Non-Gaussian random fields

TransformedField: pointwise transforms of standard Gaussian fields simulated by CholeskySim with the model rescaled to unit sill (independent field k uses seed seed + 7919 k): log-normal, chi-square, Student t (Worsley 1994), gamma anamorphosis, binary, truncated pluri-Gaussian categories (Matheron et al. 1987), Poisson counts and Cox intensities of a log-Gaussian field, white noise and mixtures. MaxStableField: Schlather (2002) extremal Gaussian field. AnisotropicCoords: gstat-style geometric anisotropy transform. Identical to the Python arm morie.fn.rfields.

Usage

TransformedField(
  coords,
  model,
  kind,
  seed = 1,
  nsim = 1,
  mean = 0,
  sd = 1,
  df = 3,
  threshold = 0,
  proportions = NULL,
  shape = 2,
  rate = 1,
  scale = 1,
  weights = NULL,
  models = NULL
)

MaxStableField(coords, model, n_fields = 200, seed = 1)

AnisotropicCoords(coords, angle, ratio)

Arguments

coords

Two-column coordinates.

model

Covariance model (list or list of nested structures).

kind

Transform (see Python documentation).

seed

Philox seed.

nsim

Number of realisations.

mean, sd

Location and scale of the Gaussian predictor.

df

Degrees of freedom.

threshold

Binary threshold.

proportions

Category proportions.

shape, rate

Gamma parameters.

scale

Poisson/Cox intensity scale.

weights, models

Mixture weights and component models.

n_fields

Number of Gaussian fields in the max-stable series.

angle

Major-axis direction (degrees clockwise from north).

ratio

Minor/major range ratio.

Value

List (field) or matrix.

References

Schlather, M. (2002). Models for stationary max-stable random fields. Extremes 5, 33-44.

Worsley, K. J. (1994). Local maxima and the expected Euler characteristic of excursion sets of chi-squared, F and t fields. Advances in Applied Probability 26, 13-42.

Examples

m <- list(model = "Exp", psill = 1, range = 1)
TransformedField(rbind(c(0, 0), c(1, 0)), m, "binary", seed = 3)$field
#>      [,1] [,2]
#> [1,]    1    0
AnisotropicCoords(rbind(c(1, 0), c(0, 1)), 90, 0.5)
#>                           major
#> [1,]  1.224647e-16 1.000000e+00
#> [2,] -2.000000e+00 6.123234e-17