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...
| Main Authors: | , , , |
|---|---|
| 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 |