English

Two-scale Neural Networks for Singularly Perturbed Dynamical Systems with Multiple Parameters

Numerical Analysis 2026-05-05 v1 Numerical Analysis Computational Physics

Abstract

We extend our two-scale neural-network method for scalar singularly perturbed problems with one small parameter to dynamical systems with multiple small parameters. To accommodate multiple small parameters, we use a single effective scale parameter defined as the geometric mean of all parameters. We thus augment the network input with a scale-aware feature, enabling it to capture sharp solution transitions intrinsically. Numerical experiments across a range of dynamical systems demonstrate that the proposed framework can handle coupled systems with multiple and high-contrast small parameters and obtain satisfactory accuracy in capturing solution features induced by small parameters.

Keywords

Cite

@article{arxiv.2605.02799,
  title  = {Two-scale Neural Networks for Singularly Perturbed Dynamical Systems with Multiple Parameters},
  author = {Qiao Zhuang and Taorui Wang and Rita Wanjiku and Majid Bani-Yaghoub and Zhongqiang Zhang},
  journal= {arXiv preprint arXiv:2605.02799},
  year   = {2026}
}
R2 v1 2026-07-01T12:48:52.672Z