Toward generative machine learning for boosting ensembles of climate simulations
Bibliographic record
Abstract
Abstract Accurately quantifying uncertainty in predictions and projections arising from irreducible internal climate variability is critical for decision‐making. Such uncertainty is typically assessed using ensembles produced with climate models. However, computational constraints impose a trade‐off between generating large ensembles required for robust uncertainty estimation and increasing model resolution to better capture fine‐scale dynamics. Generative machine learning offers a promising pathway to alleviate these constraints. We develop a conditional Variational Autoencoder (cVAE) trained on a limited sample of climate simulations to generate arbitrary large ensembles. The approach is applied to output from monthly CMIP6 historical and scenario experiments produced with the Canadian Centre for Climate Modelling and Analysis' Earth system model CanESM5. We show that the cVAE model learns the underlying distribution of data and generates physically consistent samples that reproduce realistic low‐ and high‐moment statistics, including extremes. Compared with more sophisticated generative architectures, cVAEs offer mathematically transparent, interpretable, and computationally efficient framework. Their simplicity lead to some limitations, such as smooth outputs, spectral bias, and underdispersion, that we discuss along with mitigation strategies. Specifically, we show that incorporating output noise improves the representation of climate‐relevant multiscale variability, and propose a simple method to achieve this. We show that cVAE‐enhanced ensembles capture realistic global teleconnection patterns, even under climate conditions absent from training data. Finally, our results point to limitations in accurately capturing non‐Gaussianity in higher‐order moments. It remains to be addressed whether this is amendable via more expressive architectures and output noise treatment or remains a challenge with cVAEs more generally.
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 | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".