Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications
Online ISSN : 2188-4749
Print ISSN : 2188-4730
The 47th ISCIE International Symposium on Stochastic Systems Theory and Its Applications (Dec. 2015, Honolulu)
Fast and stable estimation of macroscopic parameters in particle systems by data assimilation
Kazuyuki NakamuraYutaka Kono
Author information
JOURNALS FREE ACCESS

2016 Volume 2016 Pages 132-136

Details
Abstract

In this paper we show a data assimilation framework which gives good estimation of the macroscopic parameter in particle systems. To give the fast and stable estimation, we employed the bounded Gaussian uniform mixture (BGUM) type dynamics that is originally introduced in the econophysics field. The result of the numerical experiment implies that BGUM type dynamics enable us to obtain appropriate estimation of macroscopic parameters from macroscopic observations faster than random walk type dynamics that is usually employed. It is also implied that mixing rate between Gaussian and uniform distribution can control the trade-off between fast detection and stability of macroscopic parameters. Those results suggest that the utility of the introduced framework for macroscopic parameter estimation in particle systems.

Information related to the author
© 2016 ISCIE Symposium on Stochastic Systems Theory and Its Applications
Previous article Next article
feedback
Top