Intelligent Attractors for Singularly Perturbed Dynamical Systems
Singularly perturbed dynamical systems, commonly known as fast-slow systems, play a crucial role in various applications such as plasma physics. They are closely related to reduced order modeling, closures, and structure-preserving numerical algorithms for multiscale modeling. A powerful and well-kn...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-02 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Singularly perturbed dynamical systems, commonly known as fast-slow systems, play a crucial role in various applications such as plasma physics. They are closely related to reduced order modeling, closures, and structure-preserving numerical algorithms for multiscale modeling. A powerful and well-known tool to address these systems is the Fenichel normal form, which significantly simplifies fast dynamics near slow manifolds through a transformation. However, the Fenichel normal form is difficult to realize in conventional numerical algorithms. In this work, we explore an alternative way of realizing it through structure-preserving machine learning. Specifically, a fast-slow neural network (FSNN) is proposed for learning data-driven models of singularly perturbed dynamical systems with dissipative fast timescale dynamics. Our method enforces the existence of a trainable, attracting invariant slow manifold as a hard constraint. Closed-form representation of the slow manifold enables efficient integration on the slow time scale and significantly improves prediction accuracy beyond the training data. We demonstrate the FSNN on several examples that exhibit multiple timescales, including the Grad moment system from hydrodynamics, two-scale Lorentz96 equations for modeling atmospheric dynamics, and Abraham-Lorentz dynamics modeling radiation reaction of electrons in a magnetic field. |
---|---|
ISSN: | 2331-8422 |