mopa (version 1.0.1)

OCSVMprofiling: Environmental profiling with One-Classification Support Vector Machine

Description

Presence-only modeling and classification of coordinates predicted as presence and absence

Usage

OCSVMprofiling(xy, varstack, background = NULL, nu = 0.5)

Arguments

xy

Data frame or list of data frames with coordinates (each row is a point)

varstack

RasterStack of variables for modeling

background

Object derived from function backgroundGrid. If NULL (default), the background is extracted from varstack. Matrix or list of matrixes of the background xy coordinates in columns.

nu

Parameter needed for one-classification svm. Default is 0.5

Value

A list with two components:

absence

Matrix or list of matrixes with xy coordinates predicted as absence

presence

Matrix or list of matrixes with xy coordinates predicted as presence

Details

This function constitutes the first step from a three-step proccess to generate pseudo-absences, and is aimed at excluding the suitable areas for the species (xy records) from the background from which pseudo-absences are sampled.

References

Iturbide, M., Bedia, J., Herrera, S., del Hierro, O., Pinto, M., Gutierrez, J.M., 2015. A framework for species distribution modelling with improved pseudo-absence generation. Ecological Modelling. DOI:10.1016/j.ecolmodel.2015.05.018.

See Also

svm, backgroundGrid

Examples

# NOT RUN {
## Load presence data
data(Oak_phylo2)

## Load climate data
destfile <- tempfile()
data.url <- "https://raw.githubusercontent.com/SantanderMetGroup/mopa/master/data/biostack.rda"
download.file(data.url, destfile)
load(destfile, verbose = TRUE)

## Spatial reference
projection(biostack$baseline) <- CRS("+proj=longlat +init=epsg:4326")
r <- biostack$baseline[[1]]
## Background of the whole study area
bg <- backgroundGrid(r)

## Environmental profiling
bg.profiled <- OCSVMprofiling(xy = Oak_phylo2, varstack = biostack$baseline, 
                              background = bg$xy)
## Plot
plot(bg.profiled$absence$H11, pch="*")
points(bg.profiled$presence$H11, pch="*", col= "pink")

# }