Global concerns about climate change and the depletion of hydrocarbon reserves have made the search for new sources of renewable energy, such as solar power. Solar energy, particularly global horizontal irradiance, is a key source of green electricity. However, accurate prediction of global horizontal irradiance remains a challenge due to the variability in weather conditions. In this work, we investigate how integrating artificial intelligence can enhance solar energy forecasting by evaluating decision tree, random forest regression, and gradient boosting machine. Additionally, they are integrated into a hybrid machine learning framework with linear regression to address the challenges of global horizontal irradiance prediction. The case study is based on data from Râmnicu Vâlcea, Romania (45.10° N, 24.37° E). To assess model performance, we measure R2 score, Mean Absolute Error, and Root Mean Squared Error. The dataset for this study was generated using NASA’s Data Access Viewer. The results show that our proposed hybrid model successfully transforms non-linear data into linear data and outperforms standard machine learning models, providing valuable insights for improving solar energy forecasting in future research.