β-Variational autoencoders and transformers for reduced-order modelling of fluid flows
Abstract Variational autoencoder architectures have the potential to develop reduced-order models for chaotic fluid flows. We propose a method for learning compact and near-orthogonal reduced-order models using a combination of a β-variational autoencoder and a transformer, tested on numerical data...
Main Authors: | Alberto Solera-Rico, Carlos Sanmiguel Vila, Miguel Gómez-López, Yuning Wang, Abdulrahman Almashjary, Scott T. M. Dawson, Ricardo Vinuesa |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-02-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-024-45578-4 |
Similar Items
-
Improving Variational Graph Autoencoders With Multi-Order Graph Convolutions
by: Lining Yuan, et al.
Published: (2024-01-01) -
Multichannel Variational Autoencoder-Based Speech Separation in Designated Speaker Order
by: Lele Liao, et al.
Published: (2022-11-01) -
Enhancing Conformational Sampling for Intrinsically Disordered and Ordered Proteins by Variational Autoencoder
by: Jun-Jie Zhu, et al.
Published: (2023-04-01) -
A Bayesian Nonlinear Reduced Order Modeling Using Variational AutoEncoders
by: Nissrine Akkari, et al.
Published: (2022-10-01) -
Disentangling disentanglement in variational autoencoders
by: Mathieu, E, et al.
Published: (2019)