| Autor: |
Benrhmach, Ghassane, Namir, Khalil, Bouyaghroumni, Jamal, Namir, Abdelwahed |
| Zdroj: |
Mathematical Models & Computer Simulations; Oct2022, Vol. 14 Issue 5, p837-846, 10p |
| Abstrakt: |
Rainfall prediction is one of the most important tools for water management, prompting scientists to develop several techniques in recent years to analyze and predict rainfall. The nature of rainfall data affects the accuracy of the prediction. This paper presents a method for rainfall prediction in two African cities, Meknes located in Morocco and Cape Town in South Africa. The prediction of rainfall in these two cities is presented using a hybrid model, which combines the wavelet decomposition and artificial neural network using two different approaches (WANN-1 and WANN-2). Three other models (ARIMA, Holt–Winter, artificial neural network) were applied to the daily rainfall in the cities of Meknes and Cape Town. The simulation results using MATLAB and R software show that the proposed model is more effective than other used models. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink