EarlyDetect AI model identifies solar eruptions 9 hours in advance
A new AI model developed by researchers at the New Jersey Institute of Technology (NJIT), Princeton University, and NASA’s Ames Research Centre can detect subtle signs of emerging solar active regions before they become visible on the Sun. Called EarlyDetect, the model analyses changes in the Sun’s acoustic waves and magnetic field using observations from NASA’s Solar Dynamics Observatory (SDO). In tests, it identified the signals associated with new active regions an average of 9.24 hours before they appeared at the surface. The result could eventually improve forecasts of solar activity by providing earlier warning of regions capable of producing solar eruptions. However, the researchers stress that EarlyDetect is still experimental and cannot yet predict whether an active region will produce a flare or coronal mass ejection. Detecting solar activity beneath the surface Solar active regions are areas of intense magnetic activity where sunspots develop. They can emerge over several hours, though the structures may take days to develop fully. The challenge for researchers is that their formation begins below the Sun’s visible surface. Researchers …
