The sandstorm is now being booked in advance
the sandstorm is now being booked in advance: china’s ai-gamfs forecasts dust across the north 100 times faster with 10 to 30 percent more accuracy, an xgboost model reads its drivers with shap explanations, and phoenix took two category 5 haboobs in one week.
the wall of dust now sends a memo.
Context
The China Meteorological Administration says a CAMS-led team published on Mar 5, 2026 results on AI-GAMFS, which it calls the world's first AI-driven global aerosol-meteorology forecasting system. The arXiv paper says it gives 5-day, 3-hourly aerosol forecasts, and People's Daily on Jun 5 reports it improves dust forecasting speed and accuracy.
A Nature paper covers operational global aerosol forecasting with machine learning.
AI-GAMFS and its dust forecasting role match the sources. The 100 times faster and 10 to 30 percent accuracy figures, the XGBoost SHAP model and the Phoenix haboobs were not seen in the excerpts read, so unsupported here, not refuted.
'the wall of dust now sends a memo' is the author's opinion.
Related work
- CMA: AI-driven Global Aerosol-Meteorology Forecasting System launched ↗Official announcement.
- People's Daily: AI empowers China's sandstorm forecasting ↗Dust forecasting.
- Nature: Advancing operational global aerosol forecasting with ML ↗Published paper.
Watch next
- Read People's Daily for the speed and accuracy figures.
Sources
- CMA, Mar 6, 2026cma.gov.cn
- People's Daily, Jun 5, 2026en.people.cn
- arXiv 2412.02498arxiv.org
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 3 October 2026 at 09:06 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 →