Prediction of Evapotranspiration by Artificial Neural Network and Conventional Methods

This study describes the conceptual framework and implementation to estimate the evapotranspiration by using computation technique artificial neural network. The objective of this study is to test an artificial neural network (ANN) to estimate reference evapotranspiration (ETo). Evapotranspiration is one of the main components of the hydrologic cycle. This complex process is dependent on climatic factors. There are many conventional methods to estimate evapotranspiration. Among them three methods that is Modified Penman Method, Thornthwaite method and Blaney-Criddle method equation perform the accurate results of estimating reference evapotranspiration (ETo) among the existing methods. However, the equation requires climatic data that are not always easily available. Artificial neural networks are one of the recent technique and studies for modeling complex systems and nonlinear features have shown very high ability. The major objective of this study is to estimate evapotranspiration using an artificial neural network (ANN) technique and to examine if a trained neural network with limited input variables can estimate evapotranspiration (ETo) efficiently.