Estimation of reference evapotranspiration using artificial neural network models for semi-arid region of Haryana

The study was conducted to evaluate performance of artificial neural network (ANN) models for estimating reference evapotranspiration (ET0) semi-arid region Haryana state. Ten years (2011-2020) daily weather data maximum and minimum temperature, relative humidity, wind speed sun shine hours collected from the meteorological observatory at CCS HAU, Hisar. Multilayer perceptron feed forward back propagation ANN were evaluated different training algorithms (10), number hidden layers (1-3) neurons in (1-30). Training compared heuristic techniques (GDA, GDX, RP), conjugate gradient (CGF, CGP, CGB, SCG), quasi-Newton (BFG, OSS) Levenberg-Marquardt (LM). Results against standard FAO Penman-Monteith method. revealed that best found with LM algorithm single layer 13 exhibiting RMSE, R, ME RPD values 0.306, 0.986, 0.976 6.63, respectively. showed good prediction evapotranspiration.