Learnable Variational Models for the Reconstruction of Sea Surface Currents Using Ais Data Streams: A Case Study on the Sicily Channel - IMT Atlantique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Learnable Variational Models for the Reconstruction of Sea Surface Currents Using Ais Data Streams: A Case Study on the Sicily Channel

Résumé

In this work, we focus on the estimation of sea surface current using Automated identification system (AIS) data streams in the Mediterranean sea. We propose to use deep learning techniques to solve the associated ill-posed inverse problem, for methodological purpose we compare two differ-ent approaches, the first one relies on a physical constrained unsupervised technique whereas the seconds exploit a super-vised framework and a dataset of in-situ observation from HF Radar. Performances are evaluated using ground-truth measurement provided by drifting buyos and HF Radar over area of the Sicily channel. We show that both AIS-derived product outperform satellite-altimetry derived ones in terms of reconstruction criterion. When comparing the two learning framework, the use of supervised learning algorithms leads to the best performances.
Fichier non déposé

Dates et versions

hal-04231162 , version 1 (06-10-2023)

Identifiants

Citer

Simon Benaïchouche, C. Le Goff, B. Boussidi, François Rousseau, Ronan Fablet. Learnable Variational Models for the Reconstruction of Sea Surface Currents Using Ais Data Streams: A Case Study on the Sicily Channel. IGARSS 2022: IEEE International Geoscience and Remote Sensing Symposium, Jul 2022, Kuala Lumpur, Malaysia. pp.6821-6824, ⟨10.1109/IGARSS46834.2022.9883870⟩. ⟨hal-04231162⟩
15 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More