Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network

Developing water level forecasting models is essential in water resources management and flood prediction. Accurate water level forecasting helps achieve efficient and optimum use of water resources and minimize flooding damages. The artificial neural network (ANN) is a computing model that has been...

Full description

Bibliographic Details
Main Authors:	Muhammad @ S A Khushren, Sulaiman, Ahmed, El-Shafie, Othman, Karim, Hassan, Basri
Format:	Article
Language:	English
Published:	Springer 2011
Subjects:	T Technology (General) TA Engineering (General). Civil engineering (General)
Online Access:	http://umpir.ump.edu.my/id/eprint/13999/ http://umpir.ump.edu.my/id/eprint/13999/ http://umpir.ump.edu.my/id/eprint/13999/ http://umpir.ump.edu.my/id/eprint/13999/1/fkasa-2011-muhammad-Improved%20Water%20Level%20Forecasting%20Performance.pdf

id	ump-13999
recordtype	eprints
spelling	ump-139992016-10-19T06:28:52Z http://umpir.ump.edu.my/id/eprint/13999/ Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network Muhammad @ S A Khushren, Sulaiman Ahmed, El-Shafie Othman, Karim Hassan, Basri T Technology (General) TA Engineering (General). Civil engineering (General) Developing water level forecasting models is essential in water resources management and flood prediction. Accurate water level forecasting helps achieve efficient and optimum use of water resources and minimize flooding damages. The artificial neural network (ANN) is a computing model that has been successfully tested in many forecasting studies, including river flow. Improving the ANN computational approach could help produce accurate forecasting results. Most studies conducted to date have used a sigmoid function in a multi-layer perceptron neural network as the basis of the ANN; however, they have not considered the effect of sigmoid steepness on the forecasting results. In this study, the effectiveness of the steepness coefficient (SC) in the sigmoid function of an ANN model designed to testthe accuracyof1-day water levelforecastswasinvestigated. The performanceof data training and data validation were evaluated using the statistical index efficiency coefficient and root mean square error. The weight initialization was fixed at 0.5 in the ANN so that even comparisons could be made between models. Three hundred rounds of data training were conducted using five ANN architectures, six datasets and 10 steepness coefficients. The results showed that the optimal SC improved the forecasting accuracy of the ANN data training and data validation when compared with the standard SC. Importantly, the performance of ANN data training improved significantly with utilization of the optimal SC. Springer 2011-03-04 Article PeerReviewed application/pdf en http://umpir.ump.edu.my/id/eprint/13999/1/fkasa-2011-muhammad-Improved%20Water%20Level%20Forecasting%20Performance.pdf Muhammad @ S A Khushren, Sulaiman and Ahmed, El-Shafie and Othman, Karim and Hassan, Basri (2011) Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network. Water Resources Management, 25 (10). pp. 2525-2541. ISSN 0920-4741 (print); 1573-1650 (online) http://dx.doi.org/10.1007/s11269-011-9824-z DOI: 10.1007/s11269-011-9824-z
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Malaysia Pahang
building	UMP Institutional Repository
collection	Online Access
language	English
topic	T Technology (General) TA Engineering (General). Civil engineering (General)
spellingShingle	T Technology (General) TA Engineering (General). Civil engineering (General) Muhammad @ S A Khushren, Sulaiman Ahmed, El-Shafie Othman, Karim Hassan, Basri Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network
description	Developing water level forecasting models is essential in water resources management and flood prediction. Accurate water level forecasting helps achieve efficient and optimum use of water resources and minimize flooding damages. The artificial neural network (ANN) is a computing model that has been successfully tested in many forecasting studies, including river flow. Improving the ANN computational approach could help produce accurate forecasting results. Most studies conducted to date have used a sigmoid function in a multi-layer perceptron neural network as the basis of the ANN; however, they have not considered the effect of sigmoid steepness on the forecasting results. In this study, the effectiveness of the steepness coefficient (SC) in the sigmoid function of an ANN model designed to testthe accuracyof1-day water levelforecastswasinvestigated. The performanceof data training and data validation were evaluated using the statistical index efficiency coefficient and root mean square error. The weight initialization was fixed at 0.5 in the ANN so that even comparisons could be made between models. Three hundred rounds of data training were conducted using five ANN architectures, six datasets and 10 steepness coefficients. The results showed that the optimal SC improved the forecasting accuracy of the ANN data training and data validation when compared with the standard SC. Importantly, the performance of ANN data training improved significantly with utilization of the optimal SC.
format	Article
author	Muhammad @ S A Khushren, Sulaiman Ahmed, El-Shafie Othman, Karim Hassan, Basri
author_facet	Muhammad @ S A Khushren, Sulaiman Ahmed, El-Shafie Othman, Karim Hassan, Basri
author_sort	Muhammad @ S A Khushren, Sulaiman
title	Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network
title_short	Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network
title_full	Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network
title_fullStr	Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network
title_full_unstemmed	Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network
title_sort	improved water level forecasting performance by using optimal steepness coefficients in an artificial neural network
publisher	Springer
publishDate	2011
url	http://umpir.ump.edu.my/id/eprint/13999/ http://umpir.ump.edu.my/id/eprint/13999/ http://umpir.ump.edu.my/id/eprint/13999/ http://umpir.ump.edu.my/id/eprint/13999/1/fkasa-2011-muhammad-Improved%20Water%20Level%20Forecasting%20Performance.pdf
first_indexed	2023-09-18T22:17:14Z
last_indexed	2023-09-18T22:17:14Z
_version_	1777415419093581824

Improved Water Level Forecasting Performance by Using Optimal Steepness Coefficients in an Artificial Neural Network

Similar Items