The acidifying sea is now being asked to keep its own ph diary
the acidifying sea is now being asked to keep its own ph diary: an unsupervised model clusters arctic acidification simulations into four zones that track present and future sea ice, a portable sensor with machine learning reads full range underwater ph in the field, and ml fitting estimates pco2 and ph around the canary islands from buoys and ships.
the water now files its own acidity report.
Context
Regional sensitivity patterns of Arctic Ocean acidification (April 19, 2022) applies unsupervised SAGE clustering to GFDL-CM4 and GFDL-ESM4 climate simulations. Four Arctic surface-water regions are broadly consistent across the two models and two emissions scenarios. Their boundaries relate to present-day and projected September sea ice.
A Nature Sensors paper published July 29, 2026 describes a fibre-optic surface-enhanced Raman scattering pH sensor. Machine learning decodes the probe’s molecular fingerprints across pH 0 to 14, with paper-reported errors below 0.2 pH units and remote deployment up to 10 metres in seawater and groundwater.
The February 12, 2026 Canary Islands study fits pCO2 and pH using 2019 to 2024 buoy and voluntary-observing-ship records plus environmental inputs. Bagging gives the best reported fit, including pCO2 RMSE of 2.0 microatmospheres and pH RMSE of 0.002.
The Arctic zones are clusters of simulated surface responses, not four measured sensor zones. The full-range sensor measures water locally, whereas the Canary model estimates regional properties from fitted relationships. Canary validation uses an 80/20 cruise-level random split and a narrow observed pH range of 7.97 to 8.07; that result cannot be equated with full-range field sensor accuracy or general ocean-wide forecasting.
Watch next
- Long-term sensor drift and independent deployments. Temporal and geographic holdouts for regional carbonate estimates. Sensitivity of Arctic cluster boundaries to a wider climate-model ensemble.
Sources
- Regional sensitivity patterns of Arctic Ocean acidification revealed with machine learningnature.com
- Field-deployable full-range underwater pH sensor using a polyprotic SERS probenature.com
- Modelling seawater pCO2 and pH in the Canary Islands region based on satellite measurements and machine learning techniquesos.copernicus.org
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 07:17 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 →