Comment on bg-2021-171

Daniel Ford and coauthors use a feed-forward neural network (FNN) to estimate surface ocean partial pressure of CO2 (pCO2(sw)) in the South Atlantic Ocean. The authors test satellite chlorophyll a (Chl a), satellite-derived net primary production (NPP), and satellitederived net community production (NCP) as biological predictors in the neural network to determine which produces the most accurate pCO2(sw). They find that using satellitederived NCP as a predictor in the FNN scheme produces the most reliable pCO2(sw) reconstructions for the Amazon River plume and upwelling regions. They also show that, among the neural networks examined, the NCP-based FNN (SA-FNNNCP) has the highest capacity for improved performance under scenarios of reduced uncertainty. For these reasons, the authors suggest that using satellite-derived NCP as a proxy for biological effects in surface reconstructions of pCO2(sw) may be desirable going forward. Finally, Ford et al. find that SA-FNNNCP indicates that the South Atlantic Ocean is a source of CO2 to the atmosphere, whereas the FNNs with Chl a or NPP as a biological proxy or with no biological proxy all indicate that the South Atlantic Ocean is a CO2 sink.


General Comments
Daniel Ford and coauthors use a feed-forward neural network (FNN) to estimate surface ocean partial pressure of CO 2 (pCO 2(sw) ) in the South Atlantic Ocean. The authors test satellite chlorophyll a (Chl a), satellite-derived net primary production (NPP), and satellitederived net community production (NCP) as biological predictors in the neural network to determine which produces the most accurate pCO 2(sw) . They find that using satellitederived NCP as a predictor in the FNN scheme produces the most reliable pCO 2(sw) reconstructions for the Amazon River plume and upwelling regions. They also show that, among the neural networks examined, the NCP-based FNN (SA-FNN NCP ) has the highest capacity for improved performance under scenarios of reduced uncertainty. For these reasons, the authors suggest that using satellite-derived NCP as a proxy for biological effects in surface reconstructions of pCO 2(sw) may be desirable going forward. Finally, Ford et al. find that SA-FNN NCP indicates that the South Atlantic Ocean is a source of CO 2 to the atmosphere, whereas the FNNs with Chl a or NPP as a biological proxy or with no biological proxy all indicate that the South Atlantic Ocean is a CO 2 sink. This manuscript fits well within the scope of Biogeosciences: it explores the implications of choosing different biological predictor variables in estimation schemes for sea surface pCO 2 and demonstrates the consequences of those choices for carbon cycling calculations. It is based on the very logical assumption that NCP, which captures all biological processes that modulate CO 2 concentrations in the surface ocean, should serve as a better biological predictor than Chl a for estimates of pCO 2(sw) . This work has the potential to shift the way in which studies of this nature are typically performed. That shift could result in better representations of sea surface pCO 2 in regions that are highly influenced by biological processes, regions that may contribute a disproportionately large fraction of global CO 2 flux across the air-sea interface.
In general, the manuscript is well-written and the figures and tables are effective in communicating the results. The manuscript addresses an important aspect of the global carbon cycle and is forward-thinking in its assessment of algorithm performance in response to reduced uncertainties. A couple concerns of mine, however, include the lack of quantitative or graphical support for the conclusion that SA-FNN NCP produces the best representations of pCO 2(sw) compared to the other FNNs (section 4.2) and the shortage of further investigation into one of the manuscript's major conclusions: that SA-FNN NCP flips the South Atlantic from a CO 2 sink to a CO 2 source. More discussion of these concerns as well as some minor comments can be found in the following sections.

Performance of SA-FNN NCP :
I mainly would like to see some quantitative or graphical evidence supporting the assertion that SA-FNN NCP outperforms the other FNNs in the Amazon River plume and upwelling regions. Figure 3 shows differences between the mean climatologies given by different FNNs at different stations and Figure 4 shows that some of these differences are statistically significant (in comparison to SA-FNN NCP ), but neither says anything about the performance of any one FNN. That is left to the more qualitative discussion in section 4.2 that compares general patterns in pCO 2(sw) from previous studies to those indicated by the FNNs.
The points made in that qualitative discussion are compelling and certainly do appear to indicate superior performance of SA-FNN NCP in the Amazon River plume, Benguela upwelling system, and equatorial regions. However, following along with the discussion takes some effort from the reader, and a lot of flipping back and forth between the text and Figure 3. A new figure comparing FNN results to some pCO 2(sw) observations or a brief presentation of some relevant statistics would be more compelling. In particular, for example, pCO 2(sw) data from the moorings at 6° S 10° W and/or 8° N 38° W could be plotted along with the SA-FNNs results to demonstrate the superior performance of SA-FNN NCP .
I think this area is especially important to improve upon given that the bulk error statistics (Figures 2, A1, and A2) indicate SA-FNN NCP to be the least accurate of the three FNNs that have biological predictors.

Sink to source transition:
The change in the cumulative regional sink from -7 Tg C yr -1 with the NPP-based FNN (SA-FNN NPP ) to +14 Tg C yr -1 with SA-FNN NCP seems rather drastic, and I'm curious to know more about why such a significant change occurs. The reason is not obvious from Figure 5 alone. If indeed the transition occurs because high outgassing events in biologicallycontrolled regions with relatively limited geographic extent are captured by SA-FNN NCP but not the other FNNs, as is suggested in lines 399-412, that point should be demonstrated and emphasized more explicitly.
This could perhaps be explored by breaking down the annual fluxes into different subregions (e.g., the biogeochemical provinces from Figure 1) and/or into average monthly fluxes to clearly show the spatial and/or temporal differences that lead to the significant discrepancy between SA-FNN NPP and SA-FNN NCP . This information could be presented in a table, figure, or even just in the body of the manuscript (like the geographic comparison in lines 419-420 between SA-FNN NCP and the Watson et al. [2020] product).

Callbacks in Discussion section:
In general, because the work is presented in separate Results and Discussion sections, I'd make sure to refer specifically to figures, tables, and statements from the Results section when commenting on them in the Discussion section. This will make it easier for the reader to follow what exactly is being discussed without having to determine for themselves where those results are presented. I mention a couple specific instances of this in the following section.

Minor Comments and Technical Corrections
Line 17: There shouldn't be a comma after pCO 2(sw) .
Lines 45-48: I'd split this sentence into two; there's a lot of information here and it's a bit difficult to follow as written.  Line 189: I'd rephrase this as "A non-parametric Kruskal-Wallis was used to test for…" Line 232: Should the accuracy here for SA-FNN NCP be 21.68 matm, like in line 235 and Figure 2?
Lines 259-260 (and elsewhere): Should be "minimum" instead of "minima" and "maximum" instead of "maxima", or remove the article "a". Minimum/maximum are singular whereas minima/maxima are plural. Line 295: "Satellite NCP is reliant on NPP as input" This has already been implied in line 288, so I'd remove the statement here or move it to the previous paragraph. The point is well made, it's just that the writing is a bit repetitive here.
Line 298-299: "This showed that reducing in situ NCP uncertainties provided the greatest reduction in pCO 2(sw) RMSD, which was three times the reduction achievable using Chl a." I'd make sure to refer the reader to Tables 2 and 3 so they're not searching for this result.
Lines 328-329: "The stations (Fig. 1) represent locations of previous studies into in situ pCO 2(sw) variability in the South Atlantic Ocean and allow comparisons with literature values." This point should be made earlier, in the Methods section, perhaps around line 182.