EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamical system identification, model selection, and model uncertainty quantification by Bayesian inference

Robert K Niven iD, Laurent Cordier iD, Ali Mohammad-Djafari iD, Markus Abel iD, Markus Quade iD

Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.08.2024 · 34 (8)

DOI: 10.1063/5.0200684 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 27.08.2024. Verfasst von Robert K Niven und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Engineering and Technology, The University of New South Wales, Canberra, ACT 2600, Australia. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of New South Wales, Institut Pprime / CNRS / University of Poitiers, France, CentraleSupelec, Gif-sur-Yvette, France.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a Bayesian maximum a posteriori (MAP) framework for dynamical system identification from time-series data. This is shown to be equivalent to a generalized Tikhonov regularization, providing a rational justification for the choice of the residual and regularization terms, respectively, from the negative logarithms of the likelihood and prior distributions. In addition to the estimation of model coefficients, the Bayesian interpretation gives access to the full apparatus for Bayesian inference, including the ranking of models, the quantification of model uncertainties, and the estimation of unknown (nuisance) hyperparameters. Two Bayesian algorithms, joint MAP and variational Bayesian approximation, are compared to the least absolute shrinkage and selection operator (LASSO), ridge regression, and the sparse identification of nonlinear dynamics (SINDy) algorithms for sparse regression by application to several dynamical systems with added Gaussian or Laplace noise. For multivariate Gaussian likelihood and prior distributions, the Bayesian formulation gives Gaussian posterior and evidence distributions, in which the numerator terms can be expressed in terms of the Mahalanobis distance or “Gaussian norm” ||y−y^||M−12=(y−y^)⊤M−1(y−y^), where y is a vector variable, y^ is its estimator, and M is the covariance matrix. The posterior Gaussian norm is shown to provide a robust metric for quantitative model selection for the different systems and noise models examined.

Autor:innen und Institutionen

  • School of Engineering and Technology, The University of New South Wales, Canberra, ACT 2600, Australia.
  • Institut Pprime, CNRS-Université de Poitiers-ISAE-ENSMA, 86360 Chasseneuil-du-Poitou, France.
  • Laboratoire des Signaux et Systèmes (L2S), CentraleSupélec, 91190 Gif-sur-Yvette, France.
  • Ambrosys GmbH, 14482 Potsdam, Germany.

ORCID-Profile: Robert K Niven, Laurent Cordier, Ali Mohammad-Djafari, Markus Abel, Markus Quade

Förderung

  • University of New South Wales
  • Institut Pprime / CNRS / University of Poitiers, France
  • CentraleSupelec, Gif-sur-Yvette, France
  • Ambrosys GmbH, Potsdam, Germany

Zitieren

APA

Niven, R. K., Cordier, L., Mohammad-Djafari, A., Abel, M., & Quade, M. (2024). Dynamical system identification, model selection, and model uncertainty quantification by Bayesian inference. Chaos: An Interdisciplinary Journal of Nonlinear Science, 34(8). https://doi.org/10.1063/5.0200684

Vancouver

Niven RK, Cordier L, Mohammad-Djafari A, Abel M, Quade M. Dynamical system identification, model selection, and model uncertainty quantification by Bayesian inference. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2024;34(8). doi:10.1063/5.0200684

BibTeX
@article{Niven2024,
  author = {Niven, Robert K and Cordier, Laurent and Mohammad-Djafari, Ali and Abel, Markus and Quade, Markus},
  title = {Dynamical system identification, model selection, and model uncertainty quantification by Bayesian inference},
  journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
  year = {2024},
  volume = {34},
  number = {8},
  doi = {10.1063/5.0200684}
}
Kostenlos starten →