Interannual drivers of the seasonal cycle of CO<sub>2</sub> fluxes in the Southern Ocean

Abstract

Abstract. Machine learning methods (support vector regression and random forest regression) were used to map gridded estimates of ∆pCO 2 in the Southern Ocean from SOCAT v3 data. A low (1° ⨉ 10 monthly) and high (0.25° ⨉ 16-day) resolution implementation of each of these methods as well as the SOM-FFN method of Landschützer et al. (2014) were added to a five member ensemble. The ensemble mean ∆pCO 2 was used to calculate FCO 2 (air-sea CO 2 flux). Data was separated into nine domains defined by basin (Indian, Pacific and Atlantic) and biomes defined by . The regional approach showed large zonal asymmetry in ∆pCO 2 and FCO 2 estimates. Importantly, there was 15 a seasonal decoupling of the modes summer and winter interannual variability. Winter trends had a larger 10 year mode of variability compared to summer trends, which had a shorter 4-6 year mode. To understand this variability of FCO 2 , we separately assessed changes in summer and winter ∆pCO 2 and the drivers thereof. The dominant winter changes were driven by wind stress variability. Summer variability correlated well with chlorophyll-a variability where the latter had high concentrations. In 20 regions of low chlorophyll-a concentrations, wind stress and sea surface temperature were lower order drivers of ∆pCO 2 .