Abstract. Over the last decade, advanced statistical inference and machine learning have been used to fill the gaps in sparse surface ocean CO2 measurements (Rödenbeck et al., 2015). The estimates from these methods have been used to constrain seasonal, interannual and decadal variability in sea–air CO2 fluxes and the drivers of these changes (Landschützer et al., 2015, 2016; Gregor et al., 2018). However, it is also becoming clear that these methods are converging towards a common bias and root mean square error (RMSE) boundary: “the wall”, which suggests that pCO2 estimates are now limited by both data gaps and scale-sensitive observations. Here, we analyse this problem by introducing a new gap-filling method, an ensemble average of six machine-learning models (CSIR-ML6 version 2019a, Council for Scientific and Industrial Research – Machine Learning ensemble with Six members), where each model is constructed with a two-step clustering-regression approach. The ensemble average is then statistically compared to well-established methods. The ensemble average, CSIR-ML6, has an RMSE of 17.16 µatm and bias of 0.89 µatm when compared to a test dataset kept separate from training procedures. However, when validating our estimates with independent datasets, we find that our method improves only incrementally on other gap-filling methods. We investigate the differences between the methods to understand the extent of the limitations of gap-filling estimates of pCO2. We show that disagreement between methods in the South Atlantic, southeastern Pacific and parts of the Southern Ocean is too large to interpret the interannual variability with confidence. We conclude that improvements in surface ocean pCO2 estimates will likely be incremental with the optimisation of gap-filling methods by (1) the inclusion of additional clustering and regression variables (e.g. eddy kinetic energy), (2) increasing the sampling resolution and (3) successfully incorporating pCO2 estimates from alternate platforms (e.g. floats, gliders) into existing machine-learning approaches.

Over the last decade, advanced statistical inference and machine learning have been used to fill the gaps in sparse surface ocean CO 2 measurements . The estimates from these methods have been used to constrain seasonal, interannual and decadal variability in seaair CO 2 fluxes and the drivers of these changes , 2016, Gregor et al. 2018). However, it is also becoming clear that these methods are converging towards a common bias and RMSE boundary: the wall , which suggests that p CO 2 estimates are now limited by both data gaps and scalesensitive observations. Here, we analyse this problem by introducing a new gapfilling method, an ensemble of six machine learning models (CSIRML6 version 2019a), where each model is constructed with a twostep clusteringregression approach.The ensemble is then statistically compared to wellestablished methods. The ensemble, CSIRML6, has an RMSE of 17.16 µatm and bias of 0.89 µatm when compared to a testdataset kept separate from training procedures. However, when validating our estimates with independent datasets, we find that our method improves only incrementally on other gapfilling methods. We investigate the differences between the methods to understand the extent of the limitations of gapfilling estimates of p CO 2 . We show that disagreement between methods in the South Atlantic, southeastern Pacific and parts of the Southern Ocean are too large to interpret the interannual variability with confidence. We conclude that improvements in surface ocean p CO 2 estimates will likely be incremental with the optimisation of gapfilling methods by (1) the inclusion of additional clustering and regression variables ( e.g. eddy kinetic energy), (2) increasing the sampling resolution. Larger improvements will only be realised with an increase in CO 2 observational coverage, particularly in today's poorly sampled areas. 1Geosci. Model Dev. Discuss., https://doi.

The subpolar Southern Ocean is a critical region where CO2 outgassing influences the global mean air-sea CO2 flux (FCO2). However, the processes controlling the outgassing remain elusive. We show, using a multi-glider dataset combining FCO2 and ocean turbulence, that the air-sea gradient of CO2 (∆pCO2) is modulated by synoptic storm-driven ocean variability (20 µatm, 1–10 days) through two processes. Ekman transport explains 60% of the variability, and entrainment drives strong episodic CO2 outgassing events of 2–4 mol m−2 yr−1. Extrapolation across the subpolar Southern Ocean using a process model shows how ocean fronts spatially modulate synoptic variability in ∆pCO2 (6 µatm2 average) and how spatial variations in stratification influence synoptic entrainment of deeper carbon into the mixed layer (3.5 mol m−2 yr−1 average). These results not only constrain aliased-driven uncertainties in FCO2 but also the effects of synoptic variability on slower seasonal or longer ocean physics-carbon dynamics.

No abstract