mra_wendland_2d_pred: Code to construct the mutli-resolution sparse basis function...

In jtipton25/BayesMRA: Bayesian Multi-Resolution Gaussian Process Approximations

Code to construct the mutli-resolution sparse basis function representation for fitting spatial processes

Description

Code to construct the mutli-resolution sparse basis function representation for fitting spatial processes

Usage

mra_wendland_2d_pred(
  locs_pred,
  MRA,
  max_points = NULL,
  basis_type = "wendland",
  use_spam = TRUE
)

Arguments

locs_pred	The location variables in 2 dimensions over which to construct the basis function representation in the prediction stage.
MRA	The multi-resolution basis expansion at the observed locations. This object is the output of ⁠mra_wendland-2d()⁠ and is of class "mra_wendland_2d".
max_points	The expected number of pairs less than or equal to the radius. Default is nrow(locs) * num_neighbors.
basis_type	A string of which basis function type to use. Currently available basis function types are at make_basis()
use_spam	is a boolean flag to determine whether the output is a list of spam matrix objects (use_spam = TRUE) or a an n \times n sparse Matrix of class "dgCMatrix" use_spam = FALSE (see spam and Matrix packages for details).

Value

A list of objects including the observation locations locs, the MRA knots locations locs_grid, the Wendland basis representation matrix W_pred at the prediction locations, the basis radius radius, the numbers of resolutions M, the basis function dimensions n_dims, the basis function resolution indices dims_idx, the number of expected neighbors in the interior of each grid n_neighbors, the number of interior basis functions in one direction n_coarse_grid, the number of additional padding basis functions given by n_padding, and the setting use_spam which determines whether the MRA output uses the spam format.

Examples

set.seed(111)
locs <- matrix(runif(20), 10, 2)
locs_pred <- matrix(runif(20), 10, 2)
MRA <- mra_wendland_2d(locs, M = 2, n_coarse_grid = 4)
MRA_pred <- mra_wendland_2d_pred(locs_pred, MRA)

## plot the MRA prediction grid at different resolutions
plot_MRA_grid(MRA_pred)

jtipton25/BayesMRA documentation built on Feb. 28, 2024, 1:27 p.m.