Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 16, issue 8
Articles | Volume 16, issue 8
https://doi.org/10.5194/gmd-16-2119-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-16-2119-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 16, issue 8
Development and technical paper
 | 
19 Apr 2023
Development and technical paper |  | 19 Apr 2023

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

Model code and software

CIA-Oceanix/4dvarnet-core: Release for 4DVarNet-MM-SSH code (4dvarnet-mm-ssh-tgrs-2022) hgeorgenthum, Quentin Febvre, maxbeauchamp, Ronan Fablet, Benjamin Carpentier, and MMAMAR https://doi.org/10.5281/zenodo.7503266

Video supplement

GF (four nadirs) application of 4DVarNet-SSH Maxime Beauchamp ttps://youtube.com/shorts/QKXukB_Rd5E

GF (one SWOT plus four nadirs) application of 4DVarNet-SSH Maxime Beauchamp https://youtube.com/shorts/i91Z1pMm4gY

OSMOSIS (four nadirs) application of 4DVarNet-SSH Maxime Beauchamp https://youtube.com/shorts/Pxcsd0Afco0

OSMOSIS (one SWOT plus four nadirs) application of 4DVarNet-SSH Maxime Beauchamp https://youtube.com/shorts/HbVSJFtdG6Q

Download
Short summary
4DVarNet is a learning-based method based 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 sea surface height reconstructions based on nadir and future Surface Water and Ocean and Topography data. It outperforms other methods, from optimal interpolation to sophisticated DA algorithms. This work is part of on-going AI Chair Oceanix projects.
Read more