Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms
Surface ocean dynamics play a key role in the Earth system, contributing to regulate its climate and affecting the marine ecosystem functioning. Dynamical processes occur and interact in the upper ocean at multiple scales, down to, or even less than, few kilometres. These scales are not adequately r...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-02-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/5/1159 |
_version_ | 1797473980083339264 |
---|---|
author | Bruno Buongiorno Nardelli Davide Cavaliere Elodie Charles Daniele Ciani |
author_facet | Bruno Buongiorno Nardelli Davide Cavaliere Elodie Charles Daniele Ciani |
author_sort | Bruno Buongiorno Nardelli |
collection | DOAJ |
description | Surface ocean dynamics play a key role in the Earth system, contributing to regulate its climate and affecting the marine ecosystem functioning. Dynamical processes occur and interact in the upper ocean at multiple scales, down to, or even less than, few kilometres. These scales are not adequately resolved by present observing systems, and, in the last decades, global monitoring of surface currents has been based on the application of geostrophic balance to absolute dynamic topography maps obtained through the statistical interpolation of along-track satellite altimeter data. Due to the cross-track distance and repetitiveness of satellite acquisitions, the effective resolution of interpolated data is limited to several tens of kilometres. At the kilometre scale, sea surface temperature pattern evolution is dominated by advection, providing indirect information on upper ocean currents. Computer vision techniques are perfect candidates to infer this dynamical information from the combination of altimeter data, surface temperature images and observing-system geometry. Here, we exploit one class of image processing techniques, super-resolution, to develop an original neural-network architecture specifically designed to improve absolute dynamic topography reconstruction. Our model is first trained on synthetic observations built from a numerical general-circulation model and then tested on real satellite products. Provided concurrent clear-sky thermal observations are available, it proves able to compensate for altimeter sampling/interpolation limitations by learning from primitive equation data. The algorithm can be adapted to learn directly from future surface topography, and eventual surface currents, high-resolution satellite observations. |
first_indexed | 2024-03-09T20:23:52Z |
format | Article |
id | doaj.art-fd2387791a4d4c90ac68259c7fbe7677 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T20:23:52Z |
publishDate | 2022-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-fd2387791a4d4c90ac68259c7fbe76772023-11-23T23:42:27ZengMDPI AGRemote Sensing2072-42922022-02-01145115910.3390/rs14051159Super-Resolving Ocean Dynamics from Space with Computer Vision AlgorithmsBruno Buongiorno Nardelli0Davide Cavaliere1Elodie Charles2Daniele Ciani3Consiglio Nazionale delle Ricerche, Istituto di Scienze Marine (CNR-ISMAR), 80133 Naples, ItalyConsiglio Nazionale delle Ricerche, Istituto di Scienze Marine (CNR-ISMAR), 00133 Rome, ItalyCollecte Localisation Satellites, 11 Rue Hermès, Parc Technologique du Canal, 31520 Ramonville Saint-Agne, FranceConsiglio Nazionale delle Ricerche, Istituto di Scienze Marine (CNR-ISMAR), 00133 Rome, ItalySurface ocean dynamics play a key role in the Earth system, contributing to regulate its climate and affecting the marine ecosystem functioning. Dynamical processes occur and interact in the upper ocean at multiple scales, down to, or even less than, few kilometres. These scales are not adequately resolved by present observing systems, and, in the last decades, global monitoring of surface currents has been based on the application of geostrophic balance to absolute dynamic topography maps obtained through the statistical interpolation of along-track satellite altimeter data. Due to the cross-track distance and repetitiveness of satellite acquisitions, the effective resolution of interpolated data is limited to several tens of kilometres. At the kilometre scale, sea surface temperature pattern evolution is dominated by advection, providing indirect information on upper ocean currents. Computer vision techniques are perfect candidates to infer this dynamical information from the combination of altimeter data, surface temperature images and observing-system geometry. Here, we exploit one class of image processing techniques, super-resolution, to develop an original neural-network architecture specifically designed to improve absolute dynamic topography reconstruction. Our model is first trained on synthetic observations built from a numerical general-circulation model and then tested on real satellite products. Provided concurrent clear-sky thermal observations are available, it proves able to compensate for altimeter sampling/interpolation limitations by learning from primitive equation data. The algorithm can be adapted to learn directly from future surface topography, and eventual surface currents, high-resolution satellite observations.https://www.mdpi.com/2072-4292/14/5/1159earth observationsocean dynamicssatellite altimetrysea surface temperatureartificial intelligencemachine learning |
spellingShingle | Bruno Buongiorno Nardelli Davide Cavaliere Elodie Charles Daniele Ciani Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms Remote Sensing earth observations ocean dynamics satellite altimetry sea surface temperature artificial intelligence machine learning |
title | Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms |
title_full | Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms |
title_fullStr | Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms |
title_full_unstemmed | Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms |
title_short | Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms |
title_sort | super resolving ocean dynamics from space with computer vision algorithms |
topic | earth observations ocean dynamics satellite altimetry sea surface temperature artificial intelligence machine learning |
url | https://www.mdpi.com/2072-4292/14/5/1159 |
work_keys_str_mv | AT brunobuongiornonardelli superresolvingoceandynamicsfromspacewithcomputervisionalgorithms AT davidecavaliere superresolvingoceandynamicsfromspacewithcomputervisionalgorithms AT elodiecharles superresolvingoceandynamicsfromspacewithcomputervisionalgorithms AT danieleciani superresolvingoceandynamicsfromspacewithcomputervisionalgorithms |