Publication: Recurrent Neural Network (RNN) for stream flow forecasting
| dc.contributor.author | Alkatheri Ali Karama Gumaan | en_US |
| dc.date.accessioned | 2023-05-03T16:59:14Z | |
| dc.date.available | 2023-05-03T16:59:14Z | |
| dc.date.issued | 2020-02 | |
| dc.description | FYP Sem 2 2019/2020 | en_US |
| dc.description.abstract | The increase in stream flow is an important issue since it can be used as a flood warning indicator. The stream flow of a river depends on variables such as rainfall, runoff and surface wind. The primary objective of this study is to find a reliable method to predict the stream flow of the Kuantan River in Malaysia. In this study, applied using two different input which are daily stream flow and daily rainfall. In this study, the data of the stream flow and rainfall were obtained for a duration of nine years and . Two models were used in this study were used to analyze the data, which are Long Short Term Memory (LSTM) and Artificial Neural Networks (ANN) models. The result demonstrates that the Long Short Term Memory is superior to Artificial Neural Networks by achieving correlation coefficient (R) value of 0.851 compared to 0.802 respectively. Also, the results showed that regressions of both models achieved a good value of R and lower error values. The main finding from this study is that the Long Short Term Memory to predict the stream flow is little better than the Artificial Neural Networks. | en_US |
| dc.identifier.uri | https://irepository.uniten.edu.my/handle/123456789/21467 | |
| dc.subject | Stream Flow | en_US |
| dc.subject | Forecast | en_US |
| dc.subject | Artificial Neural Networks (ANN) | en_US |
| dc.subject | Long Short Term Memory (LSTM) | en_US |
| dc.title | Recurrent Neural Network (RNN) for stream flow forecasting | |
| dc.type | Resource Types::text::Final Year Project | |
| dspace.entity.type | Publication |