UMP Institutional Repository

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

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

[img]
Preview
PDF
Real-time flood forecasting by employing.pdf
Available under License Creative Commons Attribution.

Download (2MB) | Preview

Abstract

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.

Item Type: Article
Uncontrolled Keywords: Real-time flood forecasting by employing artificial neural network based model with zoning matching approach
Subjects: G Geography. Anthropology. Recreation > GB Physical geography
T Technology > T Technology (General)
Faculty/Division: Faculty of Civil Engineering & Earth Resources
Depositing User: Mr. Mohd Safwan Rizal Saripudin
Date Deposited: 18 Oct 2016 02:27
Last Modified: 19 Oct 2016 06:28
URI: http://umpir.ump.edu.my/id/eprint/14001
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item