EUVIMEDEUVIMED entdecken
Crossref

Model adaptive phase space reconstruction

Jayesh M Dhadphale iD, K Hauke Kraemer iD, Maximilian Gelbrecht iD, Jürgen Kurths iD, Norbert Marwan iD, R I Sujith iD

Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.07.2024 · 34 (7)

DOI: 10.1063/5.0194330 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 10.07.2024. Verfasst von Jayesh M Dhadphale und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Aerospace Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu 600036, India. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: Ministry of Education, India, Office of Global Engagement, IIT Madras, Volkswagen Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Phase space reconstruction (PSR) methods allow for the analysis of low-dimensional data with methods from dynamical systems theory, but their application to prediction models, such as those from machine learning (ML), is limited. Therefore, we here present a model adaptive phase space reconstruction (MAPSR) method that unifies the process of PSR with the modeling of the dynamical system. MAPSR is a differentiable PSR based on time-delay embedding and enables ML methods for modeling. The quality of the reconstruction is evaluated by the prediction loss. The discrete-time signal is converted into a continuous-time signal to achieve a loss function, which is differentiable with respect to the embedding delays. The delay vector, which stores all potential embedding delays, is updated along with the trainable parameters of the model to minimize prediction loss. Thus, MAPSR does not rely on any threshold or statistical criterion for determining the dimension and the set of delay values for the embedding process. We apply the MAPSR method to uni- and multivariate time series stemming from chaotic dynamical systems and a turbulent combustor. We find that for the Lorenz system, the model trained with the MAPSR method is able to predict chaotic time series for nearly seven to eight Lyapunov time scales, which is found to be much better compared to other PSR methods [AMI-FNN (average mutual information-false nearest neighbor) and PECUZAL (Pecora-Uzal) methods]. For the univariate time series from the turbulent combustor, the long-term cumulative prediction error of the MAPSR method for the regime of chaos stays between other methods, and for the regime of intermittency, MAPSR outperforms other PSR methods.

Autor:innen und Institutionen

  • Department of Aerospace Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu 600036, India.
  • Potsdam Institute for Climate Impact Research, Member of the Leibniz Association, 14473 Potsdam, Germany.
  • School of Engineering & Design, Technical University of Munich, 80333 Munich, Germany.
  • Institute of Physics and Astronomy, University of Potsdam, 14476 Potsdam, Germany.

ORCID-Profile: Jayesh M Dhadphale, K Hauke Kraemer, Maximilian Gelbrecht, Jürgen Kurths, Norbert Marwan, R I Sujith

Förderung

  • Ministry of Education, India
  • Office of Global Engagement, IIT Madras
  • Volkswagen Foundation

Zitieren

APA

Dhadphale, J. M., Hauke Kraemer, K., Gelbrecht, M., Kurths, J., Marwan, N., & Sujith, R. I. (2024). Model adaptive phase space reconstruction. Chaos: An Interdisciplinary Journal of Nonlinear Science, 34(7). https://doi.org/10.1063/5.0194330

Vancouver

Dhadphale JM, Hauke Kraemer K, Gelbrecht M, Kurths J, Marwan N, Sujith RI. Model adaptive phase space reconstruction. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2024;34(7). doi:10.1063/5.0194330

BibTeX
@article{Dhadphale2024,
  author = {Dhadphale, Jayesh M and Hauke Kraemer, K and Gelbrecht, Maximilian and Kurths, Jürgen and Marwan, Norbert and Sujith, R I},
  title = {Model adaptive phase space reconstruction},
  journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
  year = {2024},
  volume = {34},
  number = {7},
  doi = {10.1063/5.0194330}
}
Kostenlos starten →