Choosing the appropriate inputs for intelligent models is important. Because it can reduce costs and save time and increase accuracy and efficiency of the models. This work aims at the use of gamma test to select the optimum combination of input variables including delayed records of in time series modeling precipitation. Monthly time series of rainfall for the period 1383 to 1393 was used for Rasht station Rainfall data as with different lags were employed as input to gamma test. Results showed that time series with three delays (lags), provides better results. The simulation was performed using Bayesian network and multivariate linear regression. The performance of models was assessed using three criteria, i.e. coefficient of determination (R2), root mean square error (RMSE), and dispersion index (SI). Bayesian neural network using a three-month delay the coefficient of determination of 0.82, root mean square error of 17.84 and a diffusion index of 0.17 showed better performance as compared with multivariate regression. The results established the significant role of the gamma test integrated with intelligent models in the appropriate selection of input variables..
Mohammadi B, Ghorbani M A. Gamma test application in input preprocessing for time series modeling of rainfall. Journal of Rainwater Catchment Systems 2016; 4 (3) :61-72 URL: http://jircsa.ir/article-1-210-en.html
تکمیل و ارسال فرم تعارض منافع نویسنده گرامی ، پس از ارسال مقاله ، جهت دریافت فرم، لطفا بر روی کلمه فرم تعارض منافع کلیک نمایید و پس از تکمیل، در فایل های پیوست مقاله قرار دهید.