Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks
Accepted for publication in IEEE IGARSS 2020 conference The upcoming Surface Water Ocean Topography (SWOT) satellite altimetry mission is expected to yield two-dimensional high-resolution measurements of Sea Surface Height (SSH), thus allowing for a better characterization of the mesoscale and subme...
Main Authors: | , , , , , , , |
---|---|
Other Authors: | , , |
Format: | Report |
Language: | English |
Published: |
HAL CCSD
2020
|
Subjects: | |
Online Access: | https://hal.archives-ouvertes.fr/hal-03084229 |
id |
ftccsdartic:oai:HAL:hal-03084229v1 |
---|---|
record_format |
openpolar |
spelling |
ftccsdartic:oai:HAL:hal-03084229v1 2023-05-15T17:33:19+02:00 Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks LGUENSAT, Redouane Fablet, Ronan Sommer, Julien Le Metref, Sammy Cosme, Emmanuel Ouenniche, Kaouther Drumetz, Lucas Gula, Jonathan Institut des Géosciences de l’Environnement (IGE) Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ) Université Grenoble Alpes (UGA) 2020-12-20 https://hal.archives-ouvertes.fr/hal-03084229 en eng HAL CCSD info:eu-repo/semantics/altIdentifier/arxiv/2005.01090 hal-03084229 https://hal.archives-ouvertes.fr/hal-03084229 ARXIV: 2005.01090 https://hal.archives-ouvertes.fr/hal-03084229 2020 [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [SDU.STU.OC]Sciences of the Universe [physics]/Earth Sciences/Oceanography info:eu-repo/semantics/preprint Preprints, Working Papers, . 2020 ftccsdartic 2021-11-07T00:26:19Z Accepted for publication in IEEE IGARSS 2020 conference The upcoming Surface Water Ocean Topography (SWOT) satellite altimetry mission is expected to yield two-dimensional high-resolution measurements of Sea Surface Height (SSH), thus allowing for a better characterization of the mesoscale and submesoscale eddy field. However, to fulfill the promises of this mission, filtering the tidal component of the SSH measurements is necessary. This challenging problem is crucial since the posterior studies done by physical oceanographers using SWOT data will depend heavily on the selected filtering schemes. In this paper, we cast this problem into a supervised learning framework and propose the use of convolutional neural networks (ConvNets) to estimate fields free of internal tide signals. Numerical experiments based on an advanced North Atlantic simulation of the ocean circulation (eNATL60) show that our ConvNet considerably reduces the imprint of the internal waves in SSH data even in regions unseen by the neural network. We also investigate the relevance of considering additional data from other sea surface variables such as sea surface temperature (SST). Report North Atlantic Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
institution |
Open Polar |
collection |
Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
op_collection_id |
ftccsdartic |
language |
English |
topic |
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [SDU.STU.OC]Sciences of the Universe [physics]/Earth Sciences/Oceanography |
spellingShingle |
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [SDU.STU.OC]Sciences of the Universe [physics]/Earth Sciences/Oceanography LGUENSAT, Redouane Fablet, Ronan Sommer, Julien Le Metref, Sammy Cosme, Emmanuel Ouenniche, Kaouther Drumetz, Lucas Gula, Jonathan Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks |
topic_facet |
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [SDU.STU.OC]Sciences of the Universe [physics]/Earth Sciences/Oceanography |
description |
Accepted for publication in IEEE IGARSS 2020 conference The upcoming Surface Water Ocean Topography (SWOT) satellite altimetry mission is expected to yield two-dimensional high-resolution measurements of Sea Surface Height (SSH), thus allowing for a better characterization of the mesoscale and submesoscale eddy field. However, to fulfill the promises of this mission, filtering the tidal component of the SSH measurements is necessary. This challenging problem is crucial since the posterior studies done by physical oceanographers using SWOT data will depend heavily on the selected filtering schemes. In this paper, we cast this problem into a supervised learning framework and propose the use of convolutional neural networks (ConvNets) to estimate fields free of internal tide signals. Numerical experiments based on an advanced North Atlantic simulation of the ocean circulation (eNATL60) show that our ConvNet considerably reduces the imprint of the internal waves in SSH data even in regions unseen by the neural network. We also investigate the relevance of considering additional data from other sea surface variables such as sea surface temperature (SST). |
author2 |
Institut des Géosciences de l’Environnement (IGE) Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ) Université Grenoble Alpes (UGA) |
format |
Report |
author |
LGUENSAT, Redouane Fablet, Ronan Sommer, Julien Le Metref, Sammy Cosme, Emmanuel Ouenniche, Kaouther Drumetz, Lucas Gula, Jonathan |
author_facet |
LGUENSAT, Redouane Fablet, Ronan Sommer, Julien Le Metref, Sammy Cosme, Emmanuel Ouenniche, Kaouther Drumetz, Lucas Gula, Jonathan |
author_sort |
LGUENSAT, Redouane |
title |
Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks |
title_short |
Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks |
title_full |
Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks |
title_fullStr |
Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks |
title_full_unstemmed |
Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks |
title_sort |
filtering internal tides from wide-swath altimeter data using convolutional neural networks |
publisher |
HAL CCSD |
publishDate |
2020 |
url |
https://hal.archives-ouvertes.fr/hal-03084229 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_source |
https://hal.archives-ouvertes.fr/hal-03084229 2020 |
op_relation |
info:eu-repo/semantics/altIdentifier/arxiv/2005.01090 hal-03084229 https://hal.archives-ouvertes.fr/hal-03084229 ARXIV: 2005.01090 |
_version_ |
1766131794663440384 |