Data-Driven Autoencoder Numerical Solver with Uncertainty Quantification for Fast Physical Simulations

Traditional partial differential equation (PDE) solvers can be computationally expensive, which motivates the development of faster methods, such as reduced-order-models (ROMs). We present GPLaSDI, a hybrid deep-learning and Bayesian ROM. GPLaSDI trains an autoencoder on full-order-model (FOM) data...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-12
Main Authors: Bonneville, Christophe, Choi, Youngsoo, Ghosh, Debojyoti, Belof, Jonathan L
Format: Article
Language:English
Subjects:
Deep learning
Fluid mechanics
Gaussian process
Machine learning
Mathematical models
Partial differential equations
Reduced order models
Solvers
Uncertainty
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traditional partial differential equation (PDE) solvers can be computationally expensive, which motivates the development of faster methods, such as reduced-order-models (ROMs). We present GPLaSDI, a hybrid deep-learning and Bayesian ROM. GPLaSDI trains an autoencoder on full-order-model (FOM) data and simultaneously learns simpler equations governing the latent space. These equations are interpolated with Gaussian Processes, allowing for uncertainty quantification and active learning, even with limited access to the FOM solver. Our framework is able to achieve up to 100,000 times speed-up and less than 7% relative error on fluid mechanics problems.
ISSN:2331-8422