Cover Image

Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake

A reliable water level prediction in a lake system is crucial for water resources management, flood control, etc. The objective of this study is to propose a machine learning model which is able to achieve a considerably high level of accuracy in terms of water level prediction. Dongting Lake, which...

Full description

Saved in:
Bibliographic Details
Main Authors: Deng, Bin, Liu, Pan, Chin, Ren Jie, Kumar, Pavitra, Jiang, Changbo, Xiang, Yifei, Liu, Yizhuang, Lai, Sai Hin, Luo, Hongmei
Format: Article
Published: Frontiers Media SA 2022
Subjects:
QE Geology
T Technology (General)
Online Access:http://eprints.um.edu.my/41159/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.41159
record_format eprints
spelling my.um.eprints.411592023-09-11T07:15:32Z http://eprints.um.edu.my/41159/ Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake Deng, Bin Liu, Pan Chin, Ren Jie Kumar, Pavitra Jiang, Changbo Xiang, Yifei Liu, Yizhuang Lai, Sai Hin Luo, Hongmei QE Geology T Technology (General) A reliable water level prediction in a lake system is crucial for water resources management, flood control, etc. The objective of this study is to propose a machine learning model which is able to achieve a considerably high level of accuracy in terms of water level prediction. Dongting Lake, which is the second-largest freshwater lake system in China, was selected as the study area. The hourly water level, flow rate, rainfall and temperature of the upstream water stations and rainfall of the downstream water stations were used as the input features, to predict the water level at the downstream stations. Multilayer perceptron neural network (MLP-NN), Elman neural network (ENN), and integration of particle swarm optimisation algorithm to Elman neural network (PSO-ENN) were selected as the model development techniques. The PSO-ENN model appears as the best performed model, as it records NSE of 0.929-0.988, RMSE of 0.129-0.322 and MAE of 0.151-0.359 at the downstream stations in Dongting Lake. The PSO-ENN model also shows its ability to provide better performance for the water level prediction of 36 h in advance. In terms of input variables sensitivity, the developed model is most sensitive to flow rate, followed by rainfall. Frontiers Media SA 2022-08 Article PeerReviewed Deng, Bin and Liu, Pan and Chin, Ren Jie and Kumar, Pavitra and Jiang, Changbo and Xiang, Yifei and Liu, Yizhuang and Lai, Sai Hin and Luo, Hongmei (2022) Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake. Frontiers in Earth Science, 10. ISSN 2296-6463, DOI https://doi.org/10.3389/feart.2022.928052 <https://doi.org/10.3389/feart.2022.928052>. 10.3389/feart.2022.928052
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic QE Geology
T Technology (General)
spellingShingle QE Geology
T Technology (General)
Deng, Bin
Liu, Pan
Chin, Ren Jie
Kumar, Pavitra
Jiang, Changbo
Xiang, Yifei
Liu, Yizhuang
Lai, Sai Hin
Luo, Hongmei
Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake
description A reliable water level prediction in a lake system is crucial for water resources management, flood control, etc. The objective of this study is to propose a machine learning model which is able to achieve a considerably high level of accuracy in terms of water level prediction. Dongting Lake, which is the second-largest freshwater lake system in China, was selected as the study area. The hourly water level, flow rate, rainfall and temperature of the upstream water stations and rainfall of the downstream water stations were used as the input features, to predict the water level at the downstream stations. Multilayer perceptron neural network (MLP-NN), Elman neural network (ENN), and integration of particle swarm optimisation algorithm to Elman neural network (PSO-ENN) were selected as the model development techniques. The PSO-ENN model appears as the best performed model, as it records NSE of 0.929-0.988, RMSE of 0.129-0.322 and MAE of 0.151-0.359 at the downstream stations in Dongting Lake. The PSO-ENN model also shows its ability to provide better performance for the water level prediction of 36 h in advance. In terms of input variables sensitivity, the developed model is most sensitive to flow rate, followed by rainfall.
format Article
author Deng, Bin
Liu, Pan
Chin, Ren Jie
Kumar, Pavitra
Jiang, Changbo
Xiang, Yifei
Liu, Yizhuang
Lai, Sai Hin
Luo, Hongmei
author_facet Deng, Bin
Liu, Pan
Chin, Ren Jie
Kumar, Pavitra
Jiang, Changbo
Xiang, Yifei
Liu, Yizhuang
Lai, Sai Hin
Luo, Hongmei
author_sort Deng, Bin
title Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake
title_short Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake
title_full Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake
title_fullStr Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake
title_full_unstemmed Hybrid metaheuristic machine learning approach for water level prediction: A case study in Dongting Lake
title_sort hybrid metaheuristic machine learning approach for water level prediction: a case study in dongting lake
publisher Frontiers Media SA
publishDate 2022
url http://eprints.um.edu.my/41159/
_version_ 1778161634058960896
score 13.211869

Similar Items