The storm in space is now being asked to give notice
the storm in space is now being asked to give notice: nasa’s coffies predicts sunspot active regions up to 12 hours before they appear, aurora hunter runs 51 physics driven features to forecast aurora visibility, and the dagger model sees geomagnetic disturbance 30 minutes out.
the sun now files its own storm schedule.
Context
NASA says its COFFIES team built a machine learning model that can predict the emergence of active regions on the Sun up to 12 hours before they appear, using a sliding-window transformer to find small reductions in the Sun's acoustic activity. The Aurora Hunter paper describes a two-stage cascade that separates aurora occurrence from observing conditions, with stage 1 using 51 physics-driven features in five groups.
NASA describes DAGGER (Deep Learning Geomagnetic Perturbation) as a model that analyzes solar wind measurements and predicts geomagnetic disturbances worldwide 30 minutes before they occur, in under a second.
The 12 hours is an upper bound ('up to') for COFFIES. An NJIT-led team separately reported spotting such signals nearly nine hours ahead. The 51 features and the two-stage design match the Aurora Hunter abstract, which forecasts visibility at a location and not the storm itself.
The DAGGER description in the pages read is dated 2023, so it is not new. The note presents the three as one current set, but they are separate projects from different groups and years. 'The sun now files its own storm schedule' is the author's line.
The pages read give no verification record of how often COFFIES or DAGGER forecasts were right in operation, so performance claims beyond the lead times are unsupported here, not refuted.
Related work
- NASA's COFFIES Uses AI to Predict Storm-Causing Active Regions on Sun (NASA Science) ↗Primary source for the COFFIES 12-hour result and its method.
- Aurora Hunter: A Two-Stage Framework for Probabilistic Visibility Forecasting (arXiv 2605.24038) ↗Primary source for Aurora Hunter's 51 features and two stages.
- NASA-enabled AI predictions may give time to prepare for solar storms (NASA, March 2023) ↗Source for DAGGER's 30 minute warning and its date.
Watch next
- Read the COFFIES paper's validation. Check how Aurora Hunter scores its visibility forecasts against sightings.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 3 October 2026 at 20:17 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →