Comparative analysis of estimated solar radiation with different learning methods and empirical models

Solar radiation, which is used in hydrological modeling, agricultural, solar energy systems, and climatological studies, the most important element of reaching earth. The present study compared, performance two empirical equations -Angstrom Hargreaves-Samani equations- and, three machine learning models -Artificial Neural Networks (ANN), Support Vector Machine (SVM), Long Short-Term Memory (LSTM)-. Various were developed for variables each equation. In study, monthly data six stations Turkey, receiving radiation least used. terms mean squared error (MSE), root (RMSE), absolute (MAE), determination coefficient () values model, LSTM was successful followed by ANN SVM. MAE value 2.65 with equation decreased to 0.987 model while 1.24 Angstrom 0.747 model. revealed that deep more appropriate use compared even cases where there limited data.