activity
20192022
most citedRepresenting ill-known parts of a numerical model using a machine learning approach

2 citations · 2 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG2022

Learning 4DVAR inversion directly from observations

Arthur Filoche, Julien Brajard, Anastase Charantonis +1

Variational data assimilation and deep learning share many algorithmic aspects in common. While the former focuses on system state estimation, the latter provides great inductive b…

eess.SP2021

Fusion of rain radar images and wind forecasts in a deep learning model applied to rain nowcasting

Vincent Bouget, Dominique Béréziat, Julien Brajard +2

Short- or mid-term rainfall forecasting is a major task with several environmental applications such as agricultural management or flood risk monitoring. Existing data-driven appro…

physics.comp-ph2020

Combining data assimilation and machine learning to infer unresolved scale parametrisation

Julien Brajard, Alberto Carrassi, Marc Bocquet +1

In recent years, machine learning (ML) has been proposed to devise data-driven parametrisations of unresolved processes in dynamical numerical models. In most cases, the ML trainin…

stat.ML2020

Bayesian inference of chaotic dynamics by merging data assimilation, machine learning and expectation-maximization

Marc Bocquet, Julien Brajard, Alberto Carrassi +1

The reconstruction from observations of high-dimensional chaotic dynamics such as geophysical flows is hampered by (i) the partial and noisy observations that can realistically be…

stat.ML2020

Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 model

Julien Brajard, Alberto Carassi, Marc Bocquet +1

A novel method, based on the combination of data assimilation and machine learning is introduced. The new hybrid approach is designed for a two-fold scope: (i) emulating hidden, po…

physics.data-an20192 cited

Representing ill-known parts of a numerical model using a machine learning approach

Julien Brajard, Anastase Charantonis, Jérôme Sirven

In numerical modeling of the Earth System, many processes remain unknown or ill represented (let us quote sub-grid processes, the dependence to unknown latent variables or the non-…