simulBrownResnick {mvPot}

Simulation of Brown–Resnick random vectors

Description

simulBrownResnick provides n replicates of a Brown–Resnick max-stable process with semi-variogram vario at locations loc.

Usage

simulBrownResnick(n, loc, vario, nCores = 1, cl = NULL)

Arguments

n

Number of replicates desired.

loc

Matrix of coordinates as given by expand.grid().

vario

Semi-variogram function.

nCores

Number of cores needed for the computation

cl

Cluster instance as created by makeCluster of the parallel package. Make sure the random number generator has been properly initialized with clusterSetRNGStream().

Details

The algorithm used here is based on the spectral representation of the Brown–Resnick model as described in Dombry et al. (2015). It provides n exact simulations on the unit Frechet scale and requires, in average, for each max-stable vector, the simulation of d Pareto processes, where d is the number of locations.

Value

List of n random vectors drawn from a max-stable Brown–Resnick process with semi-variogram vario at location loc.

References

Dombry, C., Engelke, S. and M. Oesting. Exact simulation of max-stable processes. Biometrika, 103(2), 303-317.

Examples

#Define semi-variogram function
vario <- function(h){
   1 / 2 * norm(h,type = "2")^1.5
}

#Define locations
loc <- expand.grid(1:4, 1:4)

#Simulate data
obs <- simulBrownResnick(10, loc, vario)