Artificial neural network–genetic algorithm for estimation of crop evapotranspiration in a semi-arid region of Iran

Abstract

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