Neural networks for forecasting daily reservoir inflows
Proper integrated management of a dam reservoir requires that all components of the water resource system be known. One of these components is the daily reservoir inflow which is the subject matter of this study, i.e. to establish predictions of what is coming in the next rainfall-runoff process ove...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Putra Malaysia Press
2010
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/9612/1/neural.pdf |
| _version_ | 1796967774015193088 |
|---|---|
| author | Karimi-Googhari, Shahram Huang, Yuk Feng Ghazali, Abdul Halim Lee, Teang Shui |
| author_facet | Karimi-Googhari, Shahram Huang, Yuk Feng Ghazali, Abdul Halim Lee, Teang Shui |
| author_sort | Karimi-Googhari, Shahram |
| collection | UPM |
| description | Proper integrated management of a dam reservoir requires that all components of the water resource system be known. One of these components is the daily reservoir inflow which is the subject matter of this study, i.e. to establish predictions of what is coming in the next rainfall-runoff process over a catchment. The transformation of rainfall into runoff is an extremely complex, dynamic, and more of a non-linear process. The available six-year average daily rainfall data across the Sembrong dam catchment were computed using the well-known Theissen’s polygon method. Daily reservoir inflow data were extracted by applying the water balance model to the Sembrong dam reservoir. Modelling of relationship between rainfall and reservoir inflow data was done using feed-forward back-propagation neural networks. The final selected model has one hidden layer with 11 neurons in the hidden layer. The selected model was applied for an independent data series testing. Results in relation to specific climatic and hydrologic properties of a small tropical catchment suggested that the model is suitable to be used in forecasting the next day’s reservoir inflow. The efficiencies of the model Abtained indicated the validity of using the neural network for modelling reservoir inflow series. |
| first_indexed | 2024-03-06T07:18:45Z |
| format | Article |
| id | upm.eprints-9612 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T07:18:45Z |
| publishDate | 2010 |
| publisher | Universiti Putra Malaysia Press |
| record_format | dspace |
| spelling | upm.eprints-96122016-01-05T04:43:05Z http://psasir.upm.edu.my/id/eprint/9612/ Neural networks for forecasting daily reservoir inflows Karimi-Googhari, Shahram Huang, Yuk Feng Ghazali, Abdul Halim Lee, Teang Shui Proper integrated management of a dam reservoir requires that all components of the water resource system be known. One of these components is the daily reservoir inflow which is the subject matter of this study, i.e. to establish predictions of what is coming in the next rainfall-runoff process over a catchment. The transformation of rainfall into runoff is an extremely complex, dynamic, and more of a non-linear process. The available six-year average daily rainfall data across the Sembrong dam catchment were computed using the well-known Theissen’s polygon method. Daily reservoir inflow data were extracted by applying the water balance model to the Sembrong dam reservoir. Modelling of relationship between rainfall and reservoir inflow data was done using feed-forward back-propagation neural networks. The final selected model has one hidden layer with 11 neurons in the hidden layer. The selected model was applied for an independent data series testing. Results in relation to specific climatic and hydrologic properties of a small tropical catchment suggested that the model is suitable to be used in forecasting the next day’s reservoir inflow. The efficiencies of the model Abtained indicated the validity of using the neural network for modelling reservoir inflow series. Universiti Putra Malaysia Press 2010-01 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/9612/1/neural.pdf Karimi-Googhari, Shahram and Huang, Yuk Feng and Ghazali, Abdul Halim and Lee, Teang Shui (2010) Neural networks for forecasting daily reservoir inflows. Pertanika Journal of Science & Technology, 18 (1). pp. 33-41. ISSN 0128-7680; ESSN: 2231-8526 |
| spellingShingle | Karimi-Googhari, Shahram Huang, Yuk Feng Ghazali, Abdul Halim Lee, Teang Shui Neural networks for forecasting daily reservoir inflows |
| title | Neural networks for forecasting daily reservoir inflows |
| title_full | Neural networks for forecasting daily reservoir inflows |
| title_fullStr | Neural networks for forecasting daily reservoir inflows |
| title_full_unstemmed | Neural networks for forecasting daily reservoir inflows |
| title_short | Neural networks for forecasting daily reservoir inflows |
| title_sort | neural networks for forecasting daily reservoir inflows |
| url | http://psasir.upm.edu.my/id/eprint/9612/1/neural.pdf |
| work_keys_str_mv | AT karimigoogharishahram neuralnetworksforforecastingdailyreservoirinflows AT huangyukfeng neuralnetworksforforecastingdailyreservoirinflows AT ghazaliabdulhalim neuralnetworksforforecastingdailyreservoirinflows AT leeteangshui neuralnetworksforforecastingdailyreservoirinflows |