The night sky is now being read like a ledger
the night sky is now being read like a ledger: mistnet learned from 200,000 radar images to separate migrating birds from rain at 95 percent accuracy, birdflow identifies species inside a flock and predicts their routes, and marine radar now tracks birds automatically around orkney.
the migration now files its own manifest.
Context
MistNet is a deep convolutional neural network that discriminates precipitation from biology in archived weather radar scans for measuring historical bird migration in the US (2019). BirdFlow infers how species migrate from weekly eBird Status and Trends distribution estimates and can generate synthetic migration routes.
A May 2026 paper in IET Radar, Sonar and Navigation benchmarks automated bird detection and tracking with radar, with authors including McIlvenny.
MistNet, BirdFlow and automated radar bird tracking match the sources. The '200,000 images' and '95 percent' figures, 'species inside a flock' and the Orkney marine radar site were not seen in the excerpts read, so they are unsupported here, not refuted.
'The migration now files its own manifest' is the author's opinion.
Related work
- MistNet: measuring historical bird migration with archived radar ↗The radar network.
- BirdFlow model overview ↗Route prediction.
- Autonomous radar ornithology benchmark ↗Automated tracking.
Watch next
- Read the MistNet paper for its precision figure.
Sources
- MistNet, Oxford ORA, Aug 27, 2019ora.ox.ac.uk
- BirdFlowR documentationbirdflow-science.github.io
- IET Radar, Sonar and Navigation, May 9, 2026digital-library.theiet.org
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 3 October 2026 at 11:50 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 →