kuenm_rpca: Principal componens for raster layers and projections

In manubio13/ku.enm: Detailed development of ecological niche models using Maxent

Principal componens for raster layers and projections

Description

kuenm_rpca performs a principal component analysis with a set of variables and produces raster layers of them. If needed the pricipal components are projected to other scenarios.

Usage

kuenm_rpca(variables, in.format, var.scale = TRUE, write.result = TRUE,
           out.format = "GTiff", out.dir = "PCA_results", project = FALSE,
           proj.vars, n.pcs)

Arguments

variables	(character or RasterStack) if character, name of the folder where raster layers are located. If RasterStack, stack of raster layers to be used in principal component analyses.
in.format	(character) valid only if variables is character. Format of variables in the directory. Options are "ascii", "GTiff", and "EHdr" = bil.
var.scale	(logical) wheter or not to scale variables before performing principal component analyses. Default = TRUE.
write.result	(logical) whether or not to write PCA results and raster layers (PCs) in out.dir.
out.format	(character) if write.result = TRUE, format of variables to be written in distinct sets inside out.dir. Options are "ascii", "GTiff", and "EHdr" = bil. Default = "GTiff".
out.dir	(character) valid if write.result = TRUE. Name of the folder to be created to save the results of the analyses. Default = "PCA_results".
project	(logical) whether or not to project the species niche to other scenario(s). If TRUE, argument proj.variables needs to be defined. Default = FALSE.
proj.vars	(character or RasterStack) if character, name of the folder where subfolders with environmental variables of scenarios for projections are (useful if multiple projections are needed). If RasterStack, object containing stacked variables of only one projection scenario. Variables must correspond with variables in vars.folder (i.e., their names must correspond but they should represent conditions in other scenario).
n.pcs	(numeric) number of principal components to be returned as rasters. By default all principal components are returned as RasterLayers.

Details

If var.scale = TRUE, variables are centered to cero and scaled using scale.

Value

A list containing PCA loadings and PCA summary as matrices, as well as one or multiple (if projected) RasterStacks of principal components.

If write.result = TRUE, all results are written in out.dir.

Examples

# Data
variab <- raster::stack(list.files(system.file("extdata", package = "kuenm"),
                                   pattern = "Mbio_", full.names = TRUE))
names(variab) <- paste0("bio_", c(1, 12, 15, 17))

proj_var <- raster::stack(list.files(system.file("extdata", package = "kuenm"),
                                     pattern = "Gbio_", full.names = TRUE))
names(proj_var) <- paste0("bio_", c(1, 12, 15, 17))

# Example with no projection
npcs <- 3

rpca <- kuenm_rpca(variables = variab, var.scale = TRUE, write.result = FALSE,
                   n.pcs = npcs)

# Example with projection
project <- TRUE

rpca1 <- kuenm_rpca(variables = variab, var.scale = TRUE, write.result = FALSE,
                    project = project, proj.vars = proj_var, n.pcs = npcs)

manubio13/ku.enm documentation built on Jan. 5, 2024, 5:55 a.m.