Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions
©2019. The Authors. Dynamically similar regions of the global ocean are identified using a barotropic vorticity (BV) framework from a 20-year mean of the Estimating the Circulation and Climate of the Ocean state estimate at 1° resolution. An unsupervised machine learning algorithm, K-means, objectiv...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Geophysical Union (AGU)
2022
|
| Online Access: | https://hdl.handle.net/1721.1/141225 |
| _version_ | 1811085770783457280 |
|---|---|
| author | Sonnewald, Maike Wunsch, Carl Heimbach, Patrick |
| author_facet | Sonnewald, Maike Wunsch, Carl Heimbach, Patrick |
| author_sort | Sonnewald, Maike |
| collection | MIT |
| description | ©2019. The Authors. Dynamically similar regions of the global ocean are identified using a barotropic vorticity (BV) framework from a 20-year mean of the Estimating the Circulation and Climate of the Ocean state estimate at 1° resolution. An unsupervised machine learning algorithm, K-means, objectively clusters the standardized BV equation, identifying five unambiguous regimes. Cluster 1 covers 43 ± 3.3% of the ocean area. Surface and bottom stress torque are balanced by the bottom pressure torque and the nonlinear torque. Cluster 2 covers 24.8 ± 1.2%, where the beta effect balances the bottom pressure torque. Cluster 3 covers 14.6 ± 1.0%, characterized by a “Quasi-Sverdrupian” regime where the beta effect is balanced by the wind and bottom stress term. The small region of Cluster 4 has baroclinic dynamics covering 6.9 ± 2.9% of the ocean. Cluster 5 occurs primarily in the Southern Ocean. Residual “dominantly nonlinear” regions highlight where the BV approach is inadequate, found in areas of rough topography in the Southern Ocean and along western boundaries. |
| first_indexed | 2024-09-23T13:15:25Z |
| format | Article |
| id | mit-1721.1/141225 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:15:25Z |
| publishDate | 2022 |
| publisher | American Geophysical Union (AGU) |
| record_format | dspace |
| spelling | mit-1721.1/1412252022-03-17T03:18:50Z Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions Sonnewald, Maike Wunsch, Carl Heimbach, Patrick ©2019. The Authors. Dynamically similar regions of the global ocean are identified using a barotropic vorticity (BV) framework from a 20-year mean of the Estimating the Circulation and Climate of the Ocean state estimate at 1° resolution. An unsupervised machine learning algorithm, K-means, objectively clusters the standardized BV equation, identifying five unambiguous regimes. Cluster 1 covers 43 ± 3.3% of the ocean area. Surface and bottom stress torque are balanced by the bottom pressure torque and the nonlinear torque. Cluster 2 covers 24.8 ± 1.2%, where the beta effect balances the bottom pressure torque. Cluster 3 covers 14.6 ± 1.0%, characterized by a “Quasi-Sverdrupian” regime where the beta effect is balanced by the wind and bottom stress term. The small region of Cluster 4 has baroclinic dynamics covering 6.9 ± 2.9% of the ocean. Cluster 5 occurs primarily in the Southern Ocean. Residual “dominantly nonlinear” regions highlight where the BV approach is inadequate, found in areas of rough topography in the Southern Ocean and along western boundaries. 2022-03-16T16:51:28Z 2022-03-16T16:51:28Z 2019 2022-03-16T16:44:35Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/141225 Sonnewald, Maike, Wunsch, Carl and Heimbach, Patrick. 2019. "Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions." Earth and Space Science, 6 (5). en 10.1029/2018EA000519 Earth and Space Science Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf American Geophysical Union (AGU) Wiley |
| spellingShingle | Sonnewald, Maike Wunsch, Carl Heimbach, Patrick Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions |
| title | Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions |
| title_full | Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions |
| title_fullStr | Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions |
| title_full_unstemmed | Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions |
| title_short | Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions |
| title_sort | unsupervised learning reveals geography of global ocean dynamical regions |
| url | https://hdl.handle.net/1721.1/141225 |
| work_keys_str_mv | AT sonnewaldmaike unsupervisedlearningrevealsgeographyofglobaloceandynamicalregions AT wunschcarl unsupervisedlearningrevealsgeographyofglobaloceandynamicalregions AT heimbachpatrick unsupervisedlearningrevealsgeographyofglobaloceandynamicalregions |