A New Approach of Expert System for Rainfall Prediction Based on Data Series

This paper proposed a new approach for rainfall prediction method, which combines the Support Vector Machine (SVM) and Fuzzy Logic methods.The performance of the proposed method is compared to the Neural Network (NN)???Fuzzy.The climatological data is obtained from PT LAPAN Bandung and the Meteorology, Climatology and Geophysics Region IV Makassar Indonesiafor 10 years (2001-2010) and is analysed by MATLAB 7.6.The results confirm that the SVM-Fuzzy achieves higher accuracy than NN-Fuzzy