Deep learning-based forecast and warning of floods in Klang River, Malaysia
Long short-term memory (LSTM) networks are state of the art technique for time-series sequence learning. They are less commonly applied to the hydrological engineering area especially for river water level time-series data for flood warning and forecasting systems. This paper examines an LSTM networ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Published: |
International Information and Engineering Technology Association
2020
|
| Subjects: |
| _version_ | 1796865131289772032 |
|---|---|
| author | Faruq, Amrul Arsa, Hudan Pandu Mohd. Hussein, Shamsul Faisal Che Razali, Che Munira Marto, Aminaton Abdullah, Shahrum Shah |
| author_facet | Faruq, Amrul Arsa, Hudan Pandu Mohd. Hussein, Shamsul Faisal Che Razali, Che Munira Marto, Aminaton Abdullah, Shahrum Shah |
| author_sort | Faruq, Amrul |
| collection | ePrints |
| description | Long short-term memory (LSTM) networks are state of the art technique for time-series sequence learning. They are less commonly applied to the hydrological engineering area especially for river water level time-series data for flood warning and forecasting systems. This paper examines an LSTM network for forecasting the river water level in Klang river basin, Malaysia. The river water level contains of two features dimension and one time-series observed data, in this study, prediction responses for river water level data using a trained recurrent neural network and update the network state function is applied. The radial basis function neural network (RBFNN) in order to get comparison of the generalization solving problem also performed. The performance indicates with the root mean square error, RMSE 0.0253 and coefficient of determination value, R2 0.9815 are closely accurate when updating the network state compared with the RBFNN results. These results verified that the LSTM network with specified training set options is a promising alternative technique to the solution of flood modelling and forecasting problems. |
| first_indexed | 2024-03-05T20:52:17Z |
| format | Article |
| id | utm.eprints-90949 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T20:52:17Z |
| publishDate | 2020 |
| publisher | International Information and Engineering Technology Association |
| record_format | dspace |
| spelling | utm.eprints-909492021-05-31T13:28:44Z http://eprints.utm.my/90949/ Deep learning-based forecast and warning of floods in Klang River, Malaysia Faruq, Amrul Arsa, Hudan Pandu Mohd. Hussein, Shamsul Faisal Che Razali, Che Munira Marto, Aminaton Abdullah, Shahrum Shah T Technology (General) Long short-term memory (LSTM) networks are state of the art technique for time-series sequence learning. They are less commonly applied to the hydrological engineering area especially for river water level time-series data for flood warning and forecasting systems. This paper examines an LSTM network for forecasting the river water level in Klang river basin, Malaysia. The river water level contains of two features dimension and one time-series observed data, in this study, prediction responses for river water level data using a trained recurrent neural network and update the network state function is applied. The radial basis function neural network (RBFNN) in order to get comparison of the generalization solving problem also performed. The performance indicates with the root mean square error, RMSE 0.0253 and coefficient of determination value, R2 0.9815 are closely accurate when updating the network state compared with the RBFNN results. These results verified that the LSTM network with specified training set options is a promising alternative technique to the solution of flood modelling and forecasting problems. International Information and Engineering Technology Association 2020-06 Article PeerReviewed Faruq, Amrul and Arsa, Hudan Pandu and Mohd. Hussein, Shamsul Faisal and Che Razali, Che Munira and Marto, Aminaton and Abdullah, Shahrum Shah (2020) Deep learning-based forecast and warning of floods in Klang River, Malaysia. Ingenierie des Systemes d'Information, 25 (3). pp. 365-370. ISSN 0163-3131 http://dx.doi.org/10.18280/isi.250311 |
| spellingShingle | T Technology (General) Faruq, Amrul Arsa, Hudan Pandu Mohd. Hussein, Shamsul Faisal Che Razali, Che Munira Marto, Aminaton Abdullah, Shahrum Shah Deep learning-based forecast and warning of floods in Klang River, Malaysia |
| title | Deep learning-based forecast and warning of floods in Klang River, Malaysia |
| title_full | Deep learning-based forecast and warning of floods in Klang River, Malaysia |
| title_fullStr | Deep learning-based forecast and warning of floods in Klang River, Malaysia |
| title_full_unstemmed | Deep learning-based forecast and warning of floods in Klang River, Malaysia |
| title_short | Deep learning-based forecast and warning of floods in Klang River, Malaysia |
| title_sort | deep learning based forecast and warning of floods in klang river malaysia |
| topic | T Technology (General) |
| work_keys_str_mv | AT faruqamrul deeplearningbasedforecastandwarningoffloodsinklangrivermalaysia AT arsahudanpandu deeplearningbasedforecastandwarningoffloodsinklangrivermalaysia AT mohdhusseinshamsulfaisal deeplearningbasedforecastandwarningoffloodsinklangrivermalaysia AT cherazalichemunira deeplearningbasedforecastandwarningoffloodsinklangrivermalaysia AT martoaminaton deeplearningbasedforecastandwarningoffloodsinklangrivermalaysia AT abdullahshahrumshah deeplearningbasedforecastandwarningoffloodsinklangrivermalaysia |