Oceanographic controls on Southern Ocean dimethyl sulfide distributions revealed by machine learning algorithms

Abstract

AbstractWe developed two machine learning models to map the Southern Ocean distribution of the climate‐active gas dimethyl sulfide (DMS) at 20 km resolution. Results obtained from ensembles of random forest regressions and artificial neural networks reproduce observed DMS distributions with significantly higher accuracy than traditional statistical techniques, and are less prone to biases and spatial distortions than existing interpolation‐based climatologies. Both models predict persistently low offshore DMS concentrations associated with the Antarctic circumpolar current, suggesting that wind‐driven overturning mixing is the dominant regional control on DMS distributions. In addition, 60% of the variance in DMS seasonality is explained by changes in mixed layer depth and sea surface temperature, with a significant correlation between DMS concentrations and sea‐ice cover in coastal waters. We further identify the tracer Si* (defined as ) as a potentially important predictor for regional DMS distributions in Southern Ocean waters. At finer scales, our models capture various oceanographic features, including eddies, hydrographic fronts and jets that appear to play a role in driving DMS variability. Our results yield an estimated Southern Ocean sea‐air DMS flux of 8.7 ± 2.1 Tg S integrated across the phytoplankton growing season (October to April), representing 30.8% of total global oceanic S emissions, and highlighting the region's importance to the marine sulfur cycle. Our work provides new insights into the drivers of spatial variability in Southern Ocean DMS concentrations and sea‐air fluxes, and their potential responses to future climate‐dependent changes.