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:
Online Access:http://umpir.ump.edu.my/id/eprint/14001/1/Real-time%20flood%20forecasting%20by%20employing.pdf
_version_ 1825823085491650560
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
collection UMP
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.
first_indexed 2024-03-06T12:06:08Z
format Article
id UMPir14001
institution Universiti Malaysia Pahang
language English
last_indexed 2024-03-06T12:06:08Z
publishDate 2011
publisher European Geosciences Union
record_format dspace
spelling UMPir140012016-10-19T06:28:28Z 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. (Published) http://dx.doi.org/10.5194/hessd-8-9357-2011 DOI:10.5194/hessd-8-9357-2011
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
title 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_short 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
topic GB Physical geography
T Technology (General)
url http://umpir.ump.edu.my/id/eprint/14001/1/Real-time%20flood%20forecasting%20by%20employing.pdf
work_keys_str_mv AT muhammadsakhushrensulaiman realtimefoodforecastingbyemployingartificialneuralnetworkbasedmodelwithzoningmatchingapproach
AT ahmedelshafie realtimefoodforecastingbyemployingartificialneuralnetworkbasedmodelwithzoningmatchingapproach
AT othmankarim realtimefoodforecastingbyemployingartificialneuralnetworkbasedmodelwithzoningmatchingapproach
AT hassanbasri realtimefoodforecastingbyemployingartificialneuralnetworkbasedmodelwithzoningmatchingapproach