The invisible turbulence is now being asked to file its own encounter report
the invisible turbulence is now being asked to file its own encounter report: a gradient boosting model reached an auc of 0.904 predicting clear air turbulence in us airspace from pilot reports and reanalysis, a ten neuron network hit 0.95 on a brazilian corridor, and a physics structured mixture of experts routes four specialist sub networks by stability regime.
the upper air now files its own bump ledger.
Context
An arXiv preprint of June 16, 2026 on high-altitude clear air turbulence in United States airspace uses pilot reports, ERA5 reanalysis and aircraft aerodynamic parameters from the BADA database at 200 to 350 hPa, and says gradient boosting, particularly XGBoost, achieved the highest performance with an AUC of 0.904. A paper in the journal Atmosphere, published April 26, 2026, on severe clear air turbulence over Southeast Brazil with Global Forecast System outputs reports that a multi-layer perceptron with one hidden layer of 10 neurons achieved the highest AUC of 0.95 plus or minus 0.03, with random forest at 0.94 and logistic regression at 0.93. PSTNet, an arXiv paper of March 2026, describes a lightweight mixture-of-experts architecture with a zero-parameter analytical backbone from Monin-Obukhov similarity theory and a regime-gated mixture of four specialist sub-networks: convective, neutral, stable and stratospheric.
The three results come from different regions, data and tasks, so the 0.904 and 0.95 AUC figures are not a head-to-head comparison, and the Brazil authors note that several other algorithms performed comparably. The US repository for the 0.904 work describes the paper as under review. The Brazilian region in the paper is a Southeast Brazil box and the post says corridor. PSTNet estimates turbulence intensity and was read from its abstract and method text, and the post's description of it matches the four-expert gating. All figures are the authors' own. The upper air now files its own bump ledger is the author's line.
Watch next
- Peer review status of the US study.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 21:49 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 →