Transform predictions from species distribution models to binary

Use model-specific threshold values to transform predicted probabilities of species presence, such as resulting from fit_SDM(), to binary predictions of presence or absence.

Usage

transform_SDM(
  pathin,
  SDM,
  landscape_name,
  modlist,
  stat,
  pathout,
  overwrite = FALSE
)

Arguments

pathin, SDM, landscape_name

Character strings defining the filepath (pathin/SDM/landscape_name) containing the predicted probability of presence resulting from each distribution model, such as those created from running fit_SDM(); SDM must be one of "riparian", "waterbird_fall", or "waterbird_win".

modlist

List of model objects of class 'gbm' representing the distribution models to which new predictors should be fit.

stat

Character string defining the threshold statistic to be used; see dismo::threshold() for options

pathout

Filepath for the directory where results rasters should be written (pathout/SDM/landscape_name)

overwrite

Logical; passed to terra::writeRaster()

Value

Nothing returned to R environment. Writes rasters to pathout/SDM/landscape_name for each model in modlist

See also

fit_SDM()

Examples

# See vignette