ISSN:
1573-8868
Keywords:
Gaussian random fields
;
geostatistics
;
Monte Carlo simulations
;
orthogonal polynomials
Source:
Springer Online Journal Archives 1860-2000
Topics:
Geosciences
,
Mathematics
Notes:
Abstract Consider the problem of generating a realization y1 of a Gaussian random field on a dense grid of points Ω1 conditioned on field observations y2 collected on a sparse grid of points Ω2. An approach to this is to generate first an unconditional realization y over the grid Ω=Ω1 ∪ Ω2, and then to produce y1 by conditioning y on the data y2. As standard methods for generating y, such as the turning bands, spectral or Cholesky approaches can have various limitations, it has been proposed by M. W. Davis to generate realizations from a matrix polynomial approximations to the square root of the covariance matrix. In this paper we describe how to generate a direct approximation to the conditional realization y1, on Ω1 using a variant of Davis' approach based on approximation by Chebyshev polynomials. The resulting algorithm is simple to implement, numerically stable, and bounds on the approximation error are readily available. Furthermore we show that the conditional realization y1 can be generated directly with a lower order polynomial than the unconditional realization y, and that further reductions can be achieved by exploiting a nugget effect if one is present. A pseudocode version of the algorithm is provided that can be implemented using the fast Fourier transform if the field is stationary and the grid Ω1 is rectangular. Finally, numerical illustrations are given of the algorithm's performance in generating various 2-D realizations of conditional processes on large sampling grids.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1007/BF02083211
Permalink