End-to-end physics-informed representation learning from and for satellite ocean remote sensing data - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

End-to-end physics-informed representation learning from and for satellite ocean remote sensing data

Résumé

This paper addresses physics-informed deep learning schemes for satellite ocean remote sensing data. Such observation datasets are characterized by the irregular space-time sampling of the ocean surface due to sensors' characteristics and satellite orbits. With a focus on satellite altimetry, we show that end-to-end learning schemes based on variational formulations provide new means to explore and exploit such observation datasets. Through Observing System Simulation Experiments (OSSE) using numerical ocean simulations and real nadir and wide-swath altimeter sampling patterns, we demonstrate their relevance w.r.t. state-of-the-art and operational methods for space-time interpolation and short-term forecasting issues. We also stress and discuss how they could contribute to the design and calibration of ocean observing systems.
Fichier principal
Vignette du fichier
4VDVarNN_SLA2021 (5).pdf (1.36 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03189218 , version 1 (02-04-2021)

Identifiants

  • HAL Id : hal-03189218 , version 1

Citer

Ronan Fablet, Mohamed Mahmoud Amar, Quentin Febvre, Maxime Beauchamp, Bertrand Chapron. End-to-end physics-informed representation learning from and for satellite ocean remote sensing data. XXIV ISPRS 2021 : Intenational Society for Photogrammetry and Remote Sensing Congress, Jul 2021, Nice, France. ⟨hal-03189218⟩
334 Consultations
150 Téléchargements

Partager

Gmail Facebook X LinkedIn More