Exploring Multiple Timescale Dynamics Using Geometric Singular Perturbation-Informed Neural Networks (GSPINNs)
SIAM Journal on Scientific Computing · 30.04.2026 · 48 (2) · C301-C329
DOI: 10.1137/24m1722018 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 10.04.2026. Verfasst von Hamid Mofidi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing National Science Foundation.
Abstract (Originalsprache)
Multiple timescale systems have long been a subject of extensive study, with geometric singular perturbation theory (GSPT) emerging as a common tool for analyzing such systems. In this work, we present a comprehensive study of ordinary differential equations in the form of boundary value problems that describe multiple timescale systems, focusing specifically on normally hyperbolic systems. We introduce a novel method, geometric singular perturbation-informed neural networks (GSPINNs), which combines the analytical rigor of GSPT with the modeling power of physics-informed neural networks. Our approach converts the system into a connecting problem, allowing for the discovery of detailed dynamical characteristics that provide deeper insights into the system’s behavior. These solutions are then numerically approximated using GSPINNs. We validated our method, GSPINNs, through various challenging problems where traditional methods fail to capture the intricate dynamics of the system. For moderately nonhyperbolic, multiscale problems that are not extremely stiff, GSPINN remains stable enough to yield accurate solutions without resorting to blowup techniques, demonstrating its robustness in such cases. Our analysis and numerical experiments show that GSPINNs produce accurate and stable solutions for stiff fast-slow boundary value problems across a range of challenging examples, whereas conventional finite difference, shooting, and baseline PINN solvers often struggle. This work opens new opportunities for practical applications in modeling and simulating complex systems with varying timescales.
Förderung
- National Natural Science Foundation of China
- Beijing National Science Foundation
Zitieren
APA
Mofidi, H., Raissi, M., & Yang, W. (2026). Exploring Multiple Timescale Dynamics Using Geometric Singular Perturbation-Informed Neural Networks (GSPINNs). SIAM Journal on Scientific Computing, 48(2), C301-C329. https://doi.org/10.1137/24m1722018
Vancouver
Mofidi H, Raissi M, Yang W. Exploring Multiple Timescale Dynamics Using Geometric Singular Perturbation-Informed Neural Networks (GSPINNs). SIAM Journal on Scientific Computing. 2026;48(2):C301-C329. doi:10.1137/24m1722018
BibTeX
@article{Mofidi2026,
author = {Mofidi, Hamid and Raissi, Maziar and Yang, Wuyue},
title = {Exploring Multiple Timescale Dynamics Using Geometric Singular Perturbation-Informed Neural Networks (GSPINNs)},
journal = {SIAM Journal on Scientific Computing},
year = {2026},
volume = {48},
number = {2},
pages = {C301--C329},
doi = {10.1137/24m1722018}
}
EUVIMED