Accurate forecasting of solar radiation is essential for optimizing the operation of renewable energy systems. This study leverages an Artificial Neural Network (ANN) to perform predictions, with its learning process refined using Particle Swarm Optimization (PSO). Pre-processing steps, including data cleansing and normalization, were applied to the dataset. An investigation of feature correlations and importance was also conducted. Comparative analysis reveals that the ANN model enhanced by PSO achieves superior predictive performance, exhibiting lower MSE, RMSE, MAE, and a higher R2 value compared to the standard ANN.