Performance Evaluation of Artificial Neural Networks for Estimating Refer-ence Evapotranspiration in Shahat, Libya using limited climatic data

Abstract

This study was conducted with the aim of evaluating the performance of artificial neural networks (ANNs) to estimate the reference evapotranspiration using limited climate data in Shahat region in Libya, compared to using the FAO Penman-Monteith equation (FPM), which requires temperature, wind speed, relative humidity and number of sunshine hours, which are rarely available in most meteorological stations in developing countries. In this study, we used the average temperature (Tmean) and the average relative humidity (RHmean) obtained from Shahat meteorological station for the period from 1963 to 1999, and the extraterrestrial radiation (Ra), which can be calculated given the location and time of the day. These data are divided into two groups, from 1963 to 1988 and from 1989 to 1999 for the training and validation phases of the neural networks, respectively. This study concluded that using (Tmean), (RHmean) and (Ra) gave the best agreement with the results calculated with the FAO Penman-Monteith equation, where the values of R2 and RMSE are equal to 0.98 and 0.26, respectively.