A machine-learning reconstruction of sea surface pCO₂ in the North American Atlantic Coastal Ocean Margin from 1993 to 2021

Abstract. Insufficient spatiotemporal coverage of partial pressure of CO₂ (pCO₂) observations has hindered precise studies of the coastal carbon cycle along the North American Atlantic Coastal Ocean Margin (NAACOM). Earlier pCO₂-products have encountered difficulties in accurately capturing the heterogeneity of regional variations and decadal trends of pCO₂ in the NAACOM. This study developed a regional reconstructed pCO₂-product for the NAACOM (Reconstructed Coastal Acidification Database-pCO₂, or ReCAD-NAACOM-pCO₂) using a two-step approach combining random forest regression and linear regression. The product provides monthly pCO₂ data at 0.25° spatial resolution from 1993 to 2021, enabling investigation of regional spatial differences, seasonal cycles, and decadal changes in pCO₂. The observation-based reconstruction was trained using Surface Ocean CO₂ Atlas (SOCAT) observations as ground-truth values, with various satellite-derived and reanalysis environmental variables known to control sea surface pCO₂ as model inputs. The product shows high accuracy during the model training, validation, and independent test phases, demonstrating robustness and capability to accurately reconstruct pCO₂ in regions or periods lacking direct observational data in the NAACOM. Compared with all the observation samples from SOCAT, the pCO₂-product yields a determination coefficient of 0.83, a root-mean-square error of 18.64 µatm, and an accumulative uncertainty of 23.83 µatm. The ReCAD-NAACOM-pCO₂ product demonstrates its capability to resolve seasonal cycles, regional-scale variations, and decadal linear trends of pCO₂ along the NAACOM. This new product provides reliable pCO₂ data for more precise studies of coastal carbon dynamics in the NAACOM region. The dataset is publicly accessible at https://doi.org/10.5281/zenodo.11500974 (Wu et al., 2024a) and will be updated regularly.