High‐Resolution Neural Network Demonstrates Strong CO 2 Source‐Sink Juxtaposition in the Coastal Zone

• Published in: Journal of geophysical research. Oceans 2024-07, Vol.129 (7)
• Main Authors: Duke, P. J., Hamme, R. C., Ianson, D., Landschützer, P., Swart, N. C., Covert, P. A.
• Format: Article
• Language: English
• ISSN: 2169-9275; 2169-9291
• DOI: 10.1029/2024JC021134

The role of coastal oceans in regulating atmospheric carbon dioxide remains poorly quantified and understood. Here, we use a two‐step neural network approach to generate estimates from sparse observational data in the coastal Northeast Pacific Ocean at an unprecedented spatial resolution of 1/12° with coverage in the nearshore (0–25 km offshore). We compiled partial pressure of carbon dioxide ( p CO 2 ) observations as well as a range of predictor variables including satellite‐based and physical oceanographic reanalysis products. With the predictor variables representing processes affecting p CO 2 , we created non‐linear relationships to interpolate observations from 1998 to 2019. Compared to in situ shipboard and mooring observations, our coastal p CO 2 product captures broad spatial patterns and seasonal cycle variability well. A sensitivity analysis identifies that the parameters responsible for the neural network's ability to capture regional p CO 2 variability are associated with mechanistic processes, including mixed layer deepening, mesoscale eddies, and gyre upwelling. Using wind speed and atmospheric CO 2 , we calculated air‐sea CO 2 fluxes. We report an anticorrelation between annual air‐sea CO 2 flux and its seasonal amplitude with the relationship driven by circulation, opposing seasonal upwelling/relaxation versus downwelling, and the effects of winter mixing and primary productivity. We show that the inclusion of nearshore net outgassing fluxes lowers the overall regional net flux. Overall, our results suggest that the region is a net sink (−0.7 mol m −2  yr −1 ) for atmospheric CO 2 with trends indicating increasing oceanic uptake due to strong connectivity to subsurface waters. The importance of the coastal ocean as a hub of exchange for carbon between terrestrial ecosystems, the open ocean, and the atmosphere is still unclear. In this study, we investigate how much carbon dioxide moves between the ocean and the atmosphere in the coastal Northeast Pacific. We use a mathematical technique (i.e., machine learning) to transform limited observational data to a high‐resolution estimate of this exchange across the entire region. We found this method effectively captured the big picture patterns and seasonal changes in ocean carbon dioxide levels. We report that the coastal Northeast Pacific absorbs slightly more carbon dioxide than it releases, helping regulate atmospheric levels of this greenhouse gas. However, there are large differences region