Bright key facts / Experimental
A twelve-hour earlier clue to where the Sun may change.
NASA reports that a COFFIES machine-learning model can predict the appearance of solar active regions, including far-side emergence, up to 12 hours before they appear.
- AI’s role
- The model learns precursor patterns associated with active-region emergence.
- Documented result
- NASA reports up to 12 hours of lead time. The public account does not provide operational validation, false-alarm rates, or evidence of forecast-center adoption.
- Important limitation
- The model predicts active-region emergence, not a damaging flare or coronal mass ejection.