This function allows to use a raster as data to make predictions from a
variety of tidymodels objects, such as simple_ensemble or
stacks::stacks
predict_raster(object, raster, ...)# S3 method for default
predict_raster(object, raster, filename = "", n = 4, ...)
a terra::SpatRaster (or stars if that is the input) with the
predictions
the tidymodels object of interest
the terra::SpatRaster or stars with the input data. It
has to include levels with the same names as the variables used in object
parameters to be passed to the standard predict() function for
the appropriate object type (e.g. metric_thresh, class_thresh or
fun). See the documentation of the relevant predict() method for
possible parameters (e.g. predict.simple_ensemble()).
the name of the output file raster file; this is only needed to save large rasters, and can be left blank for rasters that can be kept in memory.
positive integer indicating how many copies the data may be in
memory at any point in time (it defaults to 4). This is used to determine
whether rasters can be processed in one go, or in chunks. If you get an out
of memory error, increase n. See terra::writeStart() for more details.