Estimating marine carbon uptake in the northeast Pacific using a neural network approach
Bibliographic record
Abstract
Abstract. The global ocean takes up nearly a quarter of anthropogenic CO2 emissions annually, but the variability in this uptake at regional scales remains poorly understood. Here we use a neural network approach to interpolate sparse observations, creating a monthly gridded seawater partial pressure of CO2 (pCO2) data product from January 1998 to December 2019, at 1/12∘ × 1/12∘ spatial resolution, in the northeast Pacific open ocean, a net sink region. The data product (ANN-NEP; NCEI Accession 0277836) was created from pCO2 observations within the 2021 version of the Surface Ocean CO2 Atlas (SOCAT) and a range of predictor variables acting as proxies for processes affecting pCO2 to create nonlinear relationships to interpolate observations at a spatial resolution 4 times greater than leading global products and with better overall performance. In moving to a higher resolution, we show that the internal division of training data is the most important parameter for reducing overfitting. Using our pCO2 product, wind speed, and atmospheric CO2, we evaluate air–sea CO2 flux variability. On sub-decadal to decadal timescales, we find that the upwelling strength of the subpolar Alaskan Gyre, driven by large-scale atmospheric forcing, acts as the primary control on air–sea CO2 flux variability (r2=0.93, p<0.01). In the northern part of our study region, divergence from atmospheric CO2 is enhanced by increased local wind stress curl, enhancing upwelling and entrainment of naturally CO2-rich subsurface waters, leading to decade-long intervals of strong winter outgassing. During recent Pacific marine heat waves from 2013 on, we find enhanced atmospheric CO2 uptake (by as much as 45 %) due to limited wintertime entrainment. Our product estimates long-term surface ocean pCO2 increase at a rate below the atmospheric trend (1.4 ± 0.1 µatm yr−1) with the slowest increase in the center of the subpolar gyre where there is strong interaction with subsurface waters. This mismatch suggests the northeast Pacific Ocean sink for atmospheric CO2 may be increasing.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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 teacher head, 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".