The hailstone is now being asked to file its own size note
the hailstone is now being asked to file its own size note: a specialized stormscope model trained with nvidia generates hyper local hail forecasts two to three hours ahead across colorado and wyoming, an automated imaging system with deep learning measures hail size distributions every minute, and ncar now runs daily ai forecasts for large hail and damaging winds a full week in advance.
the storm now files its own pellet report.
Context
Hail damage is local and fast, so forecasts have to be too. NVIDIA and Colorado State University are working on a stormscope model that gives hail forecasts two to three hours ahead over Colorado and Wyoming. The HailCam paper describes an automated imaging system that measures hail size distributions in real time, which gives forecasters ground truth they rarely have.
NCAR's work reaches the other end of the range: daily AI forecasts of large hail and damaging winds about a week ahead. Together they cover nowcasting, measurement and medium-range outlook.
Nowcasts need fine resolution and fast updates; medium-range outlooks need broad patterns. A system that does one well rarely does the other, which is why the sources describe separate models for each.
Related work
- Colorado State University Hailstorm Forecasting (NVIDIA case study) ↗The partnership behind the stormscope model.
- Real-time AI-Driven Medium-Range Convective Hazard Forecasts (NCAR) ↗Project page for the weekly outlooks.
Watch next
- Verification of hail size predictions against HailCam-type measurements.
- How forecasters use week-ahead probabilities in practice.
Sources
- CSU partners with NVIDIA to revolutionize severe storm prediction (Colorado State University)engr.source.colostate.edu
- AMT - HailCam: an automated imaging system for real-time measurement of hail size distributions and fall ratesamt.copernicus.org
- Identifying severe weather hazards further in the future with AInews.ucar.edu
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 15:36 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 →