عنوان مقاله [English]
In this study, the long-term rainfall in Babolsar city was simulated using an optimized hybrid artificial intelligence (AI) model over a 68 years period from 1951 to 2019. To develop the hybrid model, the ANFIS network and the wavelet transform were combined. Firstly, by using the autocorrelation function (ACF), the effective lags of time series data were identified. Subsequently, through these lags, six ANFIS models were defined. It is worth noticing that 49 years of the observational data are employed for training the AI models and the rest (19 years) for testing them. Moreover, by means of a trial-and-error method, the optimized numbers of membership function of the ANFIS network were chosen to be three. Then, different mother wavelets were evaluated, signifying that the dmey was introduced as the most accurate mother wavelet. By conducting a sensitivity analysis, the best ANFIS model was detected. The value of correlation coefficient (R), variance accounted for (VAF), and scatter index (SI) for testing the best ANFIS model were respectively computed to be 0.612, 37.029, and 0.761. Additionally, analysis of the models showed that the (t-1), (t-2), (t-12), and (t-36) were identified as the most significant lags. Lastly, the superior hybrid model was examined in three decomposition level (DL), revealing that the best results were obtained from the second decomposition level (DL2). In testing mode of the model, the R, VAF, and SI were calculated to be 0.972, 94.455, and 0.266, respectively. Therefore, the simulation results showed that the wavelet transform enhanced the performance of the ANFIS network significantly.