This function samples background points from a raster given a set of presences. The locations returned as the center points of the sampled cells, which can overlap with the presences (in contrast to pseudo-absences, see sample_pseudoabs). The following methods are implemented:
'random': background randomly sampled from the region covered by the raster (i.e. not NAs).
'dist_max': background randomly sampled from the unioned buffers of 'dist_max' from presences (distances in 'm' for lonlat rasters, and in map units for projected rasters). Using the union of buffers means that areas that are in multiple buffers are not oversampled. This is also referred to as "thickening".
'bias': background points are sampled according to a surface representing the biased sampling effort.
sample_background(
data,
raster,
n,
coords = NULL,
method = "random",
class_label = "background",
return_pres = TRUE
)
An object of class tibble::tibble. If presences are returned, the
presence level is set as the reference (to match the expectations in the
yardstick
package that considers the first level to be the event).
An sf::sf
data frame, or a data frame with coordinate
variables. These can be defined in coords
, unless they have standard
names (see details below).
the terra::SpatRaster or stars
from which cells will be
sampled (the first layer will be used to determine which cells are NAs, and
thus can not be sampled). If sampling is "bias", then the sampling
probability will be proportional to the values on the first layer (i.e.
band) of the raster.
number of background points to sample.
a vector of length two giving the names of the "x" and "y"
coordinates, as found in data
. If left to NULL, the function will try to
guess the columns based on standard names c("x", "y")
, c("X","Y")
,
c("longitude", "latitude")
, or c("lon", "lat")
.
sampling method. One of 'random', 'dist_max', and 'bias'. For dist_max, the maximum distance is set as an additional element of a vector, e.g c('dist_max',70000).
the label given to the sampled points. Defaults to
background
return presences together with background in a single tibble.
Note that the units of distance depend on the projection of the raster.