An Investigation of Artificial Neural Network and Time Series Performance in the Index Standard Precipitation Drought Modeling (Case Study: Selected Stations of Khuzestan Province)

Drought is a natural phenomenon which may happen everywhere and cause remarkable damages to human and natural structures. In this study، two types of artificial Neural networks; multilayer perceptron، radial basis function، as well as time series models have been used to predict the standardized pereipitation drought index. To this end، the amount of standard precipitation index was calculated firstly in the selected stations of Khuzestan province in three، six، nine، and twelve months periods. Finally، the amount of standard precipitation index was predicted using the artificial Neural network and time series models. The results showed that the time series models have better performance in predicting the amount of standard precipitation index in all of the mentioned time periods in comparison to the artificial Neural network. In addition، the results indicated that the multilayer perceptron could better predict the amount of standard precipitation index in all periods comparing to the radial basis function.