The ice sheet is now being asked to file its own melt budget
the ice sheet is now being asked to file its own melt budget: a machine emulator trained on forty five years of regional model meltwater now attributes daily melt to its drivers across greenland in space and time, a graph transformer reproduces annual melt fields across a hundred member climate ensemble with near perfect fit, and the first ice sheet wide slush map covers 2016 to 2024 at hundred meter resolution.
the ice now files its own phase change ledger.
Context
Three separate lines of work match the three systems in the post. MAR-IA, published in The Cryosphere in 2026 (volume 20, page 4235), is a machine-learning emulator of the MAR regional climate model trained on daily meltwater production for 1979 to 2024, that is 45 years, built to emulate daily surface meltwater over Greenland and attribute melt drivers using SHAP, with results on the dominance of radiative versus non-radiative drivers. A Greenland surface melt emulator using a graph transformer was presented in 2025 by CESM workshop and EGU abstracts. A Cryosphere paper of August 7, 2026 presents the first classification of slush across the Greenland Ice Sheet, using Sentinel-2 imagery and a random forest classifier for 2016 to 2024, with masks exported at 100 m resolution, a mean seasonal slush extent of 2.8% of the ice sheet, about 48,100 km2.
The match between the post's three systems and these papers is by topic and abstract. The graph transformer reproducing annual melt fields across a hundred-member ensemble with near-perfect fit was not confirmed against a published paper, since only workshop and abstract pages were found, so that figure is unverified here. The slush analysis was classified at 10 m and exported at 100 m, and the 100 m figure is the export resolution. These are authors' own evaluations of models and not operational products. The ice now files its own phase change ledger is the author's line.
Watch next
- The published graph transformer melt emulator paper and its ensemble results.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 21:17 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 →