Nonlinear prediction of chaotic time series

https://doi.org/10.1016/0167-2789(89)90074-2Get rights and content

Abstract

Numerical techniques are presented for constructing nonlinear predictive models directly from time series data. The accuracy of the short-term predictions is tested using computer-generated time series, and comparisons are made of the effectiveness of the various techniques. Scaling laws are developed which describe the data requirements for reliable predictions. It is also shown how to use the models to convincingly distinguish low-dimensional chaos from randomness, and to make statistical long-term predictions.

References (40)

  • D.S. Broomhead et al.

    Extracting qualitative dynamics from experimental data

    Physica D

    (1987)
  • D.S. Broomhead et al.

    A finite dimensional description of turbulent flows

    (1987)
  • J.G. Caputo, PhD thesis,...
  • J. Cremers et al.

    Construction of differential equations from experimental data

    Z. Naturforsch. A

    (1987)
  • J.P. Crutchfield et al.

    Equations of motion from a data series

    Complex Systems

    (1987)
  • J. Duchon

    Spline minimising rotation-invariant seminorms in Sobolev spaces

  • N. Dyn et al.

    Numerical procedures for surface spline fitting of scattered data by radial basis functions

    SIAM J. Sci. Stat. Comput.

    (1986)
  • J.P. Eckmann et al.

    Lyapunov exponents from a time series

    Phys. Rev. A

    (1986)
  • J.P. Eckmann et al.

    Ergodic theory of chaos and strange attractors

    Rev. Mod. Phys.

    (1985)
  • J.D. Farmer

    Chaotic attractors of an infinite dimensional system

    Physica D

    (1982)
  • Cited by (0)

    Present address: Center for Nonlinear Studies, Los Alamos National Laboratory, Los Alamos, NM 87545, USA.

    View full text