This study compares the daily crop evapotranspiration estimated by artificial neural network (ANN), neural network-genetic algorithm (NNG), and nonlinear regression (NLR) methods. Using a 6-year (2000-2005) daily meteorological data, recorded at Tabriz synoptic station, and Penman-Monteith FAO 56 standard approach (PMF 56), the daily crop evapotranspiration (ETC) was determined during the growing season (April-September). Air temperature, wind speed at 2 meters height, net solar radiation, air pressure, relative humidity and crop coefficient for every day of the growing season were selected as the input of artificial neural network models. In this study, the genetic algorithm was applied for optimization of parameters which used in ANN approach. It was found that the optimization of input parameters did not improve the performance of ANN method. The results indicate that NLR, ANN and NNG methods were able to predict potato crop evapotranspiration (ETC) at the desirable level of accuracy. However, the NLR method with highest coefficient of determination (R2> 0.96, P value<0.05) and minimum errors provided the superior performance among the other methods.
