popSize: Predict population density across the range of raster layers

In Xinhai-Li/abundanceR: Estimate wildlife abundance based on distance sampling and species distribution models

Predict population density across the range of raster layers

Description

Predict number of individuals at each cell using Random Forest, based on environmental variables

Usage

popSize(ENV = BioClim, model = RF)

Arguments

ENV	A RasterBrick (a multi-layer raster object)
RF	A list object of the model results of Random Forest

Value

A raster layer with number of individuals at each cell

Author(s)

Xinhai Li ([e-mail])

Examples

pred = popSize(BioClim, RF)
plot(pred)
plot(log(1+log(1+pred)), xlab="Longitude", ylab="Latitude", main='',
    col=colorRampPalette(c("grey90", "green", "yellow", "red"))(12)) #topo.colors(20)
lines(shape)
library(calibrate)
attach(loc)
loc1 = loc[loc$Class==1,]
loc2 = loc[loc$Class==2,]
loc3 = loc[loc$Class==3,]
textxy(loc1$lon, loc1$lat, loc1$Name, cex=0.8);textxy(loc2$lon, loc2$lat, loc2$Name, cex=0.6);textxy(loc3$lon, loc3$lat, loc3$Name, cex=0.4);points(loc1$lon, loc1$lat, pch=16, cex=1, col='brown')
points(species$Lon, species$Lat, pch=16, cex=species$Count/20, col=adjustcolor("darkgreen", 0.5))

Xinhai-Li/abundanceR documentation built on Feb. 1, 2024, 4:47 a.m.