Prognosis of qualitative behavior from time series: advantages and limitations of deterministic modeling
Abstract
An approach to prognosis of behavior of an unknown dynamical system (DS) from weakly nonstationary chaotic time series (TS) containing significant measurement noise is proposed. The approach is based on construction of a global time-dependent parameterized model of discrete evolution operator which is able to reproduce nonstationary dynamics of reconstructed DS. The universal model in the form of artificial neural network (ANN) with certain prior limitations is suggested. Probabilistic prognosis of the system behavior is performed using Monte-Carlo Markov Chain (MCMC) analysis of the posterior Bayesian distribution of the model parameters. The ability of the approach to provide prognosis for times greater than observation time interval is demonstrated. Some restrictions as well as possible advances of the proposed approach are discussed.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2010
- Bibcode:
- 2010AGUFMNG43H1464F
- Keywords:
-
- 3270 MATHEMATICAL GEOPHYSICS / Time series analysis;
- 4425 NONLINEAR GEOPHYSICS / Critical phenomena