Estimating Penman-Monteith Reference Evapotranspiration Using Artificial Neural Networks and Genetic Algorithm: A Case Study

摘要

The Penman-Monteith equation (PM) is widely recommended because of its detailed and comprehensive theoretical base. This method is recommended by FAO as the sole method to calculate reference evapotranspiration (ETo) and for evaluating the other methods. The objective of this study is to compare PM using hybrid of artificial neural networks and algorithm genetic (ANN-GA) and artificial neural networks (ANNs) models for estimating ETo only on the basis of the meteorological data. ANNs are effective tools to model nonlinear systems and require fewer inputs, and GAs are strong tools to reach the global optimal solution. The weather stations selected for this study are located in Esfahan Province (center of Iran). The monthly meteorological data from 1951 to 2005 have been used for this study. The meteorological data were maximum, average and minimum air temperatures, relative humidity, sunshine duration and wind speed. The ANNs and ANN-GA models learned to forecast PM reference evaporation (PM ETo). The results of this research indicate that ANN-GA predicted PM ET0 better than ANNs model.