View source: R/estimate_anisotropy.R
estimate_anisotropy | R Documentation |
Uses the coldpool::kriging_loocv() interface.
estimate_anisotropy(
x,
kriging_formula = variable_name ~ 1,
folds = 10,
variogram_model,
starting_values = NULL,
vgm_width = NULL,
nm = Inf,
seed = 19673
)
x |
A data.frame containing variables to be interpolated and latitude and longitude coordinates. |
kriging_formula |
Formula to use for kriging. Default (kriging_formula = variable_name ~ 1) is ordinary kriging without covariates. Formula for the gstat interface (see ?gstat::gstat). Covariate example: kriging_formula = variable_name ~ BOTTOM_DEPTH |
folds |
1L numeric vector indicating how many folds to use for cross-validation. |
variogram_model |
Character vector indicating which variogram model to use for interpolation. Valid options are exponential (exp), circular (cir), gaussian (gau), Bessel (bes), Matern (mat), or Stein's Matern (ste). |
starting_values |
Optional. Starting value of anisotropy parameters to use for optimization. See: ?gstat::vgm. |
vgm_width |
Optional. Width of variogram breaks. |
nm |
Maximum number of nearest neighbor observations to use for interpolation. |
seed |
RNG seed (set.seed(seed)) to use for anisotropy estimation based on cross-validation. |
variable_name |
1L character vector indicating which varible to interpolate (e.g. 'TEMPERATURE') |
latitude_name |
1L character vector indicating the name of the latitude column (e.g., 'LATITUDE') |
longitude_name |
1L character vector indicating the name of the longitude column (e.g., 'LONGITUDE') |
input_crs |
Character vector indicating the coordinate reference system for x (default = "WGS84") |
interpolation_crs |
Coordinate reference system to use for interpolation. |
only_return_anisotropy |
For internal use. Default = FALSE |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.