What question did this study set out to answer?

The aim is to model seawater pCO2 and pH using satellite measurements and machine learning techniques.

February 14, 2026Open Access

Modelling seawater p CO 2 and pH in the Canary Islands region based on satellite measurements and machine learning techniques

Key Points

The aim is to model seawater pCO2 and pH using satellite measurements and machine learning techniques.
Utilized continuous time-series data from buoys and Voluntary Observing Ships (VOS) between 2019 and 2024.
Trained and validated models using machine learning algorithms including bootstrap aggregation, multilinear regression, and neural networks.
Evaluated model performance through root mean square error (RMSE) metrics.
Bootstrap aggregation achieved the best performance with an RMSE of 2.0 µatm for pCO2 and 0.002 for pH.
An increasing trend in pCO2 of 3.51±0.31 µatm yr−1 was identified, surpassing atmospheric CO2 growth.
Acidification was observed at a rate of -0.003 ± 0.001 yr−1 from 2019 to 2024.

Abstract

Abstract. Recent advancements in remote sensing systems, combined with new machine-learning model-fitting algorithms, have enabled the estimation of seawater carbon dioxide partial pressure (pCO2,sw) and pH (pHT,is) in the waters around the Canary Islands (13–19° W; 27–30° N). Continuous time-series data collected from moored buoys and Voluntary Observing Ships (VOS) between 2019 and 2024 were used to train and validate the models, providing a robust observational basis for satellite-derived estimates. Among all models tested, bootstrap aggregation (bagging) performed best, achieving an RMSE of 2.0 µatm (R2>0.99) for pCO2,sw and 0.002 for pHT,is. Multilinear regression (MLR), neural networks (NN) and categorical boosting (CatBoost) also showed good predictive skill, with RMSE values between 5.4 and 10 µatm for pCO2,sw (360–481 µatm) and 0.004–0.008 for pHT,is (7.97–8.07). Using the most reliable model, we identified an increasing trend in pCO2,sw of 3.51±0.31 µatm yr−1, exceeding the atmospheric CO2 growth rate (2.3 µatm yr−1), alongside an acidification trend of −0.003 ± 0.001 yr−1. Over the 2019–2024 period, rising atmospheric CO2 and increasing sea surface temperatures (reaching up to 0.2 °C yr−1 during the unprecedented 2023 marine heatwave) likely contributed to these trends. The Canary Islands region shifted from a weak CO2 source (0.90 Tg CO2 yr−1) in 2019 to 4.5 Tg CO2 yr−1 in 2024. After 2022, eastern sites that previously acted as annual CO2 sinks became net sources.

Bookmark

View Full Paper

Cite This Study

Sánchez-Mendoza et al. (Thu,) studied this question.

synapsesocial.com/papers/699010df2ccff479cfe571b0 https://doi.org/https://doi.org/10.5194/os-22-609-2026

Bookmark

View Full Paper