Drought forecasting by ANN, ANFIS, and SVM and comparison of the models

Drought is a natural disaster that causes significant impact on all parts of environment and cause to reduction of the agricultural products. Other natural phenomena, for instance climate change, earthquake, storm, flood, and landslide, are also commonplace. In recent years, various techniques of artificial intelligence are used for drought prediction. The presented paper describes drought forecasting, which makes use of and compares the artificial neural network (ANN), adaptive neuro-fuzzy interface system (ANFIS), and support vector machine (SVM). The index that is used in this study is Standardized Precipitation Index (SPI). All of data from Bojnourd meteorological station (from January 1984 to December 2012) have been tested for 3-month time scales. The input parameters are as follows: temperature, humidity, and season precipitation, and the output parameter is SPI. This paper shows high accuracy of these models. The results indicated that the SVM model gives more accurate values for forecasting. On the other hand, we use the nonparametric inference to compare the proposal methods, and our results show that SVM model is more accurate than ANN and ANFIS.