NASA and NJIT researchers develop AI to predict solar storms

Researchers have developed a new artificial intelligence model, known as EarlyDetect, capable of anticipating the emergence of active regions on the Sun. By utilizing data from NASA’s Solar Dynamics Observatory, the model identifies subtle changes in acoustic waves and magnetic fields that occur before these regions appear on the solar surface.

These active regions are responsible for solar flares and coronal mass ejections, which can release radiation and charged particles toward Earth. Such events pose risks to satellite operations, GPS systems, communications, and electrical grids. The AI model has demonstrated the ability to anticipate the formation of these structures by approximately nine hours.

While the technology shows promise, it is not yet ready for real-time operational alerts. Current limitations include instances of false alarms and delays in warnings. Additionally, the model cannot guarantee that an active region will result in a major eruption. The project involves a collaboration between the New Jersey Institute of Technology, Princeton University, and NASA’s Ames Research Center.