NASA’s COFFIES Uses AI to Predict Storm-Causing Active Regions on Sun
As humanity looks to the Moon and stars for future exploration, predicting space weather — conditions in space primarily driven by the Sun — is more important than ever. Now, a team of astrophysicists and data scientists with NASA’s COFFIES (Consequence Of Fields and Flows in the Interior and Exterior of the Sun) has developed a […]
NASA’s COFFIES program, a collaboration between NJIT, Princeton University, and NASA’s Ames Research Center, has developed an artificial intelligence model to predict the formation of active regions on the Sun up to 12 hours before they become visible. Sunspots, the visible manifestations of these active regions, are the primary drivers of severe space weather events such as solar flares and coronal mass ejections.
These events pose threats to astronauts, satellites, and radio communications on Earth. To achieve this, the COFFIES team employed advanced artificial intelligence architectures and analyzed data from NASA’s Solar Dynamics Observatory and NASA Ames’ supercomputing resources. They focused on subtle changes in acoustic waves and magnetic field fluctuations, which precede the emergence of active regions.
By employing a sliding-window transformer architecture, the AI model can detect minute reductions in the Sun's acoustic activity and magnetic field, patterns that were previously difficult to capture. While the model is currently not operational for real-time forecasting, the team aims to validate and refine the technique using more solar events data.
Written by urgent.news from NASA's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
