Application of fuzzy modeling based on clustering via c-mean for estimation of pan evaporation (case study: Khuzestan Province)

In this paper by using fuzzy logic and c-mean clustering, different combinations of daily climatic variables including air temperature, relative humidity, wind speed and sunshine hours as input data for predicting pan evaporation were investigated. Therefore, meteorological parameters in years of 1386 and 87 at three synoptic stations (Ahvaz, Abadan and Izeh) in Khuzestan province were used. The results showed that the Takagi-Sugeno fuzzy model and c-mean clustering were able to predict pan evaporation, so that fuzzy models with cluster number of 2 and 3 estimated pan evaporation parameter by correlation coefficients varying from 0.86 to 0.91.