Ronan Fablet
YOU?
Author Swipe
View article: Neural ocean forecasting from sparse satellite-derived observations: a case-study for SSH dynamics and altimetry data
Neural ocean forecasting from sparse satellite-derived observations: a case-study for SSH dynamics and altimetry data Open
We present an end-to-end deep learning framework for short-term forecasting of global sea surface dynamics based on sparse satellite altimetry data. Building on two state-of-the-art architectures: U-Net and 4DVarNet, originally developed f…
View article: Multiscale neural assimilation scheme for high-resolution sea surface temperature reconstruction from satellite observations
Multiscale neural assimilation scheme for high-resolution sea surface temperature reconstruction from satellite observations Open
Sea Surface Temperature (SST) retrieved from satellites is a crucial variable for weather prediction and climate monitoring, yet satellite-based SST observations are often hindered by orbital constraints and cloud cover-especially in regio…
View article: Learning‐Based Calibration of Ocean Carbon Models to Tackle Physical Forcing Uncertainties and Observation Sparsity
Learning‐Based Calibration of Ocean Carbon Models to Tackle Physical Forcing Uncertainties and Observation Sparsity Open
Biogeochemical (BGC) ocean models are simplified representations of complex coupled processes, usually resulting in a large number of parameters, that need to be calibrated. In general, these parameters are constrained relying on incomplet…
View article: Estimating the variability of deep-ocean particle flux collected by sediment traps using satellite data and machine learning
Estimating the variability of deep-ocean particle flux collected by sediment traps using satellite data and machine learning Open
The gravitational pump plays a key role in the ocean carbon cycle by exporting sinking organic carbon from the surface to the deep ocean. Deep sediment trap time series provide unique measurements of this sequestered carbon flux. Sinking p…
View article: Enhanced Computational Complexity in Continuous-Depth Models: Neural Ordinary Differential Equations With Trainable Numerical Schemes
Enhanced Computational Complexity in Continuous-Depth Models: Neural Ordinary Differential Equations With Trainable Numerical Schemes Open
Neural Ordinary Differential Equations (NODEs) serve as continuous-time analogs of residual networks. They provide a system-theoretic perspective on neural network architecture design and offer natural solutions for time series modeling, f…
View article: Neural Variational Data Assimilation with Uncertainty Quantification Using SPDE Priors
Neural Variational Data Assimilation with Uncertainty Quantification Using SPDE Priors Open
The spatiotemporal interpolation of large geophysical datasets has historically been addressed by optimal interpolation (OI) and more sophisticated equation-based or data-driven data assimilation (DA) techniques. Recent advances in the dee…
View article: Neural Prediction of Lagrangian Drift Trajectories on the Sea Surface
Neural Prediction of Lagrangian Drift Trajectories on the Sea Surface Open
This study proposes a new deep learning approach for the simulation of Lagrangian drift at the sea surface with the objective to overcome the current limitations of the existing model-based and learning-based methods. The proposed framewor…
View article: Neural Data Assimilation for Regime Shift Monitoring of an Idealized AMOC Chaotic Model
Neural Data Assimilation for Regime Shift Monitoring of an Idealized AMOC Chaotic Model Open
Data assimilation (DA) reconstructs and forecasts the dynamics of geophysical processes using available observations and physical a priori. Recently, the hybridization of DA and deep learning has opened new perspectives to address model‐da…
View article: Simulation-informed deep learning for enhanced SWOT observations of fine-scale ocean dynamics
Simulation-informed deep learning for enhanced SWOT observations of fine-scale ocean dynamics Open
Oceanic processes at fine scales are crucial yet difficult to observe accurately due to limitations in satellite and in-situ measurements. The Surface Water and Ocean Topography (SWOT) mission provides high-resolution Sea Surface Height (S…
View article: EDITO-Model Lab: towards the next generation of ocean numerical models
EDITO-Model Lab: towards the next generation of ocean numerical models Open
The European Commission launched the European Digital Twin of the Ocean (EDITO) at the One Ocean Summit in Brest, France, in February 2022. The EU is building the infrastructure backbone of EDITO through two projects: EDITO-Model Lab and E…
View article: Probabilistic Diffusion Models for Ocean Chlorophyll-a Prediction
Probabilistic Diffusion Models for Ocean Chlorophyll-a Prediction Open
Phytoplankton play a key role in maintaining marine ecosystems and regulating global carbon dioxide concentrations through photosynthesis. Thus, it is crucial to assess and understand their temporal variations. However, fluctuations of phy…
View article: Deep Conditional Emulators for calibrating ocean vertical physics schemes
Deep Conditional Emulators for calibrating ocean vertical physics schemes Open
Differentiable programming has emerged as a powerful tool in geoscientific modelling, offering new possibilities for optimization and parameter calibration. However, this approach requires the underlying physical models to be differentiabl…
View article: Leveraging Differentiable Programming and Online Learning for the design of Hybrid Numerical Models
Leveraging Differentiable Programming and Online Learning for the design of Hybrid Numerical Models Open
Earth system models (ESMs) are widely used to study climate changes resulting from both anthropogenic and natural perturbations. Over the past years, significant advances have been made through the development of new numerical schemes, ref…
View article: OceanBench - Short-Term Global Ocean Forecasting
OceanBench - Short-Term Global Ocean Forecasting Open
The increasing adoption of AI-based approaches in Earth system sciences has led to breakthroughs in modeling and forecasting, exemplified by state-of-the-art performance of neural weather forecasting systems [Bi et al., 2023, Lam et al., 2…
View article: Performance Gains and Advantages of 4DVarNet in End-to-End Learning for Data Assimilation
Performance Gains and Advantages of 4DVarNet in End-to-End Learning for Data Assimilation Open
The 4D variational assimilation (4DVar) framework is widely used in classical numerical weather prediction and geophysical data assimilation. However, a crucial assumption in 4DVar is that the model state that is close to the true state co…
View article: Score-based Diffusion Models for the Space-Time Interpolation of Sea Surface Turbidity
Score-based Diffusion Models for the Space-Time Interpolation of Sea Surface Turbidity Open
This study explores the application of score-based generative diffusion models for mapping sea surface Suspended Particulate Matter (SPM) of the Dutch Wadden Sea using satellite-derived images, focusing on their comparative efficacy agains…
View article: Level 4 global topography mapping with 4DVarNet
Level 4 global topography mapping with 4DVarNet Open
The study of mesoscale oceanic eddy dynamics requires regular, high-resolution space-time grids of topography observations. However, most observations come from the constellation of altimetry satellites, which measure the topography along …
View article: Integrating wide-swath altimetry data into Level-4 multi-mission maps
Integrating wide-swath altimetry data into Level-4 multi-mission maps Open
Real-time observation of ocean surface topography is essential for various oceanographic applications. Historically, these observations have mainly relied on satellite nadir altimetry data, which were limited to observation scales greater …
View article: Observation-Only Deep Learning for Gappy Satellite-Derived Ocean Color Data Using 4DVarNet
Observation-Only Deep Learning for Gappy Satellite-Derived Ocean Color Data Using 4DVarNet Open
Monitoring optical properties of coastal and open ocean waters is crucial to assessing the health of marine ecosystems. Deep learning offers a promising approach to address these ecosystem dynamics, especially in scenarios where gap-free g…
View article: Multimodal learning–based reconstruction of high-resolution spatial wind speed fields
Multimodal learning–based reconstruction of high-resolution spatial wind speed fields Open
Wind speed at the sea surface is a key quantity for a variety of scientific applications and human activities. For its importance, many observation techniques exist, ranging from in situ to satellite observations. However, none of such tec…
View article: Generalization Performance of Neural Mapping Schemes for the Space–Time Interpolation of Satellite-Derived Ocean Color Datasets
Generalization Performance of Neural Mapping Schemes for the Space–Time Interpolation of Satellite-Derived Ocean Color Datasets Open
Neural mapping schemes have become appealing approaches to deliver gap-free satellite-derived products for sea surface tracers. The generalization performance of these learning-based approaches naturally arises as a key challenge. This is …
View article: Estimating the variability of deep ocean particle flux collected by sediment traps using satellite data and machine learning
Estimating the variability of deep ocean particle flux collected by sediment traps using satellite data and machine learning Open
The gravitational pump plays a key role in the ocean carbon cycle by exporting sinking organic carbon from the surface to the deep ocean. Deep sediment trap time-series provide unique measurements of this sequestered carbon flux. Sinking p…
View article: Predicting particle catchment areas of deep-ocean sediment traps using machine learning
Predicting particle catchment areas of deep-ocean sediment traps using machine learning Open
The ocean's biological carbon pump plays a major role in climate and biogeochemical cycles. Photosynthesis at the surface produces particles that are exported to the deep ocean by gravity. Sediment traps, which measure deep-carbon fluxes, …
View article: Multi-path long-term vessel trajectories forecasting with probabilistic feature fusion for problem shifting
Multi-path long-term vessel trajectories forecasting with probabilistic feature fusion for problem shifting Open
This paper presents a deep auto-encoder model and a phased framework approach to predict the next 12 h of vessel trajectories using 1 to 3 h of Automatic Identification System data as input. The strategy involves fusing spatiotemporal feat…
View article: Integrating wide swath altimetry data into Level-4 multi-mission maps
Integrating wide swath altimetry data into Level-4 multi-mission maps Open
Real-time observation of ocean surface topography is essential for various oceanographic applications. Historically, these observations relied mainly on satellite nadir altimetry data, which were limited to observe scales greater than appr…
View article: Contrasted Trends in Chlorophyll‐<i>a</i> Satellite Products
Contrasted Trends in Chlorophyll‐<i>a</i> Satellite Products Open
Phytoplankton sustains marine ecosystems and influences the global carbon cycle. This study analyzes trends in surface chlorophyll‐ a concentration (Schl), a proxy for phytoplankton biomass, using six of the most widely used merged satelli…
View article: Convolutional Encoding and Normalizing Flows: A Deep Learning Approach for Offshore Wind Speed Probabilistic Forecasting in the Mediterranean Sea
Convolutional Encoding and Normalizing Flows: A Deep Learning Approach for Offshore Wind Speed Probabilistic Forecasting in the Mediterranean Sea Open
The safe and efficient execution of offshore operations requires short-term (1–6 h ahead) high-quality probabilistic forecasts of metocean variables. The development areas for offshore wind projects, potentially in high depths, make it dif…
View article: Training Neural Mapping Schemes for Satellite Altimetry With Simulation Data
Training Neural Mapping Schemes for Satellite Altimetry With Simulation Data Open
Satellite altimetry combined with data assimilation and optimal interpolation schemes have deeply renewed our ability to monitor sea surface dynamics. Recently, deep learning schemes have emerged as appealing solutions to address space‐tim…