Preprints
https://doi.org/10.5194/gmd-2022-241
https://doi.org/10.5194/gmd-2022-241
Submitted as: development and technical paper
15 Nov 2022
Submitted as: development and technical paper | 15 Nov 2022
Status: this preprint is currently under review for the journal GMD.

4DVarNet-SSH: end-to-end learning of variational interpolation schemes for nadir and wide-swath satellite altimetry

Maxime Beauchamp, Quentin Febvre, Hugo Georgenthum, and Ronan Fablet Maxime Beauchamp et al.
  • IMT Atlantique Bretagne Pays de la Loire, 655 Av. du Technopôle, 29280 Plouzané, France

Abstract. The reconstruction of sea surface currents from satellite altimeter data is a key challenge in spatial oceanography, especially with the upcoming wide-swath SWOT (Surface Ocean and Water Topography) altimeter mission. Operational systems however generally fail to retrieve mesoscale dynamics for horizontal scales below 100 km and time-scale below 10 days. Here, we address this challenge through the 4DVarnet framework, an end-to-end neural scheme backed on a variational data assimilation formulation. We introduce a parametrization of the 4DVarNet scheme dedicated to the space-time interpolation of satellite altimeter data. Within an observing system simulation experiment (NATL60), we demonstrate the relevance of the proposed approach both for nadir and nadir+swot altimeter configurations for two contrasted case-study regions in terms of upper ocean dynamics. We report relative improvement with respect to the operational optimal interpolation between 30 % and 60 % in terms of reconstruction error. Interestingly, for the nadir+swot altimeter configuration, we reach resolved space-time scales below 70 km and 7 days. The code is open-source to enable reproductibility and future collaborative developments. Beyond its applicability to large-scale domains, we also address uncertainty quantification issues and generalization properties of the proposed learning setting. We discuss further future research avenues and extensions to other ocean data assimilation and space oceanography challenges.

Maxime Beauchamp et al.

Status: open (until 10 Jan 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Maxime Beauchamp et al.

Maxime Beauchamp et al.

Viewed

Total article views: 178 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
137 36 5 178 3 2
  • HTML: 137
  • PDF: 36
  • XML: 5
  • Total: 178
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 15 Nov 2022)
Cumulative views and downloads (calculated since 15 Nov 2022)

Viewed (geographical distribution)

Total article views: 177 (including HTML, PDF, and XML) Thereof 177 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Dec 2022
Download
Short summary
4DVarNet is a learning-based method backboned on traditional data assimilation (DA). This new class of algorithms can be used to provide efficient reconstructions of a dynamical system based on single observations. We provide a 4DVarNet application to SSH reconstructions based on nadir and future SWOT data: it turns out to outperform other state-of-the-art methods, from optimal interpolation to sophisticated DA algorithms. This research is led within the AI Chair Oceanix on-going works.