Skip to content

A hybrid machine learning framework for real-time water level prediction in high sediment load reaches

Research output: Contribution to journalArticle

Standard

A hybrid machine learning framework for real-time water level prediction in high sediment load reaches. / Zhao, Gang; Pang, Bo; Xu, Zongxue; Xu, Liyang.

In: Journal of Hydrology, Vol. 581, 124422, 01.02.2020.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Zhao, Gang ; Pang, Bo ; Xu, Zongxue ; Xu, Liyang. / A hybrid machine learning framework for real-time water level prediction in high sediment load reaches. In: Journal of Hydrology. 2020 ; Vol. 581.

Bibtex

@article{1eec30830aa14f6187e56a729f8c9a84,
title = "A hybrid machine learning framework for real-time water level prediction in high sediment load reaches",
abstract = "Accurate prediction of water level is a challenging task in high sediment load reaches because of complicated flood-sediment routing mechanisms and fluctuating reach terrain. We propose a hybrid machine learning framework to predict the water level and validate the framework in five representative high sediment load reaches of the Lower Yellow River (LYR) in China. This framework can automatically generate ensemble prediction models for different flood-sediment scenarios by integrating clustering, classification, and regression models. We compared the proposed framework with two benchmark frameworks and evaluated performances using Nash–Sutcliffe efficiency (NSE) and Pearson correlation coefficient (PCC). The results demonstrated the following: (1) The water level cannot be accurately predicted (NSE < 0.50 in the testing period) using only upstream discharge and sediment load because of the fluctuating reach terrain. Model performance is significantly improved (NSE > 0.85) by adding the time factor in model development. (2) The proposed framework can successfully identify different flood-sediment combinations with a high classification accuracy of 98{\%} by adopting K-means clustering and support vector machine (SVM) classification models. (3) The proposed framework can provide reliable water level prediction for flood early warming in the LYR with an average NSE of 0.83 and 0.89 in the training and testing periods, respectively. It outperformed traditional single and rule-based model frameworks in all reaches with different degrees of improvement between 3{\%} and 13{\%}. The best performance indicated that the proposed framework can take advantages of different types of machine learning models and could provide reliable prediction for flood mitigation in high sediment load reaches.",
keywords = "China, High sediment load reaches, Lower Yellow River, Machine learning models, Water level prediction",
author = "Gang Zhao and Bo Pang and Zongxue Xu and Liyang Xu",
year = "2020",
month = "2",
day = "1",
doi = "10.1016/j.jhydrol.2019.124422",
language = "English",
volume = "581",
journal = "Journal of Hydrology",
issn = "0022-1694",
publisher = "Elsevier",

}

RIS - suitable for import to EndNote

TY - JOUR

T1 - A hybrid machine learning framework for real-time water level prediction in high sediment load reaches

AU - Zhao, Gang

AU - Pang, Bo

AU - Xu, Zongxue

AU - Xu, Liyang

PY - 2020/2/1

Y1 - 2020/2/1

N2 - Accurate prediction of water level is a challenging task in high sediment load reaches because of complicated flood-sediment routing mechanisms and fluctuating reach terrain. We propose a hybrid machine learning framework to predict the water level and validate the framework in five representative high sediment load reaches of the Lower Yellow River (LYR) in China. This framework can automatically generate ensemble prediction models for different flood-sediment scenarios by integrating clustering, classification, and regression models. We compared the proposed framework with two benchmark frameworks and evaluated performances using Nash–Sutcliffe efficiency (NSE) and Pearson correlation coefficient (PCC). The results demonstrated the following: (1) The water level cannot be accurately predicted (NSE < 0.50 in the testing period) using only upstream discharge and sediment load because of the fluctuating reach terrain. Model performance is significantly improved (NSE > 0.85) by adding the time factor in model development. (2) The proposed framework can successfully identify different flood-sediment combinations with a high classification accuracy of 98% by adopting K-means clustering and support vector machine (SVM) classification models. (3) The proposed framework can provide reliable water level prediction for flood early warming in the LYR with an average NSE of 0.83 and 0.89 in the training and testing periods, respectively. It outperformed traditional single and rule-based model frameworks in all reaches with different degrees of improvement between 3% and 13%. The best performance indicated that the proposed framework can take advantages of different types of machine learning models and could provide reliable prediction for flood mitigation in high sediment load reaches.

AB - Accurate prediction of water level is a challenging task in high sediment load reaches because of complicated flood-sediment routing mechanisms and fluctuating reach terrain. We propose a hybrid machine learning framework to predict the water level and validate the framework in five representative high sediment load reaches of the Lower Yellow River (LYR) in China. This framework can automatically generate ensemble prediction models for different flood-sediment scenarios by integrating clustering, classification, and regression models. We compared the proposed framework with two benchmark frameworks and evaluated performances using Nash–Sutcliffe efficiency (NSE) and Pearson correlation coefficient (PCC). The results demonstrated the following: (1) The water level cannot be accurately predicted (NSE < 0.50 in the testing period) using only upstream discharge and sediment load because of the fluctuating reach terrain. Model performance is significantly improved (NSE > 0.85) by adding the time factor in model development. (2) The proposed framework can successfully identify different flood-sediment combinations with a high classification accuracy of 98% by adopting K-means clustering and support vector machine (SVM) classification models. (3) The proposed framework can provide reliable water level prediction for flood early warming in the LYR with an average NSE of 0.83 and 0.89 in the training and testing periods, respectively. It outperformed traditional single and rule-based model frameworks in all reaches with different degrees of improvement between 3% and 13%. The best performance indicated that the proposed framework can take advantages of different types of machine learning models and could provide reliable prediction for flood mitigation in high sediment load reaches.

KW - China

KW - High sediment load reaches

KW - Lower Yellow River

KW - Machine learning models

KW - Water level prediction

UR - http://www.scopus.com/inward/record.url?scp=85076775938&partnerID=8YFLogxK

U2 - 10.1016/j.jhydrol.2019.124422

DO - 10.1016/j.jhydrol.2019.124422

M3 - Article

VL - 581

JO - Journal of Hydrology

JF - Journal of Hydrology

SN - 0022-1694

M1 - 124422

ER -