Today, environmental pollution has become one of the biggest problems of our world with the effect of industrialization, population growth, fuel use and factors that harm nature. In the solution of this problem, renewable energy sources have taken place in the first place due to their features such as being obtained from natural sources, not harming the environment, being an inexhaustible energy source and being sustainable. Solar energy, which is one of the renewable energy sources, is seen as an alternative to fossil energy sources, which is cheap, has a high clean potential and is less harmful to the environment. In addition, our country is in an advantageous position in terms of solar energy. For this reason, it is important to determine suitable regions and provinces according to renewable energy sources and to plan investments accordingly. In this study, calculations were made using the amount of solar radiation, which is one of the important parameters in solar energy studies. In the study, analyzes were made for the province of Bursa, taking into account parameters such as metropolitan, industry, tourism, population and geographical location. Daily/hourly solar radiation data for the years 2015-2019 were analyzed through the Matlab program. Solutions were made with Bayesian Regularization, Levenberg-Marquardt and Scaled Conjugate Gradient methods used in the estimation with artificial neural networks. Among these three methods, Bayesian Regularization method gave the best results.
Keywords: Forecast, Solar Radiation, Artificial Neural Networks