Abstract. Resolving and understanding the drivers of variability of CO 2 in the Southern Ocean and its potential climate feedback is one of the major scientific challenges of the ocean-climate community. Here we use a regional approach on empirical estimates of pCO 2 to understand the role that seasonal variability has in long-term CO 2 changes in the Southern Ocean. Machine learning has become the preferred empirical modelling tool to interpolate time-and locationrestricted ship measurements of pCO 2 . In this study we use an ensemble of three machine-learning products: support vector regression (SVR) and random forest regression (RFR) from , and the self-organising-map feedforward neural network (SOM-FFN) method from Landschützer et al. (2016). The interpolated estimates of pCO 2 are separated into nine regions in the Southern Ocean defined by basin (Indian, Pacific, and Atlantic) and biomes (as defined by Fay and McKinley, 2014a). The regional approach shows that, while there is good agreement in the overall trend of the products, there are periods and regions where the confidence in estimated pCO 2 is low due to disagreement between the products. The regional breakdown of the data highlighted the seasonal decoupling of the modes for summer and winter interannual variability. Winter interannual variability had a longer mode of variability compared to summer, which varied on a 4-6-year timescale. We separate the analysis of the pCO 2 and its drivers into summer and winter. We find that understanding the variability of pCO 2 and its drivers on shorter timescales is critical to resolving the long-term variability of pCO 2 . Results show that pCO 2 is rarely driven by thermodynamics during winter, but rather by mixing and stratification due to the stronger correlation of pCO 2 variability with mixed layer depth. Summer pCO 2 variability is consistent with chlorophyll a variability, where higher concentrations of chlorophyll a correspond with lower pCO 2 concentrations. In regions of low chlorophyll a concentrations, wind stress and sea surface temperature emerged as stronger drivers of pCO 2 . In summary we propose that sub-decadal variability is explained by summer drivers, while winter variability contributes to the long-term changes associated with the SAM. This approach is a useful framework to assess the drivers of pCO 2 but would greatly benefit from improved estimates of pCO 2 and a longer time series.