Research on stage–discharge relationship model based on information entropy

In order to improve the estimation accuracy of stage–discharge relationship model, the back propagation neural network optimized through the genetic algorithm (GA-BP) based on information entropy was proposed. Firstly, the information entropy and hierarchical clustering were used to quickly cluster...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin Hao, Jiang Zhu, Liu Boxiang, Chen Ying
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	ga-bp hierarchical clustering information entropy k-nearest neighbor neural network stage–discharge relationship River, lake, and water-supply engineering (General) TC401-506
Acceso en línea:	https://doaj.org/article/650d1cb8798149e682e74137a5bdd52e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:650d1cb8798149e682e74137a5bdd52e
record_format	dspace
spelling	oai:doaj.org-article:650d1cb8798149e682e74137a5bdd52e2021-11-05T20:18:29ZResearch on stage–discharge relationship model based on information entropy1366-70171996-975910.2166/wp.2021.247https://doaj.org/article/650d1cb8798149e682e74137a5bdd52e2021-08-01T00:00:00Zhttp://wp.iwaponline.com/content/23/4/1075https://doaj.org/toc/1366-7017https://doaj.org/toc/1996-9759In order to improve the estimation accuracy of stage–discharge relationship model, the back propagation neural network optimized through the genetic algorithm (GA-BP) based on information entropy was proposed. Firstly, the information entropy and hierarchical clustering were used to quickly cluster the hydrological sample data and get the optimal number of clusters. Secondly, the k-nearest neighbor algorithm was used to divide the new stage data into the most appropriate clustering categories. Finally, the river daily discharge was estimated. Some measured data collected from a hydrological station were used to test the model, and the simulation results showed that the method proposed by this paper can get higher estimation accuracy than the classical analytical model, BP neural network algorithm and GA-BP neural network algorithm, which provided a new effective method for parameter estimation of the stage–discharge relationship model. HIGHLIGHTS A GA-BP algorithm based on information entropy is proposed.; Information entropy and hierarchical clustering were used to obtain the optimal number of clustering.; Through the model comparison, the GA-BP model based on information entropy has high accuracy.; This paper presented a new method for flow estimation.;Lin HaoJiang ZhuLiu BoxiangChen YingIWA Publishingarticlega-bphierarchical clusteringinformation entropyk-nearest neighborneural networkstage–discharge relationshipRiver, lake, and water-supply engineering (General)TC401-506ENWater Policy, Vol 23, Iss 4, Pp 1075-1088 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	ga-bp hierarchical clustering information entropy k-nearest neighbor neural network stage–discharge relationship River, lake, and water-supply engineering (General) TC401-506
spellingShingle	ga-bp hierarchical clustering information entropy k-nearest neighbor neural network stage–discharge relationship River, lake, and water-supply engineering (General) TC401-506 Lin Hao Jiang Zhu Liu Boxiang Chen Ying Research on stage–discharge relationship model based on information entropy
description	In order to improve the estimation accuracy of stage–discharge relationship model, the back propagation neural network optimized through the genetic algorithm (GA-BP) based on information entropy was proposed. Firstly, the information entropy and hierarchical clustering were used to quickly cluster the hydrological sample data and get the optimal number of clusters. Secondly, the k-nearest neighbor algorithm was used to divide the new stage data into the most appropriate clustering categories. Finally, the river daily discharge was estimated. Some measured data collected from a hydrological station were used to test the model, and the simulation results showed that the method proposed by this paper can get higher estimation accuracy than the classical analytical model, BP neural network algorithm and GA-BP neural network algorithm, which provided a new effective method for parameter estimation of the stage–discharge relationship model. HIGHLIGHTS A GA-BP algorithm based on information entropy is proposed.; Information entropy and hierarchical clustering were used to obtain the optimal number of clustering.; Through the model comparison, the GA-BP model based on information entropy has high accuracy.; This paper presented a new method for flow estimation.;
format	article
author	Lin Hao Jiang Zhu Liu Boxiang Chen Ying
author_facet	Lin Hao Jiang Zhu Liu Boxiang Chen Ying
author_sort	Lin Hao
title	Research on stage–discharge relationship model based on information entropy
title_short	Research on stage–discharge relationship model based on information entropy
title_full	Research on stage–discharge relationship model based on information entropy
title_fullStr	Research on stage–discharge relationship model based on information entropy
title_full_unstemmed	Research on stage–discharge relationship model based on information entropy
title_sort	research on stage–discharge relationship model based on information entropy
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/650d1cb8798149e682e74137a5bdd52e
work_keys_str_mv	AT linhao researchonstagedischargerelationshipmodelbasedoninformationentropy AT jiangzhu researchonstagedischargerelationshipmodelbasedoninformationentropy AT liuboxiang researchonstagedischargerelationshipmodelbasedoninformationentropy AT chenying researchonstagedischargerelationshipmodelbasedoninformationentropy
_version_	1718444042033823744

Research on stage–discharge relationship model based on information entropy

Ejemplares similares