The tornado is now being asked to file its own warning
the tornado is now being asked to file its own warning: a two stage network on doppler radar data cuts false alarms while keeping detections high, a deep learning system raised recall from 72 percent to over 99 percent in a very high recall configuration, and a model using an open source radar dataset now flags precursors 15 minutes ahead.
the sky now files its own funnel log.
Context
TorDet is a two-stage deep learning approach for radar-based tornado detection. Its abstract says existing methods mainly struggle with high false alarms, and it targets that problem.
The open source radar dataset is almost certainly TorNet from MIT Lincoln Laboratory, a benchmark dataset for tornado detection and prediction using full-resolution polarimetric radar data. The lab published the data and code publicly. I did not confirm that it is the exact dataset the note refers to.
The 72 to over 99 percent recall figure and the 15 minute precursor claim are not confirmed here. A very high recall setting usually trades against false alarms, which is why the two-stage design matters.
Related work
- TorNet code (MIT Lincoln Laboratory) ↗Software to work with the TorNet dataset.
- Multi-task learning for tornado identification using Doppler radar data ↗Another network aimed at false alarms and detection probability.
Watch next
- Operational tests of radar tornado detectors against warning forecasters.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 16:19 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 →