عنوان مقاله [English]
Potential evapotranspiration (ET0) rates are needed for irrigation scheduling. ET0 rates are commonly from weather parameters. The Penman-Monteith, is now accepted for computation of ET0. It requires several input parameters, some of which have no actual measurements but are estimated from measured weather parameters. In this study, the suitability of fuzzy regression was examined for estimating daily potential evapotranspiration with grass reference crop and compared with Artificial Neural Networks (ANN) and Penman-Monteith methods.The daily climatic data of the Ekbatan station in Hamadan, including maximum and minimum temperature, maximum and minimum relative humidity, wind speed and sunny hours are introduced as input data and ET0 as output data. ET0 values estimated from the fuzzy regression method were compared with direct ET0 measurements from lysimeters, and with ET0 estimations obtained using the Penman-Manteith equation and the ANN method. The estimated ET0 values from a fuzzy regression model using five input parameters, including maximum and minimum temperature, mean relative humidity, wind speed and sunny hours were obtained with RMSE=0.69mm/day, =0.88. The estimated ET0 values from a artificial neural networks model using the same input parameters were obtained with RMSE=0.74mm/day, =0.84. The estimated ET0 values from Penman-Monteith model were obtained with RMSE=1.21mm/day, =0.84. Thus, in this study the fuzzy regression is the best method.