Ocean Science
Ocean Science
OS
Articles | Volume 22, issue 1
Articles | Volume 22, issue 1
https://doi.org/10.5194/os-22-609-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/os-22-609-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 22, issue 1
Research article
 | 
12 Feb 2026
Research article |  | 12 Feb 2026

Modelling seawater pCO2 and pH in the Canary Islands region based on satellite measurements and machine learning techniques

Irene Sánchez-Mendoza, Melchor González-Dávila, David González-Santana, David Curbelo-Hernández, David Estupiñán-Santana, Aridane G. González, and J. Magdalena Santana-Casiano

Supplement

https://doi.org/10.5194/os-22-609-2026-supplement

Data sets

Canary Islands pCO2/pH data from 2019 to 2024 using VOS and Buoys data M. Gonzalez-Davila and J. M. Santana-Casiano https://doi.org/10.5281/zenodo.16780085

Atmospheric Carbon Dioxide Dry Air Mole Fractions from the NOAA GML Global Greenhouse Gas Reference Network, Version: 2025-08-15 X. Lan et al. https://doi.org/10.15138/wkgj-f215

Model code and software

Models for predicting the partial pressure of CO2 in seawater (pCO2,sw) using different machine Learning approaches S.-M. Irene et al. /10.5281/zenodo.16780313

Download
Short summary
Satellite and machine-learning methods now allow monitoring of pCO2,sw and acidity. Using ship and buoy data at the Canary Islands from 2019–2024, models (especially bagging) estimated CO2 and pH with high accuracy. Results show rapidly rising ocean CO2 and increasing acidification, driven by higher atmospheric CO2 and warming, including the 2023 marine heatwave. The region shifted from a weak CO2 sink to a strong source by 2024.
Read more
Share