Saved in:
Bibliographic Details
Main Authors: Su, Liangyu, Shu, Jun, Liu, Rui, Meng, Deyu, Xu, Zongben
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.14011
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918339587080192
author Su, Liangyu
Shu, Jun
Liu, Rui
Meng, Deyu
Xu, Zongben
author_facet Su, Liangyu
Shu, Jun
Liu, Rui
Meng, Deyu
Xu, Zongben
contents Representing and predicting high-dimensional and spatiotemporally chaotic dynamical systems remains a fundamental challenge in dynamical systems and machine learning. Although data-driven models can achieve accurate short-term forecasts, they often lack stability, interpretability, and scalability in regimes dominated by broadband or continuous spectra. Koopman-based approaches provide a principled linear perspective on nonlinear dynamics, but existing methods rely on restrictive finite-dimensional assumptions or explicit spectral parameterizations that degrade in high-dimensional settings. Against these issues, we introduce KoopGen, a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators. By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation while enforcing exact operator-theoretic constraints during learning. Across systems ranging from nonlinear oscillators to high-dimensional chaotic and spatiotemporal dynamics, KoopGen improves prediction accuracy and stability, while clarifying which components of continuous-spectrum dynamics admit interpretable and learnable representations.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14011
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra
Su, Liangyu
Shu, Jun
Liu, Rui
Meng, Deyu
Xu, Zongben
Machine Learning
Representing and predicting high-dimensional and spatiotemporally chaotic dynamical systems remains a fundamental challenge in dynamical systems and machine learning. Although data-driven models can achieve accurate short-term forecasts, they often lack stability, interpretability, and scalability in regimes dominated by broadband or continuous spectra. Koopman-based approaches provide a principled linear perspective on nonlinear dynamics, but existing methods rely on restrictive finite-dimensional assumptions or explicit spectral parameterizations that degrade in high-dimensional settings. Against these issues, we introduce KoopGen, a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators. By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation while enforcing exact operator-theoretic constraints during learning. Across systems ranging from nonlinear oscillators to high-dimensional chaotic and spatiotemporal dynamics, KoopGen improves prediction accuracy and stability, while clarifying which components of continuous-spectrum dynamics admit interpretable and learnable representations.
title KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra
topic Machine Learning
url https://arxiv.org/abs/2602.14011