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

• Published in: Neural computing & applications Vol. 23; no. 5; pp. 1387 - 1393
• Main Authors: Aghajanloo, Mohammad-Bagher, Sabziparvar, Ali-Akbar, Hosseinzadeh Talaee, P.
• Format: Journal Article
• Language: English
• Published: London Springer London 01.10.2013; Springer
• Subjects: Applied sciences; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer science; control theory; systems; Connectionism. Neural networks; Data Mining and Knowledge Discovery; Exact sciences and technology; Image Processing and Computer Vision; Original Article; Probability and Statistics in Computer Science; Penman–Monteith FAO 56 model; Neural network–genetic algorithm; Nonlinear regression; Cold semi-arid climate; Climate; Atmospheric pressure; Non linear regression; Neural network―genetic algorithm; Regression analysis; Neural network; Penman-Monteith FAO 56 model; Multivariate analysis; Gene expression; Modeling; Optimization; Statistical test; Genetic algorithm; Humidity; Solar radiation; Meteorology
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-012-1087-y

This study compares the daily potato crop evapotranspiration (ET C ) 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 ET C 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 ET C at desirable level of accuracy. However, the MNLR method with highest coefficient of determination ( R 2  > 0.96, P value < 0.05) and minimum errors provided superior performance among the other methods.