Saved in:
Bibliographic Details
Main Author: Churchill, Victor
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.10854
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912167879507968
author Churchill, Victor
author_facet Churchill, Victor
contents We present a computational technique for modeling the evolution of dynamical systems in a reduced basis, with a focus on the challenging problem of modeling partially-observed partial differential equations (PDEs) on high-dimensional non-uniform grids. We address limitations of previous work on data-driven flow map learning in the sense that we focus on noisy and limited data to move toward data collection scenarios in real-world applications. Leveraging recent work on modeling PDEs in modal and nodal spaces, we present a neural network structure that is suitable for PDE modeling with noisy and limited data available only on a subset of the state variables or computational domain. In particular, spatial grid-point measurements are reduced using a learned linear transformation, after which the dynamics are learned in this reduced basis before being transformed back out to the nodal space. This approach yields a drastically reduced parameterization of the neural network compared with previous flow map models for nodal space learning. This allows for rapid high-resolution simulations, enabled by smaller training data sets and reduced training times.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10854
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Principal Component Flow Map Learning of PDEs from Incomplete, Limited, and Noisy Data
Churchill, Victor
Machine Learning
Dynamical Systems
We present a computational technique for modeling the evolution of dynamical systems in a reduced basis, with a focus on the challenging problem of modeling partially-observed partial differential equations (PDEs) on high-dimensional non-uniform grids. We address limitations of previous work on data-driven flow map learning in the sense that we focus on noisy and limited data to move toward data collection scenarios in real-world applications. Leveraging recent work on modeling PDEs in modal and nodal spaces, we present a neural network structure that is suitable for PDE modeling with noisy and limited data available only on a subset of the state variables or computational domain. In particular, spatial grid-point measurements are reduced using a learned linear transformation, after which the dynamics are learned in this reduced basis before being transformed back out to the nodal space. This approach yields a drastically reduced parameterization of the neural network compared with previous flow map models for nodal space learning. This allows for rapid high-resolution simulations, enabled by smaller training data sets and reduced training times.
title Principal Component Flow Map Learning of PDEs from Incomplete, Limited, and Noisy Data
topic Machine Learning
Dynamical Systems
url https://arxiv.org/abs/2407.10854