11/03/2013: Statistical Methods of Interpolation, Lina Kulakova


Statistical Methods of Interpolation


March 11, 2013, 12:00, IFW D 42, ETH Zurich

Lina Kulakova
 
Abstract
Interpolation is widely used in science and engineering, when only a limited number of data points, obtained by experimentation, is available.  In my talk I will consider two interpolation methods: kriging and sequential Gaussian simulation, which we used to obtain the initial maps of porosity, permeability etc. in reservoir simulation problem. Both methods consider the data to be a random field trajectory and take into account stochastic properties of the random field. Kriging is known as the best linear unbiased estimator while sequential Gaussian simulation allows to generate multiple equiprobable realizations of the property. The talk includes general description of these methods and some implementation details.