The coastal sea is now being asked to keep its own carbon books
the coastal sea is now being asked to keep its own carbon books: two neural nets turn satellite and reanalysis fields into continuous air sea co2 maps for the global coastal ocean, a random forest rebuilds 22 years of gulf of mexico pco2 at 4 kilometers and 8 day steps, and a fleet of robot sailboats will spend five years measuring the southern ocean sink.
the tide now files its own carbon balance.
Context
The global coastal pCO2 product uses a two-step Self Organizing Map and Feed Forward Network method to fill observational gaps. The coastalv2 manuscript covers 1982-2020 at 0.25-degree monthly resolution using SOCAT observations and environmental predictors. Surface pCO2 maps support air-sea flux estimates; they are not direct measurements everywhere.
The northern Gulf of Mexico preprint reconstructs surface pCO2 from 2003 to 2024 at 4-kilometre, 8-day resolution with a season-specific random forest. It reports independent-validation R-squared of 0.82 and RMSE of 27.6 microatmospheres. This regional reconstruction is a separate product from the global coastal map.
CSIRO and Columbia describe COCO2 as a five-year Southern Ocean observing project using four autonomous Saildrone vehicles, with deployments every quarter and adjustable sampling routes. The September 2026 launch is the start of sustained measurements, not a completed five-year carbon balance.
The two neural networks are stages of one coastal interpolation method, not two independent measurements of flux. pCO2 is a surface quantity; converting it to air-sea CO2 exchange requires further assumptions. The Gulf result applies to the northern Gulf of Mexico and remains a discussion preprint. The Saildrone project adds direct observations to reduce gaps, especially in winter. Together these studies concern interpolation, regional reconstruction and new sampling, not autonomous accounting of the entire ocean carbon stock.
Related work
- Robot Sailboats Will Spend Five Years Measuring Carbon in the Southern Ocean ↗The project account distinguishes four vehicles, planned sustained sampling and model-guided choices of observation locations.
Watch next
- Track winter coverage and quality-controlled COCO2 releases, coastal-product uncertainty where observations are sparse, and the final peer-reviewed Gulf paper. Check flux sensitivity to gas-transfer and wind assumptions separately from pCO2 prediction error.
Sources
- A novel sea surface pCO2-product for the global coastal ocean resolving trends over the 1982-2020 periodarchimer.ifremer.fr
- Long term Strengthening of the CO2 Sink and Spatiotemporal pCO2 dynamics in the northern Gulf of Mexico: Insights from a 22 year Satellite based Machine Learning Reconstruction (preprint)egusphere.copernicus.org
- Ocean drones set to brave the Southern Ocean for science (CSIRO)csiro.au
- Robot Sailboats Will Spend Five Years Measuring Carbon in the Southern Ocean (Columbia)news.climate.columbia.edu
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 03:52 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 →