rstLGCPP: Simulate a spatio-temporal Log-Gaussian Cox process (LGCP)

In SepTest: Tests for First-Order Separability in Spatio-Temporal Point Processes

Simulate a spatio-temporal Log-Gaussian Cox process (LGCP)

Description

Generates a realization of a spatio-temporal LGCP over a user-defined domain. The process is simulated using a log-Gaussian random field combined with a deterministic trend function, and points are generated by thinning a homogeneous Poisson process.

Usage

rstLGCPP(
  xlim = NULL,
  ylim = NULL,
  tlim = NULL,
  grid = c(15, 15, 10),
  mu = NULL,
  Lambda = NULL,
  Lmax = NULL,
  par1 = c(1, 0.05),
  par2 = c(1, 0.06),
  sigmas = c(0.5, 0.5, 1),
  mu_par = c(1.2, 0.25, 5)
)

Arguments

xlim, ylim, tlim	Numeric vectors of length 2 specifying the spatial and temporal domains.
grid	Integer vector of length 3 specifying the number of grid cells in x, y, and t.
mu	Optional. A function of (x, y, t, par) defining a deterministic trend. Default is nonlinear.
Lambda	Optional. A user-supplied 3D intensity array or function. If NULL, it's generated from the latent Gaussian field.
Lmax	Optional. Maximum intensity used for thinning. Can be numeric or a function. If NULL, it's computed automatically.
par1, par2	Parameters for temporal and spatial exponential covariance models, respectively.
sigmas	Weights for combining spatial, temporal, and spatio-temporal components of the latent Gaussian field.
mu_par	Parameters passed to the default trend function mu() if not user-supplied.

Value

A list with:

st.lgcp

A data frame of simulated spatio-temporal points.

RF

The latent Gaussian field output from Gauss.st.F.

Examples

out <- rstLGCPP(xlim = c(0,1),
                ylim = c(0,1),
                tlim = c(0,1),
                grid = c(15,15,10))
plot_stlgcp(data = out)
plot_stpp(data = out$st.lgcp, type = "3D")

SepTest documentation built on Feb. 3, 2026, 5:07 p.m.