New AI model detects hidden signs of solar eruptions hours before they emerge
Long before dark sunspots appear on the sun's surface, a new active region—where powerful solar eruptions can originate—begins showing subtle signs of its formation. Now, researchers say a new artificial intelligence model can detect those early signals and forecast the emergence of solar active regions nearly nine hours in advance on average.
Scientists have developed an artificial intelligence model called EarlyDetect that can detect early signals of solar active region formation and forecast their emergence nearly nine hours in advance. This breakthrough could allow satellite communications and power grid companies to prepare for potential solar storms. The model, created by researchers at New Jersey Institute of Technology, Princeton University, and NASA's Ames Research Center, analyzes acoustic power maps and magnetic field measurements from NASA's Solar Dynamics Observatory.
EarlyDetect uses a Transformer architecture to learn patterns in solar observations and predict future changes in solar activity. The model identifies precursor signals an average of 9.24 hours before active regions become visible, outperforming previous methods. However, the model still produces occasional false alarms and requires further validation with more solar events.
The team has also released a publicly available dataset and web platform for researchers to build upon this work.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — it may contain errors, so check the original before relying on it.
