IBM and NASA have collaborated to create Surya, an open-source AI model designed to predict solar weather and protect critical technology. Surya, named after the Sanskrit word for the Sun, analyses high-resolution solar observation data to forecast solar activity's impact on Earth and space-based systems. Solar flares and coronal mass ejections can disrupt GPS, power grids, telecommunications, and pose radiation risks. Accurate solar weather prediction is vital as dependence on space-based technology grows.
Surya is trained on nine years of NASA's Solar Dynamics Observatory data. It can visually predict solar flares, providing a high-resolution image of the predicted location up to two hours in advance. In early tests, Surya achieved a 16% improvement in solar flare classification accuracy compared to existing methods. The model aims to provide early warnings to satellite operators and help scientists understand how solar radiation affects Earth's atmosphere. Surya is available on Hugging Face, GitHub, and IBM's TerraTorch library.
