Saved in:
Bibliographic Details
Main Authors: Garcia, Pierre, Larroche, Inès, Pesnec, Amélie, Bull, Hannah, Archambault, Théo, Moschos, Evangelos, Stegner, Alexandre, Charantonis, Anastase, Béréziat, Dominique
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.12054
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912197306744832
author Garcia, Pierre
Larroche, Inès
Pesnec, Amélie
Bull, Hannah
Archambault, Théo
Moschos, Evangelos
Stegner, Alexandre
Charantonis, Anastase
Béréziat, Dominique
author_facet Garcia, Pierre
Larroche, Inès
Pesnec, Amélie
Bull, Hannah
Archambault, Théo
Moschos, Evangelos
Stegner, Alexandre
Charantonis, Anastase
Béréziat, Dominique
contents We present ORCAst, a multi-stage, multi-arm network for Operational high-Resolution Current forecAsts over one week. Producing real-time nowcasts and forecasts of ocean surface currents is a challenging problem due to indirect or incomplete information from satellite remote sensing data. Entirely trained on real satellite data and in situ measurements from drifters, our model learns to forecast global ocean surface currents using various sources of ground truth observations in a multi-stage learning procedure. Our multi-arm encoder-decoder model architecture allows us to first predict sea surface height and geostrophic currents from larger quantities of nadir and SWOT altimetry data, before learning to predict ocean surface currents from much more sparse in situ measurements from drifters. Training our model on specific regions improves performance. Our model achieves stronger nowcast and forecast performance in predicting ocean surface currents than various state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12054
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ORCAst: Operational High-Resolution Current Forecasts
Garcia, Pierre
Larroche, Inès
Pesnec, Amélie
Bull, Hannah
Archambault, Théo
Moschos, Evangelos
Stegner, Alexandre
Charantonis, Anastase
Béréziat, Dominique
Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
We present ORCAst, a multi-stage, multi-arm network for Operational high-Resolution Current forecAsts over one week. Producing real-time nowcasts and forecasts of ocean surface currents is a challenging problem due to indirect or incomplete information from satellite remote sensing data. Entirely trained on real satellite data and in situ measurements from drifters, our model learns to forecast global ocean surface currents using various sources of ground truth observations in a multi-stage learning procedure. Our multi-arm encoder-decoder model architecture allows us to first predict sea surface height and geostrophic currents from larger quantities of nadir and SWOT altimetry data, before learning to predict ocean surface currents from much more sparse in situ measurements from drifters. Training our model on specific regions improves performance. Our model achieves stronger nowcast and forecast performance in predicting ocean surface currents than various state-of-the-art methods.
title ORCAst: Operational High-Resolution Current Forecasts
topic Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2501.12054