Daily rainfall modeling using Neural Network
| Autor: | M. Ohyver, Mohd. Khairul Bazli Mohd. Aziz, Syarifah Diana Permai |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Journal of Physics: Conference Series. 1988:012040 |
| ISSN: | 1742-6596 1742-6588 |
| DOI: | 10.1088/1742-6596/1988/1/012040 |
| Popis: | In the early 2020, Indonesia experienced flooding in several areas. This disaster caused a lot of damage and losses. One of the causes of flooding in Indonesia is due to high rainfall. This was not anticipated beforehand so there was a flood. Therefore, research on rainfall in Indonesia is very important to anticipate floods. If it is predicted that rainfall is very high and conditions do not allow it to accommodate, the government can prepare watersheds so that rainwater can flow and not be trapped. In this research, the rainfall data were obtained from Meteorological, Climatological, and Geophysical Agency (BMKG Indonesia), then the analysis of rainfall data in Indonesia was carried out. There are several statistical methods that can be used. There are ARIMA and Neural Network. In this research, the results of ARIMA model are used as input variables in the Neural Network model. Then there are several numbers of hidden layer in the Neural Network model that are compared. The results of ARIMA model and Neural Network model showed that Neural Network model is better than ARIMA model, because the mean square error (MSE) value of Neural Network model is smaller than ARIMA model. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|