English

Machine Learning-Based Nonlinear Nudging for Chaotic Dynamical Systems

Machine Learning 2025-08-11 v1 Numerical Analysis Numerical Analysis

Abstract

Nudging is an empirical data assimilation technique that incorporates an observation-driven control term into the model dynamics. The trajectory of the nudged system approaches the true system trajectory over time, even when the initial conditions differ. For linear state space models, such control terms can be derived under mild assumptions. However, designing effective nudging terms becomes significantly more challenging in the nonlinear setting. In this work, we propose neural network nudging, a data-driven method for learning nudging terms in nonlinear state space models. We establish a theoretical existence result based on the Kazantzis--Kravaris--Luenberger observer theory. The proposed approach is evaluated on three benchmark problems that exhibit chaotic behavior: the Lorenz 96 model, the Kuramoto--Sivashinsky equation, and the Kolmogorov flow.

Keywords

Cite

@article{arxiv.2508.05778,
  title  = {Machine Learning-Based Nonlinear Nudging for Chaotic Dynamical Systems},
  author = {Jaemin Oh and Jinsil Lee and Youngjoon Hong},
  journal= {arXiv preprint arXiv:2508.05778},
  year   = {2025}
}

Comments

21 pages, 5 figures, 6 tables

R2 v1 2026-07-01T04:39:51.169Z