DONATE

IAHR Document Library


« Back to Library Homepage « Proceedings of the 30th IAHR World Congress (Thessaloniki, 2...

Prediction of Nonlinear Dynamical Systems Based on Time Series Analysis: Issues of Entropy, Complexity and Predictability

Author(s): S. Velickov; R. K. Price; D. P. Solomatine

Linked Author(s):

Keywords: Nonlinear dynamics; Time series analysis; Entropy; And Predictability

Abstract: The structure of nonlinear dynamics based on time series as a sequence of strings carrying information is investigated by means of entropy concepts. Firstly, average block (ngram) entropy, local conditional entropy (uncertainty) and predictability, mutual information and complexity are introduced and several possible generalisations are discussed. The capability to describe the structure of surge dynamics at Hoek van Holland as ordered sequence of strings in the reconstructed phase-space is further investigated. The relation between local order, entropy and the predictability is demonstrated and discussed.

DOI:

Year: 2003

Copyright © 2024 International Association for Hydro-Environment Engineering and Research. All rights reserved. | Terms and Conditions