The ocean plays a critical role in modulating climate change by sequestering CO2 from the atmosphere. Quantifying the CO2 flux across the air-sea interface requires time-dependent maps of surface ocean partial pressure of CO2 (pCO2), which can be estimated using global ocean biogeochemical models (GOBMs) and observational-based data products. GOBMs are internally consistent, mechanistic representations of the ocean circulation and carbon cycle, and have long been the standard for making spatio-temporally resolved estimates of air-sea CO2 fluxes. However, there are concerns about the fidelity of GOBM flux estimates. Observation-based products have the strength of being data-based, but the underlying data are sparse and require significant extrapolation to create global full-coverage flux estimates. The Lamont Doherty Earth Observatory-Hybrid Physics Data (LDEO-HPD) pCO2 product is a new approach to estimating the temporal evolution of surface ocean pCO2 and air-sea CO2 exchange. LDEO-HPD uses machine learning to merge high-quality observations with state-of-the-art GOBMs. We train an eXtreme Gradient Boosting (XGB) algorithm to learn a non-linear relationship between model-data mismatch and observed predictors. GOBM fields are then corrected with the predicted model-data misfit to estimate real-world pCO2 for 1982–2018. The resulting reconstruction by LDEO-HPD is in better agreement with independent pCO2 observations than other currently available observation-based products. Within uncertainties, LDEO-HPD global ocean uptake of CO2 agrees with other products and the Global Carbon Budget 2020.

Plain Language Summary

The ocean absorbs carbon from the atmosphere, which slows climate change. In order to estimate how much carbon the ocean absorbs, we need to know how much is exchanged from the atmosphere into the ocean at each location over time. The direct observations required to do this are very sparse and in some regions of the ocean, observations have never been made. One approach to fill in the gaps is to use machine-learning techniques, which are algorithms that build a relationship for ocean carbon based on related satellite observations with global coverage. Another approach is to use computer simulations, which use mathematical equations to represent ocean processes. Here, we merge these two innovations by blending model output with machine-learning to create a hybrid product: the Lamont Doherty Earth Observatory-Hybrid Physics Data (LDEO-HPD). Particularly for the most recent decade, LDEO-HPD agrees better with independent observations than other products, indicating promise for the approach.