Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach

Flood forecasting models are a necessity, as they help in planning for ﬂood events, and thus help prevent loss of lives and minimize damage. At present, artiﬁcial neural networks(ANN)havebeensuccessfullyappliedinriverﬂowandwaterlevelforecasting studies. ANN requires historical data to develop a fore...

Full description

Bibliographic Details
Main Authors:	Muhammad @ S A Khushren, Sulaiman, Ahmed, El-Shafie, Othman, Karim, Hassan, Basri
Format:	Article
Language:	English
Published:	European Geosciences Union 2011
Subjects:	GB Physical geography T Technology (General)
Online Access:	http://umpir.ump.edu.my/id/eprint/14001/ http://umpir.ump.edu.my/id/eprint/14001/ http://umpir.ump.edu.my/id/eprint/14001/ http://umpir.ump.edu.my/id/eprint/14001/1/Real-time%20flood%20forecasting%20by%20employing.pdf

id	ump-14001
recordtype	eprints
spelling	ump-140012016-10-19T06:28:28Z http://umpir.ump.edu.my/id/eprint/14001/ Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach Muhammad @ S A Khushren, Sulaiman Ahmed, El-Shafie Othman, Karim Hassan, Basri GB Physical geography T Technology (General) Flood forecasting models are a necessity, as they help in planning for ﬂood events, and thus help prevent loss of lives and minimize damage. At present, artiﬁcial neural networks(ANN)havebeensuccessfullyappliedinriverﬂowandwaterlevelforecasting studies. ANN requires historical data to develop a forecasting model. However, long-5 termhistoricalwaterleveldata, suchashourlydata, posestwocrucialproblemsindata training. First is that the high volume of data slows the computation process. Second is that data training reaches its optimal performance within a few cycles of data training, due to there being a high volume of normal water level data in the data training, while the forecasting performance for high water level events is still poor. In this study, the10 zoning matching approach (ZMA) is used in ANN to accurately monitor ﬂood events in real time by focusing the development of the forecasting model on high water level zones. ZMA is a trial and error approach, where several training datasets using high water level data are tested to ﬁnd the best training dataset for forecasting high water level events. The advantage of ZMA is that relevant knowledge of water level patterns15 in historical records is used. Importantly, the forecasting model developed based on ZMA successfully achieves high accuracy forecasting results at 1 to 3h ahead and satisfactory performance results at 6h. Seven performance measures are adopted in this study to describe the accuracy and reliability of the forecasting model developed. European Geosciences Union 2011-10-13 Article PeerReviewed application/pdf en cc_by http://umpir.ump.edu.my/id/eprint/14001/1/Real-time%20flood%20forecasting%20by%20employing.pdf Muhammad @ S A Khushren, Sulaiman and Ahmed, El-Shafie and Othman, Karim and Hassan, Basri (2011) Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach. Hydrology and Earth System Sciences, 8. pp. 9357-9393. ISSN 1027-5606 http://dx.doi.org/10.5194/hessd-8-9357-2011 DOI:10.5194/hessd-8-9357-2011
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Malaysia Pahang
building	UMP Institutional Repository
collection	Online Access
language	English
topic	GB Physical geography T Technology (General)
spellingShingle	GB Physical geography T Technology (General) Muhammad @ S A Khushren, Sulaiman Ahmed, El-Shafie Othman, Karim Hassan, Basri Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach
description	Flood forecasting models are a necessity, as they help in planning for ﬂood events, and thus help prevent loss of lives and minimize damage. At present, artiﬁcial neural networks(ANN)havebeensuccessfullyappliedinriverﬂowandwaterlevelforecasting studies. ANN requires historical data to develop a forecasting model. However, long-5 termhistoricalwaterleveldata, suchashourlydata, posestwocrucialproblemsindata training. First is that the high volume of data slows the computation process. Second is that data training reaches its optimal performance within a few cycles of data training, due to there being a high volume of normal water level data in the data training, while the forecasting performance for high water level events is still poor. In this study, the10 zoning matching approach (ZMA) is used in ANN to accurately monitor ﬂood events in real time by focusing the development of the forecasting model on high water level zones. ZMA is a trial and error approach, where several training datasets using high water level data are tested to ﬁnd the best training dataset for forecasting high water level events. The advantage of ZMA is that relevant knowledge of water level patterns15 in historical records is used. Importantly, the forecasting model developed based on ZMA successfully achieves high accuracy forecasting results at 1 to 3h ahead and satisfactory performance results at 6h. Seven performance measures are adopted in this study to describe the accuracy and reliability of the forecasting model developed.
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	Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach
title_short	Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach
title_full	Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach
title_fullStr	Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach
title_full_unstemmed	Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach
title_sort	real-time food forecasting by employing artiﬁcial neural network based model with zoning matching approach
publisher	European Geosciences Union
publishDate	2011
url	http://umpir.ump.edu.my/id/eprint/14001/ http://umpir.ump.edu.my/id/eprint/14001/ http://umpir.ump.edu.my/id/eprint/14001/ http://umpir.ump.edu.my/id/eprint/14001/1/Real-time%20flood%20forecasting%20by%20employing.pdf
first_indexed	2023-09-18T22:17:15Z
last_indexed	2023-09-18T22:17:15Z
_version_	1777415419394523136

Real-Time Food Forecasting by Employing Artiﬁcial Neural Network based Model with Zoning Matching Approach

Similar Items