Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate
Abstract The oceanic Meridional Overturning Circulation (MOC) plays a key role in the climate system, and monitoring its evolution is a scientific priority. Monitoring arrays have been established at several latitudes in the Atlantic Ocean, but other latitudes and oceans remain unmonitored for logis...
Published in: | Journal of Advances in Modeling Earth Systems |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
American Geophysical Union (AGU)
2023
|
Subjects: | |
Online Access: | https://doi.org/10.1029/2022MS003370 https://doaj.org/article/4ca5d254295a44efac7877a426a6e706 |
id |
ftdoajarticles:oai:doaj.org/article:4ca5d254295a44efac7877a426a6e706 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:4ca5d254295a44efac7877a426a6e706 2023-11-05T03:45:12+01:00 Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate Aviv Solodoch Andrew L. Stewart Andrew McC. Hogg Georgy E. Manucharyan 2023-04-01T00:00:00Z https://doi.org/10.1029/2022MS003370 https://doaj.org/article/4ca5d254295a44efac7877a426a6e706 EN eng American Geophysical Union (AGU) https://doi.org/10.1029/2022MS003370 https://doaj.org/toc/1942-2466 1942-2466 doi:10.1029/2022MS003370 https://doaj.org/article/4ca5d254295a44efac7877a426a6e706 Journal of Advances in Modeling Earth Systems, Vol 15, Iss 4, Pp n/a-n/a (2023) Meridional Overturning Circulation ocean circulation satellite sensing climate variability machine learning observing systems Physical geography GB3-5030 Oceanography GC1-1581 article 2023 ftdoajarticles https://doi.org/10.1029/2022MS003370 2023-10-08T00:34:04Z Abstract The oceanic Meridional Overturning Circulation (MOC) plays a key role in the climate system, and monitoring its evolution is a scientific priority. Monitoring arrays have been established at several latitudes in the Atlantic Ocean, but other latitudes and oceans remain unmonitored for logistical reasons. This study explores the possibility of inferring the MOC from globally‐available satellite measurements via machine learning (ML) techniques, using the ECCOV4 state estimate as a test bed. The methodological advantages of the present approach include the use purely of available satellite data, its applicability to multiple basins within a single ML framework, and the ML model simplicity (a feed‐forward fully connected neural network (NN) with small number of neurons). The ML model exhibits high skill in MOC reconstruction in the Atlantic, Indo‐Pacific, and Southern Oceans. The approach achieves a higher skill in predicting the model Southern Ocean abyssal MOC than has previously been achieved via a dynamically‐based approach. The skill of the model is quantified as a function of latitude in each ocean basin, and of the time scale of MOC variability. We find that ocean bottom pressure generally has the highest reconstruction skill potential, followed by zonal wind stress. We additionally test which combinations of variables are optimal. Furthermore, ML interpretability techniques are used to show that high reconstruction skill in the Southern Ocean is mainly due to (NN processing of) bottom pressure variability at a few prominent bathymetric ridges. Finally, the potential for reconstructing MOC strength estimates from real satellite measurements is discussed. Article in Journal/Newspaper Southern Ocean Directory of Open Access Journals: DOAJ Articles Journal of Advances in Modeling Earth Systems 15 4 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Meridional Overturning Circulation ocean circulation satellite sensing climate variability machine learning observing systems Physical geography GB3-5030 Oceanography GC1-1581 |
spellingShingle |
Meridional Overturning Circulation ocean circulation satellite sensing climate variability machine learning observing systems Physical geography GB3-5030 Oceanography GC1-1581 Aviv Solodoch Andrew L. Stewart Andrew McC. Hogg Georgy E. Manucharyan Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate |
topic_facet |
Meridional Overturning Circulation ocean circulation satellite sensing climate variability machine learning observing systems Physical geography GB3-5030 Oceanography GC1-1581 |
description |
Abstract The oceanic Meridional Overturning Circulation (MOC) plays a key role in the climate system, and monitoring its evolution is a scientific priority. Monitoring arrays have been established at several latitudes in the Atlantic Ocean, but other latitudes and oceans remain unmonitored for logistical reasons. This study explores the possibility of inferring the MOC from globally‐available satellite measurements via machine learning (ML) techniques, using the ECCOV4 state estimate as a test bed. The methodological advantages of the present approach include the use purely of available satellite data, its applicability to multiple basins within a single ML framework, and the ML model simplicity (a feed‐forward fully connected neural network (NN) with small number of neurons). The ML model exhibits high skill in MOC reconstruction in the Atlantic, Indo‐Pacific, and Southern Oceans. The approach achieves a higher skill in predicting the model Southern Ocean abyssal MOC than has previously been achieved via a dynamically‐based approach. The skill of the model is quantified as a function of latitude in each ocean basin, and of the time scale of MOC variability. We find that ocean bottom pressure generally has the highest reconstruction skill potential, followed by zonal wind stress. We additionally test which combinations of variables are optimal. Furthermore, ML interpretability techniques are used to show that high reconstruction skill in the Southern Ocean is mainly due to (NN processing of) bottom pressure variability at a few prominent bathymetric ridges. Finally, the potential for reconstructing MOC strength estimates from real satellite measurements is discussed. |
format |
Article in Journal/Newspaper |
author |
Aviv Solodoch Andrew L. Stewart Andrew McC. Hogg Georgy E. Manucharyan |
author_facet |
Aviv Solodoch Andrew L. Stewart Andrew McC. Hogg Georgy E. Manucharyan |
author_sort |
Aviv Solodoch |
title |
Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate |
title_short |
Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate |
title_full |
Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate |
title_fullStr |
Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate |
title_full_unstemmed |
Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate |
title_sort |
machine learning‐derived inference of the meridional overturning circulation from satellite‐observable variables in an ocean state estimate |
publisher |
American Geophysical Union (AGU) |
publishDate |
2023 |
url |
https://doi.org/10.1029/2022MS003370 https://doaj.org/article/4ca5d254295a44efac7877a426a6e706 |
genre |
Southern Ocean |
genre_facet |
Southern Ocean |
op_source |
Journal of Advances in Modeling Earth Systems, Vol 15, Iss 4, Pp n/a-n/a (2023) |
op_relation |
https://doi.org/10.1029/2022MS003370 https://doaj.org/toc/1942-2466 1942-2466 doi:10.1029/2022MS003370 https://doaj.org/article/4ca5d254295a44efac7877a426a6e706 |
op_doi |
https://doi.org/10.1029/2022MS003370 |
container_title |
Journal of Advances in Modeling Earth Systems |
container_volume |
15 |
container_issue |
4 |
_version_ |
1781706829462503424 |