Estimate of Koopman modes and eigenvalues with Kalman Filter

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Ningxin, Liu, Shuigen, Tong, Xin T., Jiang, Lijian
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916422767083520
author Liu, Ningxin
Liu, Shuigen
Tong, Xin T.
Jiang, Lijian
author_facet Liu, Ningxin
Liu, Shuigen
Tong, Xin T.
Jiang, Lijian
contents Dynamic mode decomposition (DMD) is a data-driven method of extracting spatial-temporal coherent modes from complex systems and providing an equation-free architecture to model and predict systems. However, in practical applications, the accuracy of DMD can be limited in extracting dynamical features due to sensor noise in measurements. We develop an adaptive method to constantly update dynamic modes and eigenvalues from noisy measurements arising from discrete systems. Our method is based on the Ensemble Kalman filter owing to its capability of handling time-varying systems and nonlinear observables. Our method can be extended to non-autonomous dynamical systems, accurately recovering short-time eigenvalue-eigenvector pairs and observables. Theoretical analysis shows that the estimation is accurate in long term data misfit. We demonstrate the method on both autonomous and non-autonomous dynamical systems to show its effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02815
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Estimate of Koopman modes and eigenvalues with Kalman Filter
Liu, Ningxin
Liu, Shuigen
Tong, Xin T.
Jiang, Lijian
Systems and Control
Probability
Dynamic mode decomposition (DMD) is a data-driven method of extracting spatial-temporal coherent modes from complex systems and providing an equation-free architecture to model and predict systems. However, in practical applications, the accuracy of DMD can be limited in extracting dynamical features due to sensor noise in measurements. We develop an adaptive method to constantly update dynamic modes and eigenvalues from noisy measurements arising from discrete systems. Our method is based on the Ensemble Kalman filter owing to its capability of handling time-varying systems and nonlinear observables. Our method can be extended to non-autonomous dynamical systems, accurately recovering short-time eigenvalue-eigenvector pairs and observables. Theoretical analysis shows that the estimation is accurate in long term data misfit. We demonstrate the method on both autonomous and non-autonomous dynamical systems to show its effectiveness.
title Estimate of Koopman modes and eigenvalues with Kalman Filter
topic Systems and Control
Probability
url https://arxiv.org/abs/2410.02815