Learning Physics Informed Neural ODEs With Partial Measurements

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ghanem, Paul, Demirkaya, Ahmet, Imbiriba, Tales, Ramezani, Alireza, Danziger, Zachary, Erdogmus, Deniz
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915060545224704
author Ghanem, Paul
Demirkaya, Ahmet
Imbiriba, Tales
Ramezani, Alireza
Danziger, Zachary
Erdogmus, Deniz
author_facet Ghanem, Paul
Demirkaya, Ahmet
Imbiriba, Tales
Ramezani, Alireza
Danziger, Zachary
Erdogmus, Deniz
contents Learning dynamics governing physical and spatiotemporal processes is a challenging problem, especially in scenarios where states are partially measured. In this work, we tackle the problem of learning dynamics governing these systems when parts of the system's states are not measured, specifically when the dynamics generating the non-measured states are unknown. Inspired by state estimation theory and Physics Informed Neural ODEs, we present a sequential optimization framework in which dynamics governing unmeasured processes can be learned. We demonstrate the performance of the proposed approach leveraging numerical simulations and a real dataset extracted from an electro-mechanical positioning system. We show how the underlying equations fit into our formalism and demonstrate the improved performance of the proposed method when compared with baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08681
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Physics Informed Neural ODEs With Partial Measurements
Ghanem, Paul
Demirkaya, Ahmet
Imbiriba, Tales
Ramezani, Alireza
Danziger, Zachary
Erdogmus, Deniz
Machine Learning
Artificial Intelligence
Learning dynamics governing physical and spatiotemporal processes is a challenging problem, especially in scenarios where states are partially measured. In this work, we tackle the problem of learning dynamics governing these systems when parts of the system's states are not measured, specifically when the dynamics generating the non-measured states are unknown. Inspired by state estimation theory and Physics Informed Neural ODEs, we present a sequential optimization framework in which dynamics governing unmeasured processes can be learned. We demonstrate the performance of the proposed approach leveraging numerical simulations and a real dataset extracted from an electro-mechanical positioning system. We show how the underlying equations fit into our formalism and demonstrate the improved performance of the proposed method when compared with baselines.
title Learning Physics Informed Neural ODEs With Partial Measurements
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.08681