Forecasting Solar Radiation Storms: Satellite Data, Predictive Models, and Their Impacts on Earth

The Earth's environment is significantly impacted by solar radiation storms, caused by high-energy solar energetic particles (SEPs) that are emitted during solar flares or coronal mass ejections (CMEs). Specifically, these storms disrupt satellite operations, interfere with HF communications, and increase radiation exposure for high-altitude flights. To mitigate these effects, Korea Space Weather Center (KSWC) monitors and forecasts solar radiation storms using satellite data and predictive models. In this paper, we introduce KSWC's space weather forecasts and the analysis methodology for satellite data from GOES, SDO, the LASCO coronagraph, and STEREO. We then present the model structure for predicting solar radiation storms, which consists of (1) a machine learning model that is trained on solar flare and CME characteristics obtained from satellite data and (2) a physics-informed model based on SEP generation mechanisms, mediated by CMEs propagating toward Earth. Notably, the machine learning model predicts the maximum intensity of solar radiation storms based on the observed solar activity, while the physics-based model enhances the interpretability of the machine learning model's predictions. The applicability of these models in preventing the technological and biological impacts of solar radiation storms on Earth is also discussed.