This paper investigates the prediction of pan evaporation using M5 Model Tree technique, evaluated for its applicability for predicting evaporation from meteorological data. Different combinations of input data were considered and the resulting values of evaporation were analysed and compared with those of existing techniques. The results suggest that the M5 Model could be successfully employed in estimating the evaporation from the available meteorological data set, within a scatter of ±15%, using the combination of air temperature, wind speed, sunshine hours and relative humidity) using M5 Model Tree algorithm. This study suggests the usefulness of M5 Model Tree technique with all the meteorological parameters considered together in predicting the pan evaporation from reservoirs.