Adjustment of Decadal Ocean Carbon Sink Predictions Using Deep Learning
Bibliographic record
Abstract
Abstract We implement an encoder–decoder artificial neural network (ANN) to postprocess decadal predictions of gridded air–sea carbon dioxide (CO 2 ) flux produced with an Earth system model (ESM) having prescribed CO 2 emissions. Decadal predictions are initialized by constraining the ESM with observational data and drift toward the model unconstrained climatology. The resulting biased forecasts require adjustments to make the predictions usable. By leveraging the flexibility of the ANN to learn the complex nonlinear relationship between raw forecasts and verifying data, and its ability to learn from nonlocal spatial errors, we show that the ANN-based adjustment outperforms standard bias and linear trend corrections for the first 3 years in the forecast, both in terms of spatial and temporal accuracy. The squared root of the globally integrated mean square error is approximately 0.5 PgC yr −1 for the first year of the forecast, which is about half the value from the alternative methods, and remains well below 1.0 PgC yr −1 for the first 5 years. The globally averaged anomaly correlation coefficient is above 0.5 and remains above 0.3 for the first 4 years of the forecast, whereas the alternative corrections score about 0.3 or less at all lead years. The methodology is tested with emission-driven decadal predictions produced with the Canadian Centre for Climate Modelling and Analysis forecasting system, which contribute to the Global Carbon Budget annual update. Significance Statement Deep learning has been used for postprocessing numerical weather predictions, but applications to longer-range forecasts are less common. Forecast postprocessing is a necessary step toward making predictions usable, since climate models are imperfect representations of the climate system and the forecast initial conditions are often erroneous. A deep learning (DL)-based model is implemented to adjust near-term predictions of ocean carbon sinks produced with Fifth Generation Canadian ESM (CanESM5), which couples a physics-based climate model with an interactive carbon cycle. These predictions contribute to the Global Carbon Budget annual update that tracks the distribution of global carbon emissions and sinks to inform progress toward the goals of the Paris Agreement. The DL-based postprocessing model outperforms standard correction methods for several years in the forecast, leading to more accurate near-term predictions of the ocean carbon sink.
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 | 0.000 | 0.000 |
| 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 | 0.000 | 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".