Flow simulation based on MISO and LSTM models in the Yangtze River-Dongting Lake System

Study region: The study region is the Yangtze River-Dongting Lake system, the largest regulated river-lake system in China. Study focus: Flow simulation of the Yangtze River–Dongting Lake system has long been recognized as a critical and challenging issue in the Yangtze River basin. Current approach...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenglong Li, Shenglian Guo, Zhen Cui, Xin Xiang
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of Hydrology: Regional Studies
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214581825002940
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060393692528640
author Chenglong Li
Shenglian Guo
Zhen Cui
Xin Xiang
author_facet Chenglong Li
Shenglian Guo
Zhen Cui
Xin Xiang
author_sort Chenglong Li
collection DOAJ
description Study region: The study region is the Yangtze River-Dongting Lake system, the largest regulated river-lake system in China. Study focus: Flow simulation of the Yangtze River–Dongting Lake system has long been recognized as a critical and challenging issue in the Yangtze River basin. Current approaches rely on traditional hydrological and hydrodynamic methods, but they face limitations such as difficulty obtaining required data set, complex modeling processes, long-time consumption, and insufficient accuracy. This study proposed the multi-input and single-output (MISO) model based on system dynamics principles and the long short-term memory (LSTM) neural network model based on deep learning for flow simulation in the Yangtze River-Dongting Lake system. New hydrological insights for the region: The proposed MISO and LSTM models can achieve accurate flow simulation results using only recorded flow data and rainfall data in the Yangtze River-Dongting Lake system. Both models demonstrate significantly higher computational efficiency than traditional hydrodynamic models, the MISO model can complete simulation within one second, while the LSTM model has the higher Nash-Sutcliffe efficiency coefficients and the smaller relative errors during the training and validation periods, the peak discharge relative errors (PRE) is ranging from −1.40–1.81 % across twelve flood events. This study has provided a novel approach for flow simulation in the complex river-lake system.
format Article
id doaj-art-ea4e503482564ec5a9ebd14370ece1b8
institution DOAJ
issn 2214-5818
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of Hydrology: Regional Studies
spelling doaj-art-ea4e503482564ec5a9ebd14370ece1b82025-08-20T02:50:33ZengElsevierJournal of Hydrology: Regional Studies2214-58182025-08-016010246910.1016/j.ejrh.2025.102469Flow simulation based on MISO and LSTM models in the Yangtze River-Dongting Lake SystemChenglong Li0Shenglian Guo1Zhen Cui2Xin Xiang3State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, ChinaCorresponding author.; State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, ChinaState Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, ChinaState Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, ChinaStudy region: The study region is the Yangtze River-Dongting Lake system, the largest regulated river-lake system in China. Study focus: Flow simulation of the Yangtze River–Dongting Lake system has long been recognized as a critical and challenging issue in the Yangtze River basin. Current approaches rely on traditional hydrological and hydrodynamic methods, but they face limitations such as difficulty obtaining required data set, complex modeling processes, long-time consumption, and insufficient accuracy. This study proposed the multi-input and single-output (MISO) model based on system dynamics principles and the long short-term memory (LSTM) neural network model based on deep learning for flow simulation in the Yangtze River-Dongting Lake system. New hydrological insights for the region: The proposed MISO and LSTM models can achieve accurate flow simulation results using only recorded flow data and rainfall data in the Yangtze River-Dongting Lake system. Both models demonstrate significantly higher computational efficiency than traditional hydrodynamic models, the MISO model can complete simulation within one second, while the LSTM model has the higher Nash-Sutcliffe efficiency coefficients and the smaller relative errors during the training and validation periods, the peak discharge relative errors (PRE) is ranging from −1.40–1.81 % across twelve flood events. This study has provided a novel approach for flow simulation in the complex river-lake system.http://www.sciencedirect.com/science/article/pii/S2214581825002940Flow simulationDeep learningSystem modelComplex river-lake systemYangtze RiverDongting Lake
spellingShingle Chenglong Li
Shenglian Guo
Zhen Cui
Xin Xiang
Flow simulation based on MISO and LSTM models in the Yangtze River-Dongting Lake System
Journal of Hydrology: Regional Studies
Flow simulation
Deep learning
System model
Complex river-lake system
Yangtze River
Dongting Lake
title Flow simulation based on MISO and LSTM models in the Yangtze River-Dongting Lake System
title_full Flow simulation based on MISO and LSTM models in the Yangtze River-Dongting Lake System
title_fullStr Flow simulation based on MISO and LSTM models in the Yangtze River-Dongting Lake System
title_full_unstemmed Flow simulation based on MISO and LSTM models in the Yangtze River-Dongting Lake System
title_short Flow simulation based on MISO and LSTM models in the Yangtze River-Dongting Lake System
title_sort flow simulation based on miso and lstm models in the yangtze river dongting lake system
topic Flow simulation
Deep learning
System model
Complex river-lake system
Yangtze River
Dongting Lake
url http://www.sciencedirect.com/science/article/pii/S2214581825002940
work_keys_str_mv AT chenglongli flowsimulationbasedonmisoandlstmmodelsintheyangtzeriverdongtinglakesystem
AT shenglianguo flowsimulationbasedonmisoandlstmmodelsintheyangtzeriverdongtinglakesystem
AT zhencui flowsimulationbasedonmisoandlstmmodelsintheyangtzeriverdongtinglakesystem
AT xinxiang flowsimulationbasedonmisoandlstmmodelsintheyangtzeriverdongtinglakesystem