Oceanographic controls on Southern Ocean dimethyl sulfide distributions revealed by machine learning algorithms
Bibliographic record
Abstract
Abstract We 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".