Global Horizontal Irradiance

Global horizontal irradiance (GHI), the total solar radiation received on a horizontal surface, is crucial for optimizing solar energy resource assessment and forecasting. Current research heavily utilizes satellite imagery (like Himawari-8 data) combined with machine learning models—including deep learning architectures such as LightGBM, LSTM, and transformers—to estimate GHI with high spatial and temporal resolution. These advancements improve the accuracy of solar power predictions, enhancing grid stability and facilitating the integration of renewable energy sources into power systems. The focus is on improving both nowcasting (near real-time estimation) and forecasting (predicting future GHI), addressing challenges like cloud cover variability and improving the accuracy and uncertainty quantification of predictions.