calib_mdl_b: Calibrate MaxEnt models based on model selection criteria for...

In HemingNM/ENMwizard: Advanced Techniques for Ecological Niche Modeling Made Easy

Calibrate MaxEnt models based on model selection criteria for several species

Description

This function will read a list of objects of class ENMevaluation (See ?ENMeval::ENMevaluate for details) and return selected maxent model calibrations and predictions. Each element on the list is usually a species. a.proj.l, a.calib.l, occ.l are lists with occurence data, projection and calibration/predictor data. Species in these lists must all be in the same order of species in ENMeval.o.

Usage

calib_mdl_b(
  ENMeval.o.l,
  a.calib.l,
  occ.l = NULL,
  use.ENMeval.bgpts = TRUE,
  format = "raster",
  pred.args = c("outputformat=cloglog", "doclamp=true", "pictures=true"),
  mSel = c("AvgAIC", "LowAIC", "OR", "AUC"),
  wAICsum = 0.99,
  dAICc = 2,
  AUCmin = 0.7,
  randomseed = FALSE,
  responsecurves = TRUE,
  arg1 = "noaddsamplestobackground",
  arg2 = "noautofeature",
  numCores = 1,
  parallelTunning = TRUE
)

Arguments

ENMeval.o.l	List of objects of class ENMevaluation
a.calib.l	List of predictors (cropped environmental variables) for model tuning. Used in model calibration. Argument 'x' of dismo::maxent. Raster* object or SpatialGridDataFrame, containing grids with predictor variables. These will be used to extract values from for the point locations. Can also be a data.frame, in which case each column should be a predictor variable and each row a presence or background record..
occ.l	List of occurence data. See argument "occ" in calib_mdl.
use.ENMeval.bgpts	Logical. Use background points from ENMeval or sample new ones?
format	Character. Output file type. Argument 'format' of raster::writeRaster
pred.args	Charater. Argument 'args' of dismo::maxent. Additional argument that can be passed to MaxEnt. See the MaxEnt help for more information. The R maxent function only uses the arguments relevant to model fitting. There is no point in using args='outputformat=raw' when *fitting* the model; but you can use arguments relevant for *prediction* when using the predict function. Some other arguments do not apply at all to the R implementation. An example is 'outputfiletype', because the 'predict' function has its own 'filename' argument for that.
mSel	Character vector. Which criteria to use when selecting model(s). Currently implemented: "AvgAIC", "LowAIC", "OR", "AUC"
wAICsum	Cumulative sum of top ranked models for which arguments will be created
dAICc	Maximum delta AICc of models to be selected.
AUCmin	Minimum AUC value to select models using EBPM criteria.
randomseed	logical. Args to be passed to dismo::maxent. See ?dismo::maxent and the MaxEnt help for more information.
responsecurves	logical. Args to be passed to dismo::maxent. See ?dismo::maxent and the MaxEnt help for more information.
arg1	charater. Args to be passed to dismo::maxent. See ?dismo::maxent and the MaxEnt help for more information.
arg2	charater. Args to be passed to dismo::maxent. See ?dismo::maxent and the MaxEnt help for more information.
numCores	Number of cores to use for parallelization. If set to 1, no paralellization is performed
parallelTunning	Should parallelize within species (parallelTunning=TRUE) or between species (parallelTunning=FALSE)

Value

A 'mcm.l' object. A list of 'mcm' (calib.mdls, Maxent Calibrated Models), returned from function "calib_mdl"

See Also

mod_sel, calib_mdl, ENMevaluate_b, ENMevaluate, maxent, proj_mdl, proj_mdl_b

Examples

## Not run: 
mxnt.mdls.preds.lst <- calib_mdl_b(ENMeval.o.l=ENMeval.res.lst,
a.calib.l=occ.b.env, a.proj.l=areas.projection, occ.l=occ, wAICsum=0.99)
mxnt.mdls.preds.lst[[1]][[1]] # models [ENMevaluate]d and selected using sum of wAIC
mxnt.mdls.preds.lst[[1]][[2]] # MaxEnt models
mxnt.mdls.preds.lst[[1]][[3]] # used prediction arguments
plot(mxnt.mdls.preds.lst[[1]][[4]]) # MaxEnt predictions, based on the model selection criteria

## End(Not run)

HemingNM/ENMwizard documentation built on Jan. 4, 2024, 3:24 p.m.