Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ... (Preprint)

Deep learning for Lagrangian drift simulation at the sea surface

Abstract : We address Lagrangian drift simulation in geophysical dynamics and explore deep learning approaches to overcome known limitations of state-of-the-art model-based and Markovian approaches in terms of computational complexity and error propagation. We introduce a novel architecture, referred to as DriftNet, inspired from the Eulerian Fokker-Planck representation of Lagrangian dynamics. Numerical experiments for Lagrangian drift simulation at the sea surface demonstrates the relevance of DriftNet w.r.t. state-of-the-art schemes. Benefiting from the fully-convolutional nature of Drift-Net, we explore through a neural inversion how to diagnose modelderived velocities w.r.t. real drifter trajectories.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03852489
Contributor : Daria Botvynko Connect in order to contact the contributor
Submitted on : Wednesday, November 16, 2022 - 4:39:07 PM
Last modification on : Thursday, November 24, 2022 - 2:03:16 PM

Files

DriftNet2022.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03852489, version 1
  • ARXIV : 2211.09818

Citation

Daria Botvynko, Carlos Granero-Belinchon, Simon Van Gennip, Abdesslam Benzinou, Ronan Fablet. Deep learning for Lagrangian drift simulation at the sea surface. {date}. ⟨hal-03852489⟩

Share

Metrics

Record views

0

Files downloads

0