Artificial neural networks have been used widely in many application areas. Artificial Neural Networks (ANNs) are currently accepted as an alternative technology offering a way to tackle complex and ill-defined problems. Despite the great importance of Global Solar Radiation (GSR), the number of radiation stations are very less when compared to the stations that collect regular meteorological data like air temperature and humidity. The main objective of this paper is to study the feasibility of an Artificial Neural Network (ANN) based method to estimate and predict GSR based on metrological parameters. It is very encouraging to observe a very close agreement between the ANN and the measured values. The Root Mean Square Error values, which are is the measure of accuracy of a particular model or correlation use. For the present analysis, it was found to be lowest for ANN model value (4.74). The Mean Bias Error value has the lowest under estimation with a value of -1.029, which fall within the expected and acceptable range A low value of MPE is expected, ANN model was observed to have a Mean Percentage Error value of (- 2.345). The result of this study proves that ANN can be used to predict global solar radiation potential in Yola, Nigeria using meteorological data.