Reconstruction of global surface ocean pCO₂ using region-specific predictors based on a stepwise FFNN regression algorithm

Various machine learning methods were attempted in the global mapping of surface ocean partial pressure of CO2 (pCO2) to reduce the uncertainty of the global ocean CO2 sink estimate due to undersampling of pCO2. In previous research, the predictors of pCO2 were usually selected empirically based on theoretic drivers of surface ocean pCO2, and the same combination of predictors was applied in all areas except where there was a lack of coverage. However, the differences between the drivers of surface ocean pCO2 in different regions were not considered. In this work, we combined the stepwise regression algorithm and a feed-forward neural network (FFNN) to select predictors of pCO2 based on the mean absolute error in each of the 11 biogeochemical provinces defined by the self-organizing map (SOM) method. Based on the predictors selected, a monthly global 1∘ × 1∘ surface ocean pCO2 product from January 1992 to August 2019 was constructed. Validation of different combinations of predictors based on the Surface Ocean CO2 Atlas (SOCAT) dataset version 2020 and independent observations from time series stations was carried out. The prediction of pCO2 based on region-specific predictors selected by the stepwise FFNN algorithm was more precise than that based on predictors from previous research. Applying the FFNN size-improving algorithm in each province decreased the mean absolute error (MAE) of the global estimate to 11.32 µatm and the root mean square error (RMSE) to 17.99 µatm. The script file of the stepwise FFNN algorithm and pCO2 product are distributed through the Institute of Oceanology of the Chinese Academy of Sciences Marine Science Data Center (IOCAS, https://doi.org/10.12157/iocas.2021.0022, Zhong, 2021.