The glacier is now being asked to file its own volume report
the glacier is now being asked to file its own volume report: a machine learning model trained on over 7 million ice thickness measurements now estimates the volume of glaciers worldwide, a deep learning inventory tracks glacier shrinkage across the peruvian and bolivian andes from 2016 to 2024, and a neural network trained on 350,000 synthetic flow solutions matches ice physics on glaciers it has never seen.
the ice now files its own mass balance.
Context
Glaciers are measured in three ways here: how thick they are, where their edges sit, and how ice flows. The first result is IceBoost v2.0, a gradient-boosted tree model trained on 7 million ice thickness measurements with physical and geometric predictors. It models thickness for every glacier in the latest Randolph Glacier Inventory releases, so the output is a global volume dataset.
The Andes work is a deep learning inventory of glacier outlines in the Peruvian and Bolivian tropics for 2016 to 2024, published as a dataset on Zenodo. The third result trains a network once on synthetic flow solutions to stand in for a costly higher-order ice flow solver.
A gradient-boosted tree trained on measurements is a different bet from a neural network trained on simulations. The first learns from what was observed; the second learns to reproduce a model. Each answers a different part of the problem: how much ice there is, and how it will move.
Related work
- Machine-learned global glacier ice volumes (arXiv) ↗Preprint version of the IceBoost paper.
- Ice-flow model emulator based on physics-informed deep learning (Journal of Glaciology) ↗An earlier emulator of the same kind.
Watch next
- How well the thickness estimates match new radar surveys that were not in the training data.
- Whether the flow emulator stays stable over long projections.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 14:36 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 →