Combination of Limited Meteorological Data for Predicting Reference Crop Evapotranspiration Using Artificial Neural Network Method

Reference crop evapotranspiration (ETo) is an important component of the hydrological cycle that used for water resource planning, irrigation, and agricultural management, as well in other processes. The aim this study was to estimate ETo based on limited meteorological data using artificial neural network (ANN) method. daily minimum temperature (Tmin), maximum (Tmax), mean (Tmean), solar radiation (SR), humidity (H), wind speed (WS), sunshine hours (Ssh), global (gradmax), (gradmin), day length, were obtained over long-term period from 1969 2019. analysed divided into two parts 2007 2008 2019 model training testing, respectively. optimal ANN forecasting included Tmax, Tmin, H, SR at hidden layers (4, 3); gradmin, SR, WS (6, 4); Ssh, Tmean (3, 2); all collected parameters layer (5, 4). results showed different alternative methods estimation case a lack climate with high performance. Models can help promote decision-making managers, designers, development planners.