Evaluation of the Efficiency of Linear and Nonlinear Models in Predicting Monthly Rainfall (Case Study: Hamedan Province)

In this research, we used the support vector machine (SVM), support vector machine combine with wavelet transform (W-SVM), ARMAX and ARIMA models to predict the monthly values of precipitation. The study considers monthly time series data for precipitation stations located in Hamedan province during a 25-year period (1998-2016). The 25-year simulation period was divided into 17 years for training, 4 years for calibration and 4 years for validation. Statistical comparison of the results was done by using correlation coefficient (r), root mean square error (RMSE), and standard error (SE). Results showed that ARIMA, Support Vector Machines, ARMAX and support vector machine combine with wavelet transform were ranked first to forth, respectively. Furthermore, the support vector machine has fewer adjustable parameters than other models. So, the model is able to predict precipitation with greater ease and less time. For this reason, it is preferable to other methods.