RandomFields (version 3.1.16)

RMmodelsSpacetime: Space-time Covariance Models

Description

Here, a collection of implemented space-time models is given.

Details

Stationary space-time models

Here, most of the models are composed models (operators). Note that in space-time modelling the argument proj may take also the values "space" for the projection on the space and "time" for the projection onto the time axis.

separable models

are easily constructed using +, *, and proj, see also the example below

RMave

space-time moving average model

RMcoxisham

Cox-Isham model

RMcurlfree

curlfree (spatial) field (stationary and anisotropic)

RMdivfree

divergence free (spatial) vector valued field, (stationary and anisotropic)

RMgennsst

generalization of Gneiting's non-separable space-time model

RMiaco

non-separabel space-time model

RMmastein

Ma-Stein model

RMnsst

Gneiting's non-separable space-time model

RMstein

Stein's non-separabel space-time model

RMstp

Single temporal process

References

• Schlather, M. (2011) Construction of covariance functions and unconditional simulation of random fields. In Porcu, E., Montero, J.M. and Schlather, M., Space-Time Processes and Challenges Related to Environmental Problems. New York: Springer.

See Also

RFformula, RM, RMmodels, RMmodelsAdvanced

Examples

RFoptions(seed=0) ## *ANY* simulation will have the random seed 0; set
##                   RFoptions(seed=NA) to make them all random again

## separable model with expontential model in space and gaussian in time
model <- RMexp(proj = "space") * RMgauss(proj = "time")
xT <- seq(0, 10, 0.1)
z <- RFsimulate(model, x=xT, T=xT)
plot(z)