Regionalizing the sea-level budget with machine learning techniques
<p>Attribution of sea-level change to its different drivers is typically done using a sea-level budget approach. While the global mean sea-level budget is considered closed, closing the budget on a finer spatial scale is more complicated due to, for instance, limitations in our observational s...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-01-01
|
| Series: | Ocean Science |
| Online Access: | https://os.copernicus.org/articles/19/17/2023/os-19-17-2023.pdf |
| _version_ | 1797951949138558976 |
|---|---|
| author | C. M. L. Camargo C. M. L. Camargo R. E. M. Riva T. H. J. Hermans T. H. J. Hermans E. M. Schütt M. Marcos I. Hernandez-Carrasco A. B. A. Slangen |
| author_facet | C. M. L. Camargo C. M. L. Camargo R. E. M. Riva T. H. J. Hermans T. H. J. Hermans E. M. Schütt M. Marcos I. Hernandez-Carrasco A. B. A. Slangen |
| author_sort | C. M. L. Camargo |
| collection | DOAJ |
| description | <p>Attribution of sea-level change to its different drivers is typically done using a sea-level budget approach. While the global mean sea-level budget is considered closed, closing the budget on a finer spatial scale is more complicated due to, for instance, limitations in our observational system and the spatial processes contributing to regional sea-level change.
Consequently, the regional budget has been mainly analysed on a basin-wide scale.
Here we investigate the sea-level budget at sub-basin scales, using two machine learning techniques to extract domains of coherent sea-level variability: a neural network approach (self-organizing map, SOM) and a network detection approach (<span class="inline-formula"><i>δ</i></span>-MAPS).
The extracted domains provide more spatial detail within the ocean basins and indicate how sea-level variability is connected among different regions.
Using these domains we can close, within 1<span class="inline-formula"><i>σ</i></span> uncertainty, the sub-basin regional sea-level budget from 1993–2016 in 100 % and 76 % of the SOM and <span class="inline-formula"><i>δ</i></span>-MAPS regions, respectively.
Steric variations dominate the temporal sea-level variability and determine a significant part of the total regional change.
Sea-level change due to mass exchange between ocean and land has a relatively homogeneous contribution to all regions. In highly dynamic regions (e.g. the Gulf Stream region) the dynamic mass redistribution is significant.
Regions where the budget cannot be closed highlight processes that are affecting sea level but are not well captured by the observations, such as the influence of western boundary currents.
The use of the budget approach in combination with machine learning techniques leads to new insights into regional sea-level variability and its drivers.</p> |
| first_indexed | 2024-04-10T22:38:38Z |
| format | Article |
| id | doaj.art-a0fdaa3468e249d28ee8cdf4f3f2937f |
| institution | Directory Open Access Journal |
| issn | 1812-0784 1812-0792 |
| language | English |
| last_indexed | 2024-04-10T22:38:38Z |
| publishDate | 2023-01-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Ocean Science |
| spelling | doaj.art-a0fdaa3468e249d28ee8cdf4f3f2937f2023-01-16T09:09:11ZengCopernicus PublicationsOcean Science1812-07841812-07922023-01-0119174110.5194/os-19-17-2023Regionalizing the sea-level budget with machine learning techniquesC. M. L. Camargo0C. M. L. Camargo1R. E. M. Riva2T. H. J. Hermans3T. H. J. Hermans4E. M. Schütt5M. Marcos6I. Hernandez-Carrasco7A. B. A. Slangen8Department of Estuarine and Delta Systems, NIOZ Royal Netherlands Institute for Sea Research, Yerseke, The NetherlandsDepartment of Geoscience and Remote Sensing, Delft University of Technology, Delft, The NetherlandsDepartment of Geoscience and Remote Sensing, Delft University of Technology, Delft, The NetherlandsDepartment of Estuarine and Delta Systems, NIOZ Royal Netherlands Institute for Sea Research, Yerseke, The NetherlandsDepartment of Geoscience and Remote Sensing, Delft University of Technology, Delft, The NetherlandsDepartment of Geography, Kiel University, Kiel, GermanyMediterranean Institute for Advanced Studies (IMEDEA), Spanish National Research Council – University of the Balearic Islands (CSIC-UIB), Esporles, SpainMediterranean Institute for Advanced Studies (IMEDEA), Spanish National Research Council – University of the Balearic Islands (CSIC-UIB), Esporles, SpainDepartment of Estuarine and Delta Systems, NIOZ Royal Netherlands Institute for Sea Research, Yerseke, The Netherlands<p>Attribution of sea-level change to its different drivers is typically done using a sea-level budget approach. While the global mean sea-level budget is considered closed, closing the budget on a finer spatial scale is more complicated due to, for instance, limitations in our observational system and the spatial processes contributing to regional sea-level change. Consequently, the regional budget has been mainly analysed on a basin-wide scale. Here we investigate the sea-level budget at sub-basin scales, using two machine learning techniques to extract domains of coherent sea-level variability: a neural network approach (self-organizing map, SOM) and a network detection approach (<span class="inline-formula"><i>δ</i></span>-MAPS). The extracted domains provide more spatial detail within the ocean basins and indicate how sea-level variability is connected among different regions. Using these domains we can close, within 1<span class="inline-formula"><i>σ</i></span> uncertainty, the sub-basin regional sea-level budget from 1993–2016 in 100 % and 76 % of the SOM and <span class="inline-formula"><i>δ</i></span>-MAPS regions, respectively. Steric variations dominate the temporal sea-level variability and determine a significant part of the total regional change. Sea-level change due to mass exchange between ocean and land has a relatively homogeneous contribution to all regions. In highly dynamic regions (e.g. the Gulf Stream region) the dynamic mass redistribution is significant. Regions where the budget cannot be closed highlight processes that are affecting sea level but are not well captured by the observations, such as the influence of western boundary currents. The use of the budget approach in combination with machine learning techniques leads to new insights into regional sea-level variability and its drivers.</p>https://os.copernicus.org/articles/19/17/2023/os-19-17-2023.pdf |
| spellingShingle | C. M. L. Camargo C. M. L. Camargo R. E. M. Riva T. H. J. Hermans T. H. J. Hermans E. M. Schütt M. Marcos I. Hernandez-Carrasco A. B. A. Slangen Regionalizing the sea-level budget with machine learning techniques Ocean Science |
| title | Regionalizing the sea-level budget with machine learning techniques |
| title_full | Regionalizing the sea-level budget with machine learning techniques |
| title_fullStr | Regionalizing the sea-level budget with machine learning techniques |
| title_full_unstemmed | Regionalizing the sea-level budget with machine learning techniques |
| title_short | Regionalizing the sea-level budget with machine learning techniques |
| title_sort | regionalizing the sea level budget with machine learning techniques |
| url | https://os.copernicus.org/articles/19/17/2023/os-19-17-2023.pdf |
| work_keys_str_mv | AT cmlcamargo regionalizingthesealevelbudgetwithmachinelearningtechniques AT cmlcamargo regionalizingthesealevelbudgetwithmachinelearningtechniques AT remriva regionalizingthesealevelbudgetwithmachinelearningtechniques AT thjhermans regionalizingthesealevelbudgetwithmachinelearningtechniques AT thjhermans regionalizingthesealevelbudgetwithmachinelearningtechniques AT emschutt regionalizingthesealevelbudgetwithmachinelearningtechniques AT mmarcos regionalizingthesealevelbudgetwithmachinelearningtechniques AT ihernandezcarrasco regionalizingthesealevelbudgetwithmachinelearningtechniques AT abaslangen regionalizingthesealevelbudgetwithmachinelearningtechniques |