Scalable nonlinear manifold reduced order model for dynamical systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zanardi, Ivan, Diaz, Alejandro N., Chung, Seung Whan, Panesi, Marco, Choi, Youngsoo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916501364146176
author Zanardi, Ivan
Diaz, Alejandro N.
Chung, Seung Whan
Panesi, Marco
Choi, Youngsoo
author_facet Zanardi, Ivan
Diaz, Alejandro N.
Chung, Seung Whan
Panesi, Marco
Choi, Youngsoo
contents The domain decomposition (DD) nonlinear-manifold reduced-order model (NM-ROM) represents a computationally efficient method for integrating underlying physics principles into a neural network-based, data-driven approach. Compared to linear subspace methods, NM-ROMs offer superior expressivity and enhanced reconstruction capabilities, while DD enables cost-effective, parallel training of autoencoders by partitioning the domain into algebraic subdomains. In this work, we investigate the scalability of this approach by implementing a "bottom-up" strategy: training NM-ROMs on smaller domains and subsequently deploying them on larger, composable ones. The application of this method to the two-dimensional time-dependent Burgers' equation shows that extrapolating from smaller to larger domains is both stable and effective. This approach achieves an accuracy of 1% in relative error and provides a remarkable speedup of nearly 700 times.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00507
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scalable nonlinear manifold reduced order model for dynamical systems
Zanardi, Ivan
Diaz, Alejandro N.
Chung, Seung Whan
Panesi, Marco
Choi, Youngsoo
Numerical Analysis
Dynamical Systems
Computational Physics
The domain decomposition (DD) nonlinear-manifold reduced-order model (NM-ROM) represents a computationally efficient method for integrating underlying physics principles into a neural network-based, data-driven approach. Compared to linear subspace methods, NM-ROMs offer superior expressivity and enhanced reconstruction capabilities, while DD enables cost-effective, parallel training of autoencoders by partitioning the domain into algebraic subdomains. In this work, we investigate the scalability of this approach by implementing a "bottom-up" strategy: training NM-ROMs on smaller domains and subsequently deploying them on larger, composable ones. The application of this method to the two-dimensional time-dependent Burgers' equation shows that extrapolating from smaller to larger domains is both stable and effective. This approach achieves an accuracy of 1% in relative error and provides a remarkable speedup of nearly 700 times.
title Scalable nonlinear manifold reduced order model for dynamical systems
topic Numerical Analysis
Dynamical Systems
Computational Physics
url https://arxiv.org/abs/2412.00507