Currently, the energy market is facing the challenge of significant increase in demand and it is a well known fact that the availability of fossil fuels is limited. The solar generation has evolved as the most promising solution to meet the demand, but the integration of solar generation to the power grid poses a stability threat due to its intermittent nature. To ensure the legitimate operation of the grid, accurate solar power forecast is essential. Apart from stability, accurate forecasting can also help in maintaining economic operation of the grid since it would help in appropriate installation of storage resources. In this study, we present an approach for short term solar irradiance forecast at a given location based on numerical weather prediction in combination with gradient boosting regression and bootstrap aggregation machine learning models. We considered additional parameters such as spatial parameters (elevation, latitude, longitude) and seasonal parameters (day and month of the year). Effectiveness of the proposed method will be evaluated based on Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE) indices.