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.
- Maturity
- Experimental, stage 1 of 4
- Support
- 2 sources · government
- Evidence detail
- How we know ↓
Space-weather forecasters need earlier evidence about regions that may later produce disruptive activity.
Active regions can emerge out of view or before visible surface signs become clear.
The model learns precursor patterns associated with active-region emergence.
What was shown, and what wasn’t
Shown
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.
Not shown · limits
- The model predicts active-region emergence, not a damaging flare or coronal mass ejection.
- No public false-alarm or operational validation rate is provided.
- The evidence is an agency report pending underlying paper-level performance review.
Bright editorial interpretation
Even a modest additional window could become another input for forecasters if performance holds under operational evaluation.
Still open
What sensitivity and false-positive rate accompany the 12-hour lead?
How does far-side performance compare with visible-side emergence?
Will operational forecasters adopt it?
How we know2 sources · checked 2026-09-19 · no corrections
Original sources
- NASA’s COFFIES Uses AI to Predict Storm-Causing Active Regions ↗ · government
- COFFIES Drive Science Center ↗ · government
Institutions: NASA · COFFIES
- Maturity
- Experimental
- Claim confidence
- medium
- Event date
- 2026-08-14
- Source published
- 2026-08-14
- Captured
- 2026-09-19
- Last source review
- 2026-09-19
- Editorial method
- AI-assisted source review
- Place / relevance
- The Sun · global-study
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Revision & correction history
2026-09-19 · Initial lead-time draft with target-event distinction.
No corrections recorded.
Keep exploring
Explore the shared question in another setting. These connections do not imply replication.