Machine Learning COFFIES “Hears” Sunspots Before We Can See Them

Satellite and power grid operators stand to gain improved warning times for potential disruptions as researchers enhance solar activity forecasting. These organizations face significant operational risks from space weather, which can interfere with communication systems and electricity distribution on Earth. The ability to anticipate solar eruptions provides a buffer for protective measures.

This capability originates from a machine learning project known as COFFIES, which detects hidden signs of magnetic energy build-up. Unlike traditional observation, this model monitors active regions before they become visible to standard imaging. NASA Science explains the system tracks the evolution of magnetic fields, while IIA researchers note the 3D modeling contributes to forecasting the arrival of Coronal Mass Ejections.

Additional reporting from NJIT News and Hackaday describes the technology as an auditory-like detection system that hears sunspots beneath the solar surface. The scientific community is now analyzing the precision of these multi-hour lead times. While the underlying model has demonstrated an ability to map magnetic energy trends, coverage does not yet specify how these findings will be integrated into global alert protocols or the frequency of future operational testing.