AIConfPaper
← Search

Ronan Fablet

15 accepted papers

2025

OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems

Anass El Aouni, Quentin Gaudel, Juan Emmanuel Johnson, REGNIER Charly, Julien Le Sommer, van Gennip +4
NeurIPS 2025poster

Data-driven approaches, particularly those based on deep learning, are rapidly advancing Earth system modeling. However, their application to ocean forecasting remains limited despite the ocean's pivotal role in climate regulation and marine ecosystems. To address this gap, we present OceanBench, a…

Cited by 0Source ↗code ↗Scholar ↗
2024

Deep Learning Inversion of Ocean Wave Spectrum from SAR Satellite Observations

S. P. Tripathi, Bertrand Chapron, Fabrice Collard, Gilles Guitton, Manuel Lopez-Radcenco, Alexis Mouche +1
ICASSP 2024accepted

The monitoring of waves at the ocean surface is critical for both operational needs (e.g., maritime traffic) and scientific studies (e.g., air-sea interactions). Synthetic aperture radar (SAR) Satellites provide one of the only remote sensing observations to retrieve ocean wave information on a glob…

Cited by 0Source ↗Scholar ↗
2024

Impact of Sampling Strategies on the Monitoring of Climate Regime Shifts with a Learning Data Assimilation Method

Perrine Bauchot, Angélique Drémeau, Florian Sévellec, Ronan Fablet
ICASSP 2024accepted

In oceanography, the acquisition and processing of observations are crucial to improve the understanding of complex oceanic processes. Considering an idealized model of the North Atlantic ocean circulation, we propose to implement a variational data assimilation method optimized by deep learning to…

Cited by 0Source ↗Scholar ↗
2024

Neural Ordinary Differential Equations with Trainable Solvers

Said Ouala, Laurent Debreu, Bertrand Chapron, Fabrice Collard, Lucile Gaultier, Ronan Fablet
ICASSP 2024accepted

When considering the data-driven identification of non-linear differential equations, the choice of the integration scheme to use is far from being trivial and may dramatically impact the identification problem. In this work, we discuss this aspect and propose a novel architecture that jointly learn…

Cited by 0Source ↗Scholar ↗
2023

Deep Learning for Lagrangian Drift Simulation at The Sea Surface

Daria Botvynko, Carlos Granero-Belinchón, Simon Van Gennip, Abdesslam Benzinou, Ronan Fablet
ICASSP 2023accepted

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 Dri…

Cited by 0Source ↗Scholar ↗
2023

OceanBench: The Sea Surface Height Edition

Juan Emmanuel Johnson, Quentin Febvre, Anastasia Gorbunova, Sammy Metref, Maxime Ballarotta, Julien Le Sommer +1
NeurIPS 2023poster

The ocean is a crucial component of the Earth's system. It profoundly influences human activities and plays a critical role in climate regulation. Our understanding has significantly improved over the last decades with the advent of satellite remote sensing data, allowing us to capture essential s…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2022

Joint Calibration and Mapping of Satellite Altimetry Data Using Trainable Variational Models

Quentin Febvre, Ronan Fablet, Julien Le Sommer, Clément Ubelmann
ICASSP 2022accepted

Satellite radar altimeters are a key source of observation of ocean surface dynamics. However, current sensor technology and mapping techniques do not yet allow to systematically resolve scales smaller than 100km. With their new sensors, upcoming wide-swath altimeter missions such as SWOT should hel…

Cited by 0Source ↗Scholar ↗
2021

End-to-End Learning of Variational Models and Solvers for the Resolution of Interpolation Problems

Ronan Fablet, Lucas Drumetz, François Rousseau
ICASSP 2021accepted

Variational models are among the state-of-the-art formulations for the resolution of ill-posed inverse problems. Following recent advances in learning-based variational settings, we investigate the end-to-end learning of variational models, more precisely of the regularization term given some observ…

Cited by 0Source ↗Scholar ↗
2021

Unsupervised Reconstruction of Sea Surface Currents from AIS Maritime Traffic Data Using Learnable Variational Models

Simon Benaïchouche, Clément Le Goff, Yann Guichoux, François Rousseau, Ronan Fablet
ICASSP 2021accepted

Space oceanography missions, especially altimeter missions, have considerably improved the observation of sea surface dynamics over the last decades. They can however hardly resolve spatial scales below ~ 100km. Meanwhile the AIS (Automatic Identification System) monitoring of the maritime traffic i…

Cited by 0Source ↗Scholar ↗
2020

Assimilation-Based Learning of Chaotic Dynamical Systems from Noisy and Partial Data

Duong Nguyen, Said Ouala, Lucas Drumetz, Ronan Fablet
ICASSP 2020accepted

Despite some promising results under ideal conditions (i.e. noise-free and complete observation), learning chaotic dynamical systems from real life data is still a very challenging task. We propose a novel framework, which combines data assimilation schemes and neural network representation, namely…

Cited by 0Source ↗Scholar ↗
2020

Learning Endmember Dynamics in Multitemporal Hyperspectral Data Using A State-Space Model Formulation

Lucas Drumetz, Mauro Dalla Mura, Guillaume Tochon, Ronan Fablet
ICASSP 2020accepted

Hyperspectral image unmixing is an inverse problem aiming at recovering the spectral signatures of pure materials of interest (called endmembers) and estimating their proportions (called abundances) in every pixel of the image. However, in spite of a tremendous applicative potential and the avent of…

Cited by 7Source ↗Scholar ↗
2019

Learning Stochastic Representations of Geophysical Dynamics

Said Ouala, Ronan Fablet, Cédric Herzet, Bertrand Chapron, Ananda Pascual, Fabrice Collard +1
ICASSP 2019accepted

In the last years, Neural Networks have enriched the state-of-the-art in probabilistic modeling. This is principally due to the advances in deep learning which allow a better understanding of complex systems. However, the stochastic representation of spatio-temporal fields is still an open challenge…

Cited by 0Source ↗Scholar ↗
2019

Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection

Duong Nguyen, Oliver S. Kirsebom, Fábio Frazão, Ronan Fablet, Stan Matwin
ICASSP 2019accepted

In this paper, we adapt Recurrent Neural Networks with Stochastic Layers, which are the state-of-the-art for generating text, music and speech, to the problem of acoustic novelty detection. By integrating uncertainty into the hidden states, this type of network is able to learn the distribution of c…

Cited by 8Source ↗Scholar ↗
2016

Non-negative decomposition of linear relationships: Application to multi-source ocean remote sensing data

Manuel Lopez-Radcenco, Abdeldjalil Aïssa-El-Bey, Pierre Ailliot, Pierre Tandeo, Ronan Fablet
ICASSP 2016accepted

The identification and separation of contributions associated with different sources or processes is a general problem in signal and image processing. Here, we focus on the decomposition of multiple linear relationships and introduce a non-negative formulation. The proposed models can be viewed as g…

Cited by 0Source ↗Scholar ↗