One way to forecast solar radiation when the measurement data are not available is estimation by using meteorological parameters. In this study, meteorological data, including maximum and minimum temperatures, wind speed, sunshine hours, degree of cloudiness, precipitation, pressure, and humidity were collected in the sixth stations of Mashhad, Isfahan, Ramsar, Zahedan, Urmia, and Shiraz. Meteorological parameters affecting solar radiation were determined using Gamma test at each station. The results showed that in all stations the maximum temperature and sunshine hours, in 5 stations degree of cloudiness, and in 4 station pressure and wind speed were the parameters affecting the solar radiation. The most important influencing parameters were different at each station so that in four stations the wind speed and in three stations the sunshine hours were ranked as first and second. The results showed that the maximum temperature and the degree of cloudiness were also effective on solar radiation but they possessed less importance compared to the latter parameters. After determining the effective meteorological parameters at each station, solar radiation was estimated using support vector machine (SVM) and three experimental methods of Angstrom, Hargreaves, and Abdullah. Coefficients of experimental methods was calibrated using data training. In stations under study the accuracy of Angstrom and Abdullah were not certain and at some stations Abdullah and in others the Angstrom methods estimated radiation more accurately. Hargreaves method estimated the solar radiation with less accuracy compared to the two other experimental methods. SVM estimated the solar radiation in the test phase at Isfahan, Mashhad, Urmia, Ramsar, Shiraz, and Zahedan stations by RMSE errors of 1.38, 1.28, 1.36, 1.51, 1.21, and 1.58 MJm-2d-1 and MEF errors of 3.59, 5.50, 4.18, 7.96, 3.26, and 5.17 percent, respectively. SVM estimated the solar radiation with greater accuracy than empirical methods in all stations by using artificial intelligence.