Abstract

Evapotranspiration is an important parameter in hydrological and meteorological studies, and accurate estimation of evaporation is important for various purposes such as the development and management of water resources. In this study, daily reference evapotranspiration (ET0) is calculated by using Penman-Monteith equation, which is accepted as standard equation by FAO (Food and Agriculture Organization). ET0 is tried to be estimated by using Hargreaves-Samani and Turc traditional equations and results are compared with Artificial Neural Network (ANN) model performance. A station which is stated near to the Hartwell Lake (South Carolina, USA) was chosen as the study area. Average daily air temperature (T), highest (Tmax) and lowest daily air temperatures (Tmin), wind speed (U), solar radiation (SR) and relative humidity (RH) were used for daily average evapotranspiration estimation. Feed forward-back-propagation ANN method is used for model creation. Comparison between empirical equations and ANN model shows that ANN model performance for daily ET0 estimation is better than others.