Thresholds for Ensamble of Small Models
This function evaluates the full model which is used for projections and provides thresholds to produce binary maps.
ecospat.ESM.threshold( ESM.EnsembleModeling.output,
PEplot = FALSE)ESM.EnsembleModeling.output |
a list object returned by |
PEplot |
logical. Should the predicted to expected ratio along the suitability class from the boyce index be plotted. Default FALSE (see |
This function provides evaluation scores of the full model (no split sampling) and thresholds which can be used to convert suitability maps into binary maps. Various thresholds are provided: TSS (where sensitivity and specificity are maximised), MPA 1.0 (where all presences are prdicted positive), MPA 0.95 (where 95% of all presences are predicted positive), MPA 0.90 (where 90% of all presences are predicted positive), Boyce.th.min (the lowest suitability value where the predicted/expected ratio is >1) and Boyce.th.max (the highest suitability value where the predicted/expected ratio is =1).
A data.frame with evluation scores and thresholds.
Frank Breiner frank.breiner@unil.ch
Hirzel, Alexandre H., et al. Evaluating the ability of habitat suitability models to predict species presences. Ecological modelling, 199.2 (2006): 142-152.
Engler, Robin, Antoine Guisan, and Luca Rechsteiner. An improved approach for predicting the distribution of rare and endangered species from occurrence and pseudo-absence data. Journal of applied ecology, 41.2 (2004): 263-274.
Fielding, Alan H., and John F. Bell. A review of methods for the assessment of prediction errors in conservation presence/absence models." Environmental conservation, 24.1 (1997): 38-49.
library(biomod2)
# Loading test data
data(ecospat.testNiche.inv)
inv <- ecospat.testNiche.inv
# species occurrences
xy <- inv[,1:2]
sp_occ <- inv[11]
# env
current <- inv[3:10]
### Formating the data with the BIOMOD_FormatingData() function from the package biomod2
sp <- 1
myBiomodData <- BIOMOD_FormatingData( resp.var = as.numeric(sp_occ[,sp]),
expl.var = current,
resp.xy = xy,
resp.name = colnames(sp_occ)[sp])
### Calibration of simple bivariate models
my.ESM <- ecospat.ESM.Modeling( data=myBiomodData,
models=c('GLM','CTA'),
NbRunEval=2,
DataSplit=70,
weighting.score=c('AUC'),
parallel=FALSE)
### Evaluation and average of simple bivariate models to ESMs
my.ESM_EF <- ecospat.ESM.EnsembleModeling(my.ESM,weighting.score=c('SomersD'),threshold=0)
output.TH <- ecospat.ESM.threshold(my.ESM_EF,PEplot = TRUE)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.