calib_mdl: Calibrate MaxEnt models based on model selection criteria

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

Calibrate MaxEnt models based on model selection criteria

Description

This function will read an object of class ENMevaluation (See ?ENMeval::ENMevaluate for details) and calibrate the selected maxent models.

Usage

calib_mdl(
  ENMeval.o,
  sp.nm = "species",
  a.calib,
  occ = NULL,
  use.ENMeval.bgpts = TRUE,
  nbg = 10000,
  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	Object of class ENMevaluation
sp.nm	Species name. Used to name the output folder
a.calib	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	Occurrence data. Argument 'p' of dismo::maxent. This can be a data.frame, matrix, SpatialPoints* object, or a vector. If p is a data.frame or matrix it represents a set of point locations; and it must have two columns with the first being the x-coordinate (longitude) and the second the y-coordinate (latitude). Coordinates can also be specified with a SpatialPoints* object If x is a data.frame, p should be a vector with a length equal to nrow(x) and contain 0 (background) and 1 (presence) values, to indicate which records (rows) in data.frame x are presence records, and which are background records
use.ENMeval.bgpts	Logical. Use background points from ENMeval or sample new ones?
nbg	Number of background points to use. These are sampled randomly from the cells that are not NA in the first predictor variable. Ignored if background points are specified with argument a
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' (calib.mdls, Maxent Calibrated Models). A list containing the models ('selected.mdls') used for model calibration, calibrated maxent models ('mxnt.mdls'), and arguments used for calibration ('pred.args').

See Also

mod_sel, calib_mdl_b, ENMevaluate_b, ENMevaluate, maxent, proj_mdl, proj_mdl_b

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