Learning phase-space flows using time-discrete implicit Runge-Kutta PINNs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Corral, Álvaro Fernández, Mendoza, Nicolás, Iske, Armin, Yachmenev, Andrey, Küpper, Jochen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910619500806144
author Corral, Álvaro Fernández
Mendoza, Nicolás
Iske, Armin
Yachmenev, Andrey
Küpper, Jochen
author_facet Corral, Álvaro Fernández
Mendoza, Nicolás
Iske, Armin
Yachmenev, Andrey
Küpper, Jochen
contents We present a computational framework for obtaining multidimensional phase-space solutions of systems of non-linear coupled differential equations, using high-order implicit Runge-Kutta Physics- Informed Neural Networks (IRK-PINNs) schemes. Building upon foundational work originally solving differential equations for fields depending on coordinates [J. Comput. Phys. 378, 686 (2019)], we adapt the scheme to a context where the coordinates are treated as functions. This modification enables us to efficiently solve equations of motion for a particle in an external field. Our scheme is particularly useful for explicitly time-independent and periodic fields. We apply this approach to successfully solve the equations of motion for a mass particle placed in a central force field and a charged particle in a periodic electric field.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16826
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning phase-space flows using time-discrete implicit Runge-Kutta PINNs
Corral, Álvaro Fernández
Mendoza, Nicolás
Iske, Armin
Yachmenev, Andrey
Küpper, Jochen
Machine Learning
Artificial Intelligence
Numerical Analysis
Dynamical Systems
We present a computational framework for obtaining multidimensional phase-space solutions of systems of non-linear coupled differential equations, using high-order implicit Runge-Kutta Physics- Informed Neural Networks (IRK-PINNs) schemes. Building upon foundational work originally solving differential equations for fields depending on coordinates [J. Comput. Phys. 378, 686 (2019)], we adapt the scheme to a context where the coordinates are treated as functions. This modification enables us to efficiently solve equations of motion for a particle in an external field. Our scheme is particularly useful for explicitly time-independent and periodic fields. We apply this approach to successfully solve the equations of motion for a mass particle placed in a central force field and a charged particle in a periodic electric field.
title Learning phase-space flows using time-discrete implicit Runge-Kutta PINNs
topic Machine Learning
Artificial Intelligence
Numerical Analysis
Dynamical Systems
url https://arxiv.org/abs/2409.16826