Reducing uncertainty in the global carbon budget requires better quantification of ocean CO2 uptake and its temporal variability. Several methodologies for reconstructing air-sea CO2 exchange from sparse pCO2 observations indicate larger decadal variability than estimated using ocean models. We develop a new application of multiple Large Ensemble Earth system models to assess these reconstructions’ ability to estimate spatiotemporal variability. With our Large Ensemble Testbed, pCO2 fields from 25 ensemble members each of four independent Earth system models are subsampled as the observations and the reconstruction is performed as it would be with real- world observations. The power of a testbed is that the perfect reconstruction is known for each of the 100 original model fields; thus, reconstruction skill can be comprehensively assessed. We find that a commonly used neural-network approach can skillfully reconstruct air-sea CO2 fluxes when and where it is trained with sufficient data. Flux bias is low for the global mean and Northern Hemisphere, but can be regionally high in the Southern Hemisphere. The phase and amplitude of the seasonal cycle are accurately reconstructed outside of the tropics, but longer-term variations are reconstructed with only moderate skill. For Southern Ocean decadal variability, insufficient sampling leads to a 39% [15%:58%, interquartile range] overestimation of amplitude, and phasing is only moderately correlated with known truth (r=0.54 [0.46:0.63]). Globally, the amplitude of decadal variability is overestimated by 21% [3%:34%]. Machine learning, when supplied with sufficient data, can skillfully reconstruct ocean properties. However, data sparsity remains a fundamental limitation to quantification of decadal variability in the ocean carbon sink.

The ocean has absorbed the equivalent of 39% of industrial-age fossil carbon emissions, significantly modulating the growth rate of atmospheric CO2 and its associated impacts on climate. Despite the importance of the ocean carbon sink to climate, our understanding of the causes of its interannual-to-decadal variability remains limited. This hinders our ability to attribute its past behavior and project its future. A key period of interest is the 1990s, when the ocean carbon sink did not grow as expected. Previous explanations of this behavior have focused on variability internal to the ocean or associated with coupled atmosphere/ocean modes. Here, we use an idealized upper ocean box model to illustrate that two external forcings are sufficient to explain the pattern and magnitude of sink variability since the mid-1980s. First, the global-scale reduction in the decadal-average ocean carbon sink in the 1990s is attributable to the slowed growth rate of atmospheric pCO2. The acceleration of atmospheric pCO2 growth after 2001 drove recovery of the sink. Second, the global sea surface temperature response to the 1991 eruption of Mt Pinatubo explains the timing of the global sink within the 1990s. These results are consistent with previous experiments using ocean hindcast models with and without forcing from variable atmospheric pCO2 and climate variability. The fact that variability in the growth rate of atmospheric pCO2 directly imprints on the ocean sink implies that there will be an immediate reduction in ocean carbon uptake as atmospheric pCO2 responds to cuts in anthropogenic emissions.