of Water and Climate Change, Vol 12, Iss 6, Pp 2674-2696 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	discrete wavelet transformation improved narx network monte carlo simulations probabilistic forecast taihu lake water level prediction Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350
spellingShingle	discrete wavelet transformation improved narx network monte carlo simulations probabilistic forecast taihu lake water level prediction Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350 Feiqing Jiang Zengchuan Dong Zeng'an Wang Yiqing Zhu Moyang Liu Yun Luo Tianyan Zhang Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China
description	Reliable flood forecasting can provide a scientific basis for flood risk assessment and water resources management, and the Taihu water level forecasting with high precision is essential for flood control in the Taihu Basin. To increase the prediction accuracy, a coupling model (DWT-iNARX) is established by combining the discrete wavelet transformation (DWT) with improved nonlinear autoregressive with exogenous inputs network (iNARX), for predicting the daily Taihu water level during the flood season under different forecast periods. And the DWT-iNARX model is compared with the back-propagation neural network (BP) and iNARX models to assess its capability in prediction. Meanwhile, we propose an uncertainty analysis method based on Monte Carlo simulations (MCS) for quantifying model uncertainty and performing probabilistic water level forecast. The results show that three models achieve good simulation results with higher accuracy when the forecast period is short, such as 1–3 days. In overall performance, iNARX and DWT-iNARX models show superiority in comparison with the BP model, while the DWT-iNARX model yields the best performance among all the other models. The research results can provide a certain reference for the water level forecast of the Taihu Lake. HIGHLIGHTS This study investigates a new data-mining-based model, which incorporates the discrete wavelet transformation and improved nonlinear autoregressive with exogenous inputs network, for flood forecasting in different forecast periods.; This study proposes an uncertainty analysis method framework based on Monte Carlo simulations for quantifying model uncertainty and performing probabilistic water level forecast.;
format	article
author	Feiqing Jiang Zengchuan Dong Zeng'an Wang Yiqing Zhu Moyang Liu Yun Luo Tianyan Zhang
author_facet	Feiqing Jiang Zengchuan Dong Zeng'an Wang Yiqing Zhu Moyang Liu Yun Luo Tianyan Zhang
author_sort	Feiqing Jiang
title	Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China
title_short	Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China
title_full	Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China
title_fullStr	Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China
title_full_unstemmed	Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China
title_sort	flood forecasting using an improved narx network based on wavelet analysis coupled with uncertainty analysis by monte carlo simulations: a case study of taihu basin, china
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/269ea5781c8a47049395b0ffac938aa9
work_keys_str_mv	AT feiqingjiang floodforecastingusinganimprovednarxnetworkbasedonwaveletanalysiscoupledwithuncertaintyanalysisbymontecarlosimulationsacasestudyoftaihubasinchina AT zengchuandong floodforecastingusinganimprovednarxnetworkbasedonwaveletanalysiscoupledwithuncertaintyanalysisbymontecarlosimulationsacasestudyoftaihubasinchina AT zenganwang floodforecastingusinganimprovednarxnetworkbasedonwaveletanalysiscoupledwithuncertaintyanalysisbymontecarlosimulationsacasestudyoftaihubasinchina AT yiqingzhu floodforecastingusinganimprovednarxnetworkbasedonwaveletanalysiscoupledwithuncertaintyanalysisbymontecarlosimulationsacasestudyoftaihubasinchina AT moyangliu floodforecastingusinganimprovednarxnetworkbasedonwaveletanalysiscoupledwithuncertaintyanalysisbymontecarlosimulationsacasestudyoftaihubasinchina AT yunluo floodforecastingusinganimprovednarxnetworkbasedonwaveletanalysiscoupledwithuncertaintyanalysisbymontecarlosimulationsacasestudyoftaihubasinchina AT tianyanzhang floodforecastingusinganimprovednarxnetworkbasedonwaveletanalysiscoupledwithuncertaintyanalysisbymontecarlosimulationsacasestudyoftaihubasinchina
_version_	1718444026207666176

Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China

Ejemplares similares