NIES-ML3 ensemble product of surface ocean CO2 concentrations and air-sea CO2 fluxes reconstructed by using three machine learning models with new CO2 trends

Global oceans have absorbed a substantial portion of the anthropogenic carbon dioxide (CO2) emitted into the atmosphere. Data-based machine learning estimates for the oceanic CO2 sink have become an import part of the Global Carbon Budget in recent years. This product is the result of our new study on ocean CO2 trends using Random Forest, Gradient Boost Machine, and Feedforward Neural Network. Using the time-dependent trends for ocean CO2 reconstruction substantially reduced the bias of using a constant trend and therefore improved the oceanic sink estimate.