maskRangeR (version 1.1)

rangeSVM_predict: Generate a raster based on predictions of SVM model with values corresponding to the species.

Description

rangeSVM_predict() returns a raster representing the ranges of the species predicted by the fitted SVM tuned with rangeSVM().

Usage

rangeSVM_predict(svm, r, sdm = NULL)

Arguments

svm

Model object for the SVM, returned by rangeSVM().

r

Raster with the extent desired for the prediction. The values for cells used for predictions must have non-NA values, but the particular values do not matter.

sdm

Raster or RasterStack representing environmental suitability (can be predictions from SDMs). These rasters must match the predictor variables used in the SVM. Default is NULL.

Value

The Raster representing the SVM predictions.

Details

The values of the output raster are 1, 2, ..., corresponding to xy1, xy2, and any additional species used in rangeSVM(). These values represent the identities of the species.

Examples

# NOT RUN {
r1.sdm <- raster::raster(raster::extent(c(-72, -64, 41, 50)), res = c(0.008333333, 0.008333333))
raster::values(r1.sdm) <- (1:raster::ncell(r1.sdm))^2
r2.sdm <- raster::raster(raster::extent(c(-72, -64, 41, 50)), res = c(0.008333333, 0.008333333))
raster::values(r2.sdm) <- (raster::ncell(r2.sdm):1)^2
r3.sdm <- raster::raster(raster::extent(c(-72, -64, 41, 50)), res = c(0.008333333, 0.008333333))
r3.sdm [1] <- 10
r3.sdm <- raster::distance(r3.sdm)
sp1.xy <- data.frame(dismo::randomPoints(r1.sdm, 15, prob = TRUE))
colnames(sp1.xy) <- c("longitude", "latitude")
sp2.xy <- data.frame(dismo::randomPoints(r2.sdm, 15, prob = TRUE))
colnames(sp2.xy) <- c("longitude", "latitude")
sp3.xy <- data.frame(dismo::randomPoints(r3.sdm, 15, prob = TRUE))
colnames(sp3.xy) <- c("longitude", "latitude")
# Spatial SVMs (this can take about a minute to run)
svm.SP <- rangeSVM(sp1.xy, sp2.xy, sp3.xy, nrep=5)
# Use SVM to create a raster of predicted regions
rand_svm.SP <- rangeSVM_predict(svm = svm.SP, r = r1.sdm)
# }