Abstarct: Abstract As a renewable energy resources, Solar radiation (Rs) is crucial in determination of water requirement and irrigation scheduling planning. In the present study, the effect of MODIS satellite-baxsed indices on Rs estimation in Mashhad watershed was investigated (2005-2015). In the first scenario, solely the meteorological parameters (air temperature, average air temperature and relative humidity) and in the second one, combination of both meteorological parameters and satellite-baxsed parameters (normalized difference vegetation index, net radiation and land surface temperature) were considered as the inputs of multi-laxyer perceptron neural network. To achieve the best results, three different transfer function algorithms including Levenberg-Marquardt backpropagation (MLP-LVM), Gradient descend backpropagation (MLP-GDB) and Batch training with weight and bias learning rules (MLP-BTWB) were employed. Application of the second scenario with assigning the values of (RMSE=104.2 J.cm-2.day-1, R2=0.84), (RMSE=124.5, R2=0.83) and (RMSE=123.8, R2=0.82) for the aforementioned transfer functions, respectively, in comparison with the values of (RMSE=225.2, R2=0.71), (RMSE=227.7, R2=0.7) and (RMSE=228.4, R2=0.7) for the first scenario, lead to an improvement on Rs estimation. Using satellite-baxsed indices in the form of other artificial intelligence models can be considered as an approach to increase the accuracy of Rs estimation.