Â鶹ӰԺ

William Kleiber, Department of Applied Mathematics, Â鶹ӰԺÌý

Simulation of High-Resolution Random Fields

Ìý

Simulation of spatial random fields is an essential goal in most geostatistical analyses. This talk will focus on two approaches to generating high resolution simulations of nonstationary Gaussian random fields.Ìý The first relies on spatial deformation of a stationary solution that can then be generated using extant approaches such as circulant embedding.Ìý The second generates approximate realizations for an arbitrary given covariance function.Ìý The procedure rests on sequential conditional simulations based on topologically connected regions in the domain.Ìý We suggest initializing this consecutive conditioning approach with an initial coarse resolution simulation over the domain to reduce bias of correlations at long distances.Ìý We provide a theoretical justification for the local prediction step.Ìý Both approaches are illustrated on climatological datasets.