RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia

Zaher Mundher Yaseen, Ahmed El-Shafie, Haitham Abdulmohsin Afan, Mohammed Hameed, Wan Hanna Melini Wan Mohtar, Aini Hussain

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Streamflow forecasting can have a significant economic impact, as this can help in water resources management and in providing protection from water scarcities and possible flood damage. Artificial neural network (ANN) had been successfully used as a tool to model various nonlinear relations, and the method is appropriate for modeling the complex nature of hydrological systems. They are relatively fast and flexible and are able to extract the relation between the inputs and outputs of a process without knowledge of the underlying physics. In this study, two types of ANN, namely feed-forward back-propagation neural network (FFNN) and radial basis function neural network (RBFNN), have been examined. Those models were developed for daily streamflow forecasting at Johor River, Malaysia, for the period (1999–2008). Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static neural networks. The results demonstrate that RBFNN model is superior to the FFNN forecasting model, and RBFNN can be successfully applied and provides high accuracy and reliability for daily streamflow forecasting.

Original languageEnglish
JournalNeural Computing and Applications
DOIs
Publication statusAccepted/In press - 28 Jun 2015

Fingerprint

Backpropagation
Rivers
Neural networks
Flood damage
Water resources
Physics
Economics
Water

Keywords

  • Artificial neural networks
  • FFNN
  • RBFNN
  • Streamflow forecasting

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia. / Yaseen, Zaher Mundher; El-Shafie, Ahmed; Afan, Haitham Abdulmohsin; Hameed, Mohammed; Wan Mohtar, Wan Hanna Melini; Hussain, Aini.

In: Neural Computing and Applications, 28.06.2015.

Research output: Contribution to journalArticle

Yaseen, Zaher Mundher ; El-Shafie, Ahmed ; Afan, Haitham Abdulmohsin ; Hameed, Mohammed ; Wan Mohtar, Wan Hanna Melini ; Hussain, Aini. / RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia. In: Neural Computing and Applications. 2015.
@article{0bbb32605ff34696aa439338d99e683b,
title = "RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia",
abstract = "Streamflow forecasting can have a significant economic impact, as this can help in water resources management and in providing protection from water scarcities and possible flood damage. Artificial neural network (ANN) had been successfully used as a tool to model various nonlinear relations, and the method is appropriate for modeling the complex nature of hydrological systems. They are relatively fast and flexible and are able to extract the relation between the inputs and outputs of a process without knowledge of the underlying physics. In this study, two types of ANN, namely feed-forward back-propagation neural network (FFNN) and radial basis function neural network (RBFNN), have been examined. Those models were developed for daily streamflow forecasting at Johor River, Malaysia, for the period (1999–2008). Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static neural networks. The results demonstrate that RBFNN model is superior to the FFNN forecasting model, and RBFNN can be successfully applied and provides high accuracy and reliability for daily streamflow forecasting.",
keywords = "Artificial neural networks, FFNN, RBFNN, Streamflow forecasting",
author = "Yaseen, {Zaher Mundher} and Ahmed El-Shafie and Afan, {Haitham Abdulmohsin} and Mohammed Hameed and {Wan Mohtar}, {Wan Hanna Melini} and Aini Hussain",
year = "2015",
month = "6",
day = "28",
doi = "10.1007/s00521-015-1952-6",
language = "English",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",

}

TY - JOUR

T1 - RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia

AU - Yaseen, Zaher Mundher

AU - El-Shafie, Ahmed

AU - Afan, Haitham Abdulmohsin

AU - Hameed, Mohammed

AU - Wan Mohtar, Wan Hanna Melini

AU - Hussain, Aini

PY - 2015/6/28

Y1 - 2015/6/28

N2 - Streamflow forecasting can have a significant economic impact, as this can help in water resources management and in providing protection from water scarcities and possible flood damage. Artificial neural network (ANN) had been successfully used as a tool to model various nonlinear relations, and the method is appropriate for modeling the complex nature of hydrological systems. They are relatively fast and flexible and are able to extract the relation between the inputs and outputs of a process without knowledge of the underlying physics. In this study, two types of ANN, namely feed-forward back-propagation neural network (FFNN) and radial basis function neural network (RBFNN), have been examined. Those models were developed for daily streamflow forecasting at Johor River, Malaysia, for the period (1999–2008). Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static neural networks. The results demonstrate that RBFNN model is superior to the FFNN forecasting model, and RBFNN can be successfully applied and provides high accuracy and reliability for daily streamflow forecasting.

AB - Streamflow forecasting can have a significant economic impact, as this can help in water resources management and in providing protection from water scarcities and possible flood damage. Artificial neural network (ANN) had been successfully used as a tool to model various nonlinear relations, and the method is appropriate for modeling the complex nature of hydrological systems. They are relatively fast and flexible and are able to extract the relation between the inputs and outputs of a process without knowledge of the underlying physics. In this study, two types of ANN, namely feed-forward back-propagation neural network (FFNN) and radial basis function neural network (RBFNN), have been examined. Those models were developed for daily streamflow forecasting at Johor River, Malaysia, for the period (1999–2008). Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static neural networks. The results demonstrate that RBFNN model is superior to the FFNN forecasting model, and RBFNN can be successfully applied and provides high accuracy and reliability for daily streamflow forecasting.

KW - Artificial neural networks

KW - FFNN

KW - RBFNN

KW - Streamflow forecasting

UR - http://www.scopus.com/inward/record.url?scp=84933545314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933545314&partnerID=8YFLogxK

U2 - 10.1007/s00521-015-1952-6

DO - 10.1007/s00521-015-1952-6

M3 - Article

AN - SCOPUS:84933545314

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

ER -