simspde {RGeostats}R Documentation

Perform Simulations using SPDE technology


Perform Simulations using SPDE technology


simspde(dbin = NA, dbout, model = NA, pattern = NA, triswitch = "nqQ",
        nostat = NA, seed = 232131, nbsimu = 1, numparts=NA, ngiter=10,
        nburn = 50,niter = 100,
        gext = NA, flag.gibbs = FALSE, flag.grid = TRUE,
        flag.modif = FALSE, verbose = FALSE,
        radix = "SPDE", = db.locmod())



The db-class structure containing the input 2-D data. This file is optional: when absent, we perform non-conditional simulations; when present, we perform conditional simulations. When used, there must be a single variable defined.


The db-class structure which contains the resulting simulations.


The model-class describing the spatial characteristics.


When 'dbout' is organized as regular grid, the simulation may take place starting from the definition of a pattern.


Command line for the internal triangulation step. For more information see meshing.


List of non-stationary parameters. For details see model.param.define.


Seed for the random number generation.


Number of simulations.


Array for subdividing the field into parts. Its dimension must be equal to the space dimension. If not defined (or equal to 1 in each space direction), the space is not subdivided. Subdividing in parts reduces the dimension of the matrices and can be used in the case of large files (input or output). In order to reduce the artifacts that may be induced by the subdivision, two steps of subdivisions are actually processed. For illustration purpose, let us assume that the field (SX by SY) with origin (X0,Y0) is subdivided into NX ny NY parts.

  • Step 1: The field is subdivided into NX by NY parts, with dimensions equal to SX/NX and SY/NY

  • Step 2: The field (with origin X0-SX/2, Y0-SY/2) is subdivided into NX+1 by NY+1 parts, with dimensions equal to SX/NX and SY/NY.


When the field is subdivided into several parts, several iterations are necessary to glue the parts. This parameter defined the number of iterations to be processed.


Number of burning iterations when the iterative Gibbs method is used as a simulation procedure. During these burning simulations, the intervals are gradually restrained from almost no constraint down to the final constraints.


Number of iterations when the iterative Gibbs method is used as a simulation procedure.


When 'dbout' is organized as a grid, it may be dilated by gext. This argument designates an array, with its dimension equal to the dimension of the space and which contains the extension defined in number of grid nodes.


When TRUE, the iterative Gibbs method is used.


When FALSE, the simulation is performed after a triangulations step. This is NOT the default solution when performing non-conditional simulation(s) on a 'dbout' organized as a grid.


When TRUE, the simulation outcomes are not stored individually. Instead the simulations outcomes are summarized in two output variables, i.e. the mean and standard deviation of dispersion of the simulations.


Verbose option


Radix of the name given to the variables storing the results in the target Db.

Decides whether or not the newly created variables will have their locator defined or not. For more information, see db.locmod.


The output db-class where the following variables have been added:

The Double Quilting can be switched OFF by using the function set.keypair() with the keyword "Flag_Double_Quilt". By default, its value is set to 1.

The keypair mechanism has also been used to transmit the some values calculated internally to the user with the keywords:

[Package RGeostats version 11.0.6 Index]