Revealing the Impact of Global Heating on North Atlantic Circulation Using Transparent Machine Learning
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
The North Atlantic ocean is key to climate through its role in heat transport and storage. Climate models suggest that the circulation is weakening but the physical drivers of this change are poorly constrained. Here, the root mechanisms are revealed with the explicitly transparent machine learning (ML) method Tracking global Heating with Ocean Regimes (THOR). Addressing the fundamental question of the existence of dynamical coherent regions, THOR identifies these and their link to distinct currents and mechanisms such as the formation regions of deep water masses, and the location of the Gulf Stream and North Atlantic Current. Beyond a black box approach, THOR is engineered to elucidate its source of predictive skill rooted in physical understanding. A labeled data set is engineered using an explicitly interpretable equation transform and k‐means application to model data, allowing theoretical inference. A multilayer perceptron is then trained, explaining its skill using a combination of layerwise relevance propagation and theory. With abrupt CO 2 quadrupling, the circulation weakens due to a shift in deep water formation regions, a northward shift of the Gulf Stream and an eastward shift in the North Atlantic Current. If CO 2 is increased 1% yearly, similar but weaker patterns emerge influenced by natural variability. THOR is scalable and applicable to a range of models using only the ocean depth, dynamic sea level and wind stress, and could accelerate the analysis and dissemination of climate model data. THOR constitutes a step toward trustworthy ML called for within oceanography and beyond, as its predictions are physically tractable.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Deep learning and process understanding for data-driven Earth system science
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., & Prabhat (2019) · Nature · doi:10.1038/s41586-019-0912-1 · Cited by 5,673 · cited 2×
“climate models (Eyring et al., 2019; Reichstein et al., 2019; Schlund et al., 2020), while opening the “black box” often associated with ML applications.”
BackgroundOn Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · cited 1×
“A positive/negative relevance suggests that a feature contributes positively/ negatively to NN decision (Lapuschkin et al., 2015).”
Backgroundxarray: N-D labeled Arrays and Datasets in Python
Hoyer, S., & Hamman, J. (2017) · Journal of Open Research Software · doi:10.5334/jors.148 · Cited by 1,856
Explaining nonlinear classification decisions with deep taylor decomposition
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., & Müller, K.-R. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.11.008 · Cited by 1,357
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Slack, D., Hilgard, S., Jia, E., Singh, S., & Lakkaraju, H. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375830 · Cited by 900
Taking climate model evaluation to the next level
Eyring, V., Cox, P. M., Flato, G. M., Gleckler, P. J., Abramowitz, G., Caldwell, P., Collins, W. D., Gier, B. K., Hall, A. D., Hoffman, F. M., et al. (2019) · Nature Climate Change · doi:10.1038/s41558-018-0355-y · Cited by 748
Visualizing and Understanding Convolutional Networks
Zeiler, M. D., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1311.2901 · Cited by 522
Enhanced warming of the Northwest Atlantic Ocean under climate change
Saba, V. S., Griffies, S. M., Anderson, W. G., Winton, M., Alexander, M. A., Delworth, T. L., Hare, J. A., Harrison, M. J., Rosati, A., Vecchi, G. A., et al. (2016) · Journal of Geophysical Research: Oceans · doi:10.1002/2015jc011346 · Cited by 468 · cited 2×
“Assessing the source of the spread in AMOC weakening in CMIP5 points to a number of dynamics, and the weakening may have been underestimated (Saba et al., 2016).”
BackgroundUnderspecification Presents Challenges for Credibility in Modern Machine Learning
D'Amour, A., Heller, K., Moldovan, D., Adlam, B., Alipanahi, B., Beutel, A., Chen, C., Deaton, J., Eisenstein, J., Hoffman, M. D., et al. (2020) · arXiv · doi:10.48550/arxiv.2011.03395 · Cited by 398 · cited 4×
“A danger is that the NN model “underspecifies”, meaning that the given data leave enough ambiguity as to the true global minimum, that the NN model would not be generally applicable to the problem at hand (D’Amour et al., 2020).”
BackgroundMethodInfluential
Cited by
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science
Irrgang, C., Boers, N., Sonnewald, M., Barnes, E. A., Kadow, C., Staneva, J., & Saynisch-Wagner, J. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-021-00374-3 · Cited by 308
Self-citationInterpretable machine learning for weather and climate prediction: A review
Yang, R., Hu, J., Li, Z., Mu, J., Yu, T., Xia, J., Li, X., Dasgupta, A., & Xiong, H. (2024) · Atmospheric Environment · doi:10.1016/j.atmosenv.2024.120797 · Cited by 139
Materia, S., García, L. P., van Straaten, C., O, S., Mamalakis, A., Cavicchia, L., Coumou, D., de Luca, P., Kretschmer, M., & Donat, M. (2024) · WIREs Climate Change · doi:10.1002/wcc.914 · Cited by 130
Metadata
- Authors
- Sonnewald, M., & Lguensat, R.
- Venue
- Journal of Advances in Modeling Earth Systems
- Publisher
- American Geophysical Union (AGU)
- Published
- 2021-08
- Volume
- 13
- Issue
- 8
- ISSN
- 1942-2466 (ISSN-L)
- OpenAlex
- W3126640999
- Cited by
- 43
- References
- 13
- FWCI
- 4.31
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.