Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions
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 sta...
Published in: | Earth and Space Science |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
American Geophysical Union (AGU)
2019
|
Subjects: | |
Online Access: | https://doi.org/10.1029/2018EA000519 https://doaj.org/article/13e5410efce740888fcb96e91978a5b0 |
id |
ftdoajarticles:oai:doaj.org/article:13e5410efce740888fcb96e91978a5b0 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:13e5410efce740888fcb96e91978a5b0 2023-05-15T18:24:57+02:00 Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions Maike Sonnewald Carl Wunsch Patrick Heimbach 2019-05-01T00:00:00Z https://doi.org/10.1029/2018EA000519 https://doaj.org/article/13e5410efce740888fcb96e91978a5b0 EN eng American Geophysical Union (AGU) https://doi.org/10.1029/2018EA000519 https://doaj.org/toc/2333-5084 2333-5084 doi:10.1029/2018EA000519 https://doaj.org/article/13e5410efce740888fcb96e91978a5b0 Earth and Space Science, Vol 6, Iss 5, Pp 784-794 (2019) machine learning global patterns ocean dynamics big data ocean modeling physical oceanography Astronomy QB1-991 Geology QE1-996.5 article 2019 ftdoajarticles https://doi.org/10.1029/2018EA000519 2022-12-31T06:53:36Z 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. Article in Journal/Newspaper Southern Ocean Directory of Open Access Journals: DOAJ Articles Southern Ocean Earth and Space Science 6 5 784 794 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
machine learning global patterns ocean dynamics big data ocean modeling physical oceanography Astronomy QB1-991 Geology QE1-996.5 |
spellingShingle |
machine learning global patterns ocean dynamics big data ocean modeling physical oceanography Astronomy QB1-991 Geology QE1-996.5 Maike Sonnewald Carl Wunsch Patrick Heimbach Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions |
topic_facet |
machine learning global patterns ocean dynamics big data ocean modeling physical oceanography Astronomy QB1-991 Geology QE1-996.5 |
description |
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. |
format |
Article in Journal/Newspaper |
author |
Maike Sonnewald Carl Wunsch Patrick Heimbach |
author_facet |
Maike Sonnewald Carl Wunsch Patrick Heimbach |
author_sort |
Maike Sonnewald |
title |
Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions |
title_short |
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_sort |
unsupervised learning reveals geography of global ocean dynamical regions |
publisher |
American Geophysical Union (AGU) |
publishDate |
2019 |
url |
https://doi.org/10.1029/2018EA000519 https://doaj.org/article/13e5410efce740888fcb96e91978a5b0 |
geographic |
Southern Ocean |
geographic_facet |
Southern Ocean |
genre |
Southern Ocean |
genre_facet |
Southern Ocean |
op_source |
Earth and Space Science, Vol 6, Iss 5, Pp 784-794 (2019) |
op_relation |
https://doi.org/10.1029/2018EA000519 https://doaj.org/toc/2333-5084 2333-5084 doi:10.1029/2018EA000519 https://doaj.org/article/13e5410efce740888fcb96e91978a5b0 |
op_doi |
https://doi.org/10.1029/2018EA000519 |
container_title |
Earth and Space Science |
container_volume |
6 |
container_issue |
5 |
container_start_page |
784 |
op_container_end_page |
794 |
_version_ |
1766206007921344512 |