State-of-the-art strategies address the problem as a supervised learning task and optimize algorithms that predict subgrid fluxes based on information from coarse resolution models.
For numerous earth observation applications, one may benefit from various satellite sensors to address the reconstruction of some process or information of interest.
The complexity of real-world geophysical systems is often compounded by the fact that the observed measurements depend on hidden variables.
Modeling the subgrid-scale dynamics of reduced models is a long standing open problem that finds application in ocean, atmosphere and climate predictions where direct numerical simulation (DNS) is impossible.
The proposed framework significantly outperforms the operational state-of-the-art mapping pipeline and truly benefits from wide-swath data to resolve finer scales on the global map as well as in the SWOT sensor geometry.
Modelling trajectory in general, and vessel trajectory in particular, is a difficult task because of the multimodal and complex nature of motion data.
They are notable for the ability to include a deterministic component of the system and a stochastic one to represent random unknown factors.
Inevitably, a numerical simulation of a differential equation will then always be distinct from a true analytical solution.
In this paper we present a new strategy to model the subgrid-scale scalar flux in a three-dimensional turbulent incompressible flow using physics-informed neural networks (NNs).
The data-driven recovery of the unknown governing equations of dynamical systems has recently received an increasing interest.
The constant growth of maritime traffic leads to the need of automatic anomaly detection, which has been attracting great research attention.
Intriguingly, we also show that the variational models issued from the true Lorenz-63 and Lorenz-96 ODE representations may not lead to the best reconstruction performance.
The variational cost and the gradient-based solver are both stated as neural networks using automatic differentiation for the latter.
The upcoming Surface Water Ocean Topography (SWOT) satellite altimetry mission is expected to yield two-dimensional high-resolution measurements of Sea Surface Height (SSH), thus allowing for a better characterization of the mesoscale and submesoscale eddy field.
While deep learning frameworks open avenues in physical science, the design of physically-consistent deep neural network architectures is an open issue.
Representing maritime traffic patterns and detecting anomalies from them are key to vessel monitoring and maritime situational awareness.
We introduce a new strategy designed to help physicists discover hidden laws governing dynamical systems.
In this paper, we address the end-to-end learning of representations of signals, images and image sequences from irregularly-sampled data, i. e. when the training data involved missing data.
This paper addresses the data-driven identification of latent dynamical representations of partially-observed systems, i. e., dynamical systems for which some components are never observed, with an emphasis on forecasting applications, including long-term asymptotic patterns.
To solve for the joint inference of the hidden dynamics and of model parameters, we combine neural-network representations and state-of-the-art assimilation schemes.
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.
Ranked #2 on Acoustic Novelty Detection on A3Lab PASCAL CHiME
In a world of global trading, maritime safety, security and efficiency are crucial issues.
The forecasting and reconstruction of ocean and atmosphere dynamics from satellite observation time series are key challenges.
This paper addresses the understanding and characterization of residual networks (ResNet), which are among the state-of-the-art deep learning architectures for a variety of supervised learning problems.
Due to the increasing availability of large-scale observation and simulation datasets, data-driven representations arise as efficient and relevant computation representations of dynamical systems for a wide range of applications, where model-driven models based on ordinary differential equation remain the state-of-the-art approaches.
This work presents EddyNet, a deep learning based architecture for automated eddy detection and classification from Sea Surface Height (SSH) maps provided by the Copernicus Marine and Environment Monitoring Service (CMEMS).
Super-resolution is a classical problem in image processing, with numerous applications to remote sensing image enhancement.