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

Abstract. The improvement of remote sensing systems, together with the emergence of new model-fitting algorithms based on machine-learning techniques, has allowed the determination of the partial pressure of carbon dioxide (pCO2,sw) and pH (pHT,sw) in the waters of the Canary Islands. Among all the fitted models, the most powerful one was the bootstrap aggregation (bagging), giving a RMSE of 2.0 µatm (R2 > 0.99) for pCO2,sw and RMSE of 0.002 for pHT,is, although the multilinear regression (MLR), neural network (NN) and categorical boosting (catBoost) also have a good predictive performance, with RMSE ranging from 5.4 to 10 µatm for 360 < pCO2,sw < 481 µatm and from 0.004 and 0.008 for 7.97 < pHT,is < 8.07. Using the most reliable model, it was determined that there is an interannual trend of 3.51 ± 0.31 µatm yr-1 for pCO2,sw (which surpasses the rate of increase for atmospheric CO2 of 2.3 µatm yr-1) and an increase in acidity of -0.003 ± 0.001 pH units yr-1. The increase in both, the atmospheric CO2 and the sea surface temperature of 0.2 °C yr-1 observed in the 6-year period, influenced by the unprecedented 2023 marine heat wave, contribute to this important rate. Considering the Canary Islands between 13°–19° W and 27°–30° N, the region has moved from a slight CO2 source of 0.90 Tg CO2 yr-1 in 2019 to 4.5 Tg CO2 yr-1 in 2024. After 2022, eastern locations that acted as an annual sink of CO2 switched to acting as a source.