A Bayesian Nonlinear Reduced Order Modeling Using Variational AutoEncoders

A Bayesian Nonlinear Reduced Order Modeling Using Variational AutoEncoders

This paper presents a new nonlinear projection based model reduction using convolutional Variational AutoEncoders (VAEs). This framework is applied on transient incompressible flows. The accuracy is obtained thanks to the expression of the velocity and pressure fields in a nonlinear manifold maximis...

Full description

Bibliographic Details
Main Authors: Nissrine Akkari, Fabien Casenave, Elie Hachem, David Ryckelynck
Format: Article
Language:English
Published: MDPI AG 2022-10-01
Series:Fluids
Subjects:
Navier–Stokes equations
nonstationary
reduced order model
variational Bayesian methods
variational autoencoders
approximation error
Online Access:https://www.mdpi.com/2311-5521/7/10/334

Internet

https://www.mdpi.com/2311-5521/7/10/334

Similar Items