In this paper, an artificial neural network (ANN) models for estimating and modelling of daily global solar radiation have been developed. The data used in this work are the global irradiation H-G, diffuse irradiation H-D, air temperature T and relative humidity H-u. These data are available from 1998 to 2002 at the National Renewable Energy Laboratory (NREL) website. We have developed six ANN-models by using different combination as inputs: the air temperature, relative humidity, sunshine duration and the day of year. For each model. the output is the daily global solar radiation. Firstly, a set of 4 x 365 points (4 years) has been used for training each networks while a set of 365 points (1 year) has been used for testing and validating the ANN-models. It was found that the model using sunshine duration and air temperature as inputs, gives good accurate results since the correlation coefficient is 97.65%. A comparative study between developed ANN-models and conventional regression models is presented in this study. (C) 2009 Elsevier Ltd. All rights reserved.