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.
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.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
19 Apr 2023
Development and technical paper |
| 19 Apr 2023
| 19 Apr 2023
4DVarNet-SSH: end-to-end learning of variational interpolation schemes for nadir and wide-swath satellite altimetry
Maxime Beauchamp
CORRESPONDING AUTHOR
IMT Atlantique Bretagne-Pays de la Loire, 655 Av. du Technopôle, 29280 Plouzané, France
Quentin Febvre
IMT Atlantique Bretagne-Pays de la Loire, 655 Av. du Technopôle, 29280 Plouzané, France
Hugo Georgenthum
IMT Atlantique Bretagne-Pays de la Loire, 655 Av. du Technopôle, 29280 Plouzané, France
Ronan Fablet
IMT Atlantique Bretagne-Pays de la Loire, 655 Av. du Technopôle, 29280 Plouzané, France
Related authors
R. Fablet, M. M. Amar, Q. Febvre, M. Beauchamp, and B. Chapron
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2021, 295–302, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021, 2021
Théo Picard, Chelsey A. Baker, Jonathan Gula, Ronan Fablet, Laurent Mémery, and Richard Lampitt
Biogeosciences, 22, 4309–4331, https://doi.org/10.5194/bg-22-4309-2025, https://doi.org/10.5194/bg-22-4309-2025, 2025
Short summary
Short summary
Ocean sediment traps measure the sequestrated sinking organic carbon. While sinking, the particles are affected by local currents, which presents a challenge with regard to linking the deep flux with the surface. We present a machine learning tool that predicts the source location of the sinking particles based on satellite data. The predictions demonstrate a stronger correlation between surface and deep carbon fluxes, allowing a more comprehensive understanding of the deep carbon sequestration drivers.
Maxime Ballarotta, Clément Ubelmann, Valentin Bellemin-Laponnaz, Florian Le Guillou, Guillaume Meda, Cécile Anadon, Alice Laloue, Antoine Delepoulle, Yannice Faugère, Marie-Isabelle Pujol, Ronan Fablet, and Gérald Dibarboure
Ocean Sci., 21, 63–80, https://doi.org/10.5194/os-21-63-2025, https://doi.org/10.5194/os-21-63-2025, 2025
Short summary
Short summary
The Surface Water and Ocean Topography (SWOT) mission provides unprecedented swath altimetry data. This study examines SWOT's impact on mapping systems, showing a moderate effect with the current nadir altimetry constellation and a stronger impact with a reduced one. Integrating SWOT with dynamic mapping techniques improves the resolution of satellite-derived products, offering promising solutions for studying and monitoring sea-level variability at finer scales.
Théo Picard, Jonathan Gula, Ronan Fablet, Jeremy Collin, and Laurent Mémery
Ocean Sci., 20, 1149–1165, https://doi.org/10.5194/os-20-1149-2024, https://doi.org/10.5194/os-20-1149-2024, 2024
Short summary
Short summary
The biological carbon pump plays a key role in the climate system. Plankton absorb and transform CO2 into organic carbon, forming particles that sink to the ocean floor. Sediment traps catch these particles and measure the carbon stored in the abyss. However, the particles' surface origin is unknown as ocean currents alter their paths. Here, we train an AI model to predict the origin of these particles. This new tool enables a better link between deep-ocean observations and satellite images.
Etienne Pauthenet, Loïc Bachelot, Kevin Balem, Guillaume Maze, Anne-Marie Tréguier, Fabien Roquet, Ronan Fablet, and Pierre Tandeo
Ocean Sci., 18, 1221–1244, https://doi.org/10.5194/os-18-1221-2022, https://doi.org/10.5194/os-18-1221-2022, 2022
Short summary
Short summary
Temperature and salinity profiles are essential for studying the ocean’s stratification, but there are not enough of these data. Satellites are able to measure daily maps of the surface ocean. We train a machine to learn the link between the satellite data and the profiles in the Gulf Stream region. We can then use this link to predict profiles at the high resolution of the satellite maps. Our prediction is fast to compute and allows us to get profiles at any locations only from surface data.
R. Fablet, M. M. Amar, Q. Febvre, M. Beauchamp, and B. Chapron
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2021, 295–302, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021, 2021
Cited articles
Alvera-Azcárate, A., Barth, A., Rixen, M., and Beckers, J. M.: Reconstruction
of incomplete oceanographic data sets using empirical orthogonal functions:
application to the Adriatic Sea surface temperature, Ocean Model., 9,
325–346, https://doi.org/10.1016/j.ocemod.2004.08.001, 2005. a
Alvera-Azcárate, A., Barth, A., Sirjacobs, D., and Beckers, J.-M.: Enhancing temporal correlations in EOF expansions for the reconstruction of missing data using DINEOF, Ocean Sci., 5, 475–485, https://doi.org/10.5194/os-5-475-2009, 2009. a, b
Andrychowicz, M., Denil, M., Gomez, S., Hoffman, M. W., Pfau, D., Schaul, T.,
Shillingford, B., and De Freitas, N.: Learning to learn by gradient descent
by gradient descent, in: Advances in neural information processing systems,
3981–3989, https://doi.org/10.48550/arXiv.1606.04474, 2016. a
Ardhuin, F., Ubelmann, C., Dibarboure, G., Gaultier, L., Ponte, A., Ballarotta,
M., and Faugère, Y.: Reconstructing Ocean Surface Current Combining
Altimetry and Future Spaceborne Doppler Data, ESS Open Archive [preprint], p. 22, https://doi.org/10.1002/essoar.10505014.1, 2020. a, b, c
Asch, M., Bocquet, M., and Nodet, M.: Data Assimilation, in: Fundamentals of
Algorithms, Society for Industrial and Applied Mathematics,
https://doi.org/10.1137/1.9781611974546, 2016. a, b, c
Ballarotta, M., Ubelmann, C., Pujol, M.-I., Taburet, G., Fournier, F., Legeais, J.-F., Faugère, Y., Delepoulle, A., Chelton, D., Dibarboure, G., and Picot, N.: On the resolutions of ocean altimetry maps, Ocean Sci., 15, 1091–1109, https://doi.org/10.5194/os-15-1091-2019, 2019. a
Ballarotta, M., Ubelmann, C., Rogé, M., Fournier, F., Faugère, Y.,
Dibarboure, G., Morrow, R., and Picot, N.: Dynamic Mapping of Along-Track
Ocean Altimetry: Performance from Real Observations, J. Atmos.
Ocean. Tech., 37, 1593–1601, https://doi.org/10.1175/JTECH-D-20-0030.1,
2020. a, b
Barbastathis, G., Ozcan, A., and Situ, G.: On the use of deep learning for
computational imaging, Optica, 6, 921–943, https://doi.org/10.1364/OPTICA.6.000921,
2019. a
Barth, A., Alvera-Azcárate, A., Licer, M., and Beckers, J.-M.: DINCAE 1.0: a
convolutional neural network with error estimates to reconstruct sea surface
temperature satellite observations, Geoscientific Model Development
Discussions, 2019, 1–21, https://doi.org/10.5194/gmd-2019-128, 2019. a, b
Beauchamp, M.: GF (four nadirs) application of 4DVarNet-SSH, Youtube [video], https://youtube.com/shorts/QKXukB_Rd5E, last access: 26 August 2022a. a
Beauchamp, M.:
GF (one SWOT plus four nadirs) application of 4DVarNet-SSH, Youtube [video], https://youtube.com/shorts/i91Z1pMm4gY,
last access: 26 August 2022b. a
Beauchamp, M.:
OSMOSIS (four nadirs) application of 4DVarNet-SSH, Youtube [video], https://youtube.com/shorts/Pxcsd0Afco0,
last access: 26 August 2022c. a
Beauchamp, M.: OSMOSIS (one SWOT plus four nadirs) application of 4DVarNet-SSH, Youtube [video], https://youtube.com/shorts/HbVSJFtdG6Q,
last access: 26 August 2022d. a
Beauchamp, M., Amar, M. M., Febvre, Q., and Fablet, R.: End-to-End Learning of
Variational Interpolation Schemes for Satellite-Derived SSH Data, in: 2021
IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium, 2021, 7418–7421,
https://doi.org/10.1109/IGARSS47720.2021.9554800, 2021. a, b
Beauchamp, M., Thompson, J., Georgenthum, H., Febvre, Q., and Fablet, R.:
Learning Neural Optimal Interpolation Models and Solvers, arXiv [preprint],
https://doi.org/10.48550/ARXIV.2211.07209, 2022. a, b
Beckers, J. M. and Rixen, M.: EOF Calculations and Data Filling from Incomplete
Oceanographic Datasets, J. Atmos. Ocean. Tech., 20,
1839–1856, https://doi.org/10.1175/1520-0426(2003)020<1839:ECADFF>2.0.CO;2,
2003a. a
Beckers, J. M. and Rixen, M.: EOF Calculations and Data Filling from
Incomplete Oceanographic Datasets, J. Atmos. Ocean.
Tech., 20, 1839–1856, 2003b. a
Benkiran, M., Ruggiero, G., Greiner, E., Le Traon, P.-Y., Rémy, E., Lellouche,
J. M., Bourdallé-Badie, R., Drillet, Y., and Tchonang, B.: Assessing the
Impact of the Assimilation of SWOT Observations in a Global High-Resolution
Analysis and Forecasting System Part 1: Methods, Front. Mar. Sci.,
8, https://doi.org/10.3389/fmars.2021.691955, 2021. a, b
Carrassi, A., Bocquet, M., Bertino, L., and Evensen, G.: Data assimilation in
the geosciences: An overview of methods, issues, and perspectives, WIREs
Clim. Change, 9, e535, https://doi.org/10.1002/wcc.535, 2018. a, b
Chelton, D. B., Ries, J., Haines, B. J., Fu, L.-L., and Callahan, P. S.:
Satellite Altimetry, in: International Geophysics, edited by: Cazenave, A.
and Fu, L.-L., vol. 69 of Satellite Altimetry and Earth SciencesA
Handbook of Techniques and Applications, 1–ii, Academic Press,
http://www.sciencedirect.com/science/article/pii/S0074614201801467 (last access: 11 April 2023),
2001. a
Delepoulle, A., evanmason, Clément, CoriPegliasco, Capet, A., Troupin, C., and Koldunov, N.:
AntSimi/py-eddy-tracker: v3.6.1,
Zenodo [code], https://doi.org/10.5281/zenodo.7197432,
2022. a
Dufau, C., Orsztynowicz, M., Dibarboure, G., Morrow, R., and Le Traon, P.-Y.:
Mesoscale resolution capability of altimetry: Present and future, J.
Geophys. Res.-Oceans, 121, 4910–4927, https://doi.org/10.1002/2015JC010904,
2016. a
Esteban-Fernandez, D.: SWOT project mission performance and error budget
document, Tech. rep., JPL D-79084, NASA, 2014. a
Evensen, G.: Data Assimilation, Springer Berlin Heidelberg, Berlin,
https://doi.org/10.1007/978-3-642-03711-5, 2009. a
Fablet, R. and Chapron, B.: Multimodal learning-based inversion models for the
space-time reconstruction of satellite-derived geophysical fields, ArXiv [preprint],
https://doi.org/10.48550/ARXIV.2203.10640, 2022. a, b, c
Fablet, R., Drumetz, L., and Rousseau, F.: End-to-end learning of optimal
interpolators for geophysical dynamics, CI 2019: 9th International Workshop on Climate Informatics, Paris, France, https://imt-atlantique.hal.science/hal-02285701 (last access: 11 April 2023), 2019. a
Fablet, R., Drumetz, L., and Rousseau, F.: Joint learning of variational
representations and solvers for inverse problems with partially-observed
data, arXiv [preprint], https://doi.org/10.48550/arXiv.2006.03653, 2020. a, b
Fablet, R., Beauchamp, M., Drumetz, L., and Rousseau, F.: Joint Interpolation
and Representation Learning for Irregularly Sampled Satellite-Derived
Geophysical Fields, Front. Appl. Math. Stat., 7, 655224,
https://doi.org/10.3389/fams.2021.655224, 2021. a, b, c, d
Febvre, Q., Fablet, R., Sommer, J. L., and Ubelmann, C.: Joint Calibration and
Mapping of Satellite Altimetry Data Using Trainable Variational Models, in:
ICASSP 2022 – 2022 IEEE International Conference on Acoustics, Speech and
Signal Processing (ICASSP), 1536–1540,
https://doi.org/10.1109/ICASSP43922.2022.9746889, 2022. a
Gaultier, L. and Ubelmann, C.: SWOT Simulator Documentation, Tech. rep., JPL,
NASA, 2010. a
Gaultier, L., Ubelmann, C., and Fu, L.-L.: The Challenge of Using Future
SWOT Data for Oceanic Field Reconstruction, J. Atmos.
Ocean. Tech., 33, 119–126, https://doi.org/10.1175/JTECH-D-15-0160.1, 2015. a, b
Goodfellow, I., Bengio, Y., and Courville, A.: Deep Learning, MIT Press,
http://www.deeplearningbook.org (last access: 11 April 2023), 2016. a
hgeorgenthum, Febvre, Q., maxbeauchamp, Fablet, R., Carpentier, B., and MMAMAR: CIA-Oceanix/4dvarnet-core: Release for 4DVarNet-MM-SSH code (4dvarnet-mm-ssh-tgrs-2022), Zenodo [code], https://doi.org/10.5281/zenodo.7503266, 2023. a, b, c
Le Guillou, F., Metref, S., Cosme, E., Ubelmann, C., Ballarotta, M., Verron,
J., and Le Sommer, J.: Mapping altimetry in the forthcoming SWOT era by
back-and-forth nudging a one-layer quasi-geostrophic model, Earth and Space
Science Open Archive [preprint], p. 15, https://doi.org/10.1002/essoar.10504575.1, 2020. a, b, c, d, e, f
Lellouche, J.-M., Greiner, E., Le Galloudec, O., Garric, G., Regnier, C., Drevillon, M., Benkiran, M., Testut, C.-E., Bourdalle-Badie, R., Gasparin, F., Hernandez, O., Levier, B., Drillet, Y., Remy, E., and Le Traon, P.-Y.: Recent updates to the Copernicus Marine Service global ocean monitoring and forecasting real-time 1∕12° high-resolution system, Ocean Sci., 14, 1093–1126, https://doi.org/10.5194/os-14-1093-2018, 2018. a
Lguensat, R., Tandeo, P., Aillot, P., and Fablet, R.: The Analog Data
Assimilation, Mon. Weather Rev., 145, 4093–4107, https://doi.org/10.1175/MWR-D-16-0441.1, 2017. a, b, c
Li, Z., Archer, M., Wang, J., and Fu, L.-L.: Formulation and demonstration of an extended-3DVAR multi-scale data assimilation system for the SWOT altimetry era, Ocean Sci. Discuss. [preprint], https://doi.org/10.5194/os-2021-89, 2021. a
Lopez-Radcenco, M., Pascual, A., Gomez-Navarro, L., Aissa-El-Bey, A., Chapron,
B., and Fablet, R.: Analog Data Assimilation of Along-Track Nadir
and Wide-Swath SWOT Altimetry Observations in the Western
Mediterranean Sea, IEEE J. Sel. Top. Appl., 12, 2530–2540,
https://doi.org/10.1109/JSTARS.2019.2903941, 2019. a
Manucharyan, G. E., Siegelman, L., and Klein, P.: A Deep Learning Approach to
Spatiotemporal Sea Surface Height Interpolation and Estimation of Deep
Currents in Geostrophic Ocean Turbulence, J. Adv. Model.
Earth Sy., 13, e2019MS001965,
https://doi.org/10.1029/2019MS001965, 2021. a
Mason, E., Pascual, A., and McWilliams, J. C.: A New Sea Surface Height–Based Code for
Oceanic Mesoscale Eddy Tracking, J. Atmos. Ocean.
Tech., 31, 1181–1188, https://doi.org/10.1175/JTECH-D-14-00019.1, 2014. a
Metref, S., Cosme, E., Le Guillou, F., Le Sommer, J., Brankart, J.-M., and
Verron, J.: Wide-Swath Altimetric Satellite Data Assimilation With
Correlated-Error Reduction, Front. Mar. Sci., 6, 822,
https://doi.org/10.3389/fmars.2019.00822, 2020. a
Molines, J.-M.: meom-configurations/NATL60-CJM165: NATL60 code used for
CJM165 experiment, Zenodo [code], https://doi.org/10.5281/zenodo.1210116, 2018. a
Ngodock, H., Carrier, M., Souopgui, I., Smith, S., Martin, P., Muscarella, P.,
and Jacobs, G.: On the direct assimilation of along-track sea-surface height
observations into a free-surface ocean model using a weak constraints
four-dimensional variational (4D-Var) method, Q. J. Roy.
Meteor. Soc., 142, 1160–1170, https://doi.org/10.1002/qj.2721, 2015. a
Pauthenet, E., Bachelot, L., Balem, K., Maze, G., Tréguier, A.-M., Roquet, F., Fablet, R., and Tandeo, P.: Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks, Ocean Sci., 18, 1221–1244, https://doi.org/10.5194/os-18-1221-2022, 2022. a
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., and WOO, W.-C.:
Convolutional LSTM Network: A Machine Learning Approach for Precipitation
Nowcasting, in: Advances in Neural Information Processing Systems, edited by:
Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., and Garnett, R., vol. 28,
Curran Associates, Inc.,
https://proceedings.neurips.cc/paper/2015/file/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf (last access: 11 April 2023),
2015.
a
Taburet, G., Sanchez-Roman, A., Ballarotta, M., Pujol, M.-I., Legeais, J.-F., Fournier, F., Faugere, Y., and Dibarboure, G.: DUACS DT2018: 25 years of reprocessed sea level altimetry products, Ocean Sci., 15, 1207–1224, https://doi.org/10.5194/os-15-1207-2019, 2019. a, b, c, d
Tandeo, P., Ailliot, P., Bocquet, M., Carrassi, A., Miyoshi, T., Pulido, M.,
and Zhen, Y.: A Review of Innovation-Based Methods to Jointly Estimate Model
and Observation Error Covariance Matrices in Ensemble Data Assimilation,
Mon. Weather Rev., 148, 3973–3994, https://doi.org/10.1175/mwr-d-19-0240.1, 2020. a, b
Ubelmann, C., Cornuelle, B., and Fu, L.-L.: Dynamic Mapping of Along-Track
Ocean Altimetry: Method and Performance from Observing System Simulation
Experiments, J. Atmos. Ocean. Tech., 33, 1691–1699,
https://doi.org/10.1175/JTECH-D-15-0163.1, 2016. a, b
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N.,
Kaiser, L., and Polosukhin, I.: Attention is All you Need, in: Advances in
Neural Information Processing Systems, edited by: Guyon, I., Luxburg, U. V.,
Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R.,
vol. 30, Curran Associates, Inc.,
https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf (last access: 11 April 2023),
2017. a
Vient, J.-M., Fablet, R., Jourdin, F., and Delacourt, C.: End-to-End Neural
Interpolation of Satellite-Derived Sea Surface Suspended Sediment
Concentrations, Remote Sensing, 14, 4024, https://doi.org/10.3390/rs14164024, 2022. a
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.
4DVarNet is a learning-based method based on traditional data assimilation (DA). This new class...
