Mobile version

AI learning method to improve altimetry gridding

Image of the Month - November 2021

Current velocity over the Gulf Stream area. From top to bottom and left to right: model high-resolution output considered in the experiment as the "truth", Altimetry measurements (four-satellite configuration plus Swot), current output from optimal interpolation (Duacs processing), and using physics-informed AI scheme (credits IMT Atlantique, with support from Cnes, Idris and NVidia)


Newcomers to altimetry data are often surprised when they see along-track data maps. As all Earth Observation techniques, but with a much smaller "footprint" than most sensors, altimetry satellites can't see the whole Earth at once. The workaround has been to use several satellites' data, several days (including, if possible in the future as well as in the past of a given data file), and ocean physics to estimate what is missing by optimal interpolation. That is what is behind the "multi-mission gridded maps" that a number of altimetry users have been retrieving. However the approach has its drawbacks, including not being able to retrieve details below scales of around 100 km, even when the information were in the native along-track measurements. 

Using artificial intelligence methods provides with a new approach to this problem. The deep learning scheme designed by OceaniX team at IMT Atlantique/Lab-STICC enables to better estimate the gradients between the measurements, using an a-priori knowledge of the involved physics. 

Improving data processing to provide with the most accurate and most detailed datasets is among the studies ongoing. Swot data will help, but it won't provide data everywhere and anywhere, so such processings will continue to be in order.

See also:

Other website on this topic:

Reference:

  • R. Fablet, M.M. Amar, Q. Febvre, M. Beauchamp, B. Chapron, 2021: End-to-end physics-informed representation learning for satellite ocean remote sensing data: applications to satellite altimetry and sea surface currents. ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2021, 295–302, 2021, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021
EnglishFrançaisEspañol
Rss feedsContactPartnersFAQLexiconMobile
You must enable cookies in your browser preferences to save the modifications
You are using an older version of Internet Explorer, please update to take full advantage of Aviso+ features

Customize the home page

View all widgets
-->
Reduce display
Public profile
User profile

Select/Deselect widgets

Discover AVISO+

Customizable home, reading tools, products search guide, etc.. Discover step by step the features of the new site AVISO+.

Customizable homepage

The new home page is composed of blocks called "widgets".

Rearrange the blocks with a "Click & Drop".

Hide a widget with the cross at the top right. Reset or add a widget with the "wrench" icon. The "User" and "Public" profiles offer a predefined organization.

All the modifications are automatically saved as cookies on your machine so as to enable you to have your own specific AVISO+.

Reading tools

Ease your reading by choosing the page background colour (black/white) and/or by modifying the font size.

Browsing menu and breadcrum trail

To ease your browsing through AVISO+, you can use at any time the main banner items with the interactive submenus or use the browsing menu on the left side of the screen (it is open by default). For more readiness of the page contents, you can fold and unfold the browsing menu by clicking on the tab. At any time you can know where you are thanks to the browsing menu or the breadcrum at the top of the page.

Products search guide

The first submenu of the "Data" banner item leads you to a new search form enabling you to find quickier the product that suits your needs. The list of results is updated according to your selection criteria.

AVISO+ Multimedia

The first submenu of the "Multimedia" banner item leads you to AVISO+ collections of images and videos linked to altimetry and its applications. Have a nice visit!