What is it about?

We develop a cheap approximation of the Bayesian Update. In contrast to the classical Bayesian Update we update not the probability densities, but PCE coefficients, approximated via polynomial chaos expansion.

Featured Image

Why is it important?

Very important for fast and efficient data assimilation. The developed method allows us to incorporate available measurements into existing model.


This is a non-linear extension of the famous Kalman filter.

Dr. Alexander Litvinenko
Rheinisch Westfalische Technische Hochschule Aachen

Read the Original

This page is a summary of: Sampling-free linear Bayesian update of polynomial chaos representations, Journal of Computational Physics, July 2012, Elsevier,
DOI: 10.1016/j.jcp.2012.04.044.
You can read the full text:



The following have contributed to this page