bm_RunModelsLoop: Loop to compute all single species distribution models

In biomodhub/biomod2: Ensemble Platform for Species Distribution Modeling

Loop to compute all single species distribution models

Description

This internal biomod2 function allows the user to compute all single species distribution models (asked by the BIOMOD_Modeling function).

Usage

bm_RunModelsLoop(
  bm.format,
  modeling.id,
  models,
  models.pa,
  calib.lines,
  bm.options,
  metric.eval,
  var.import,
  weights,
  scale.models = FALSE,
  nb.cpu = 1,
  seed.val = NULL,
  do.progress = TRUE
)

bm_RunModel(
  model,
  run.name,
  dir.name = ".",
  modeling.id = "",
  Data,
  bm.options,
  calib.lines.vec,
  eval.data = NULL,
  metric.eval = c("AUCroc", "TSS", "KAPPA"),
  var.import = 0,
  weights.vec,
  scale.models = FALSE,
  nb.cpu = 1,
  seed.val = NULL,
  do.progress = TRUE
)

Arguments

bm.format	a BIOMOD.formated.data or BIOMOD.formated.data.PA object returned by the BIOMOD_FormatingData function
modeling.id	a character corresponding to the name (ID) of the simulation set (a random number by default)
models	a vector containing model names to be computed, must be among ANN, CTA, DNN, FDA, GAM, GBM, GLM, MARS, MAXENT, MAXNET, RF, RFd, SRE, XGBOOST
models.pa	(optional, default NULL) A list containing for each model a vector defining which pseudo-absence datasets are to be used, must be among colnames([e-mail])
calib.lines	a matrix containing calibration / validation lines for each pseudo-absence (or allData) x repetition (or allRun) combination that can be obtained with the bm_CrossValidation function
bm.options	a BIOMOD.models.options object returned by the bm_ModelingOptions function
metric.eval	a vector containing evaluation metric names to be used, must be among AUCroc, AUCprg, TSS, KAPPA, ACCURACY, BIAS, POD, FAR, POFD, SR, CSI, ETS, OR, ORSS, BOYCE, MPA (binary data), RMSE, MAE, MSE, Rsquared, Rsquared_aj, Max_error (abundance / count / relative data), Accuracy, Recall, Precision, F1 (multiclass/ordinal data)
var.import	(optional, default NULL) An integer corresponding to the number of permutations to be done for each variable to estimate variable importance
weights	a matrix containing observation weights for each pseudo-absence (or allData) dataset
scale.models	(optional, default FALSE) A logical value defining whether all models predictions should be scaled with a binomial GLM or not
nb.cpu	(optional, default 1) An integer value corresponding to the number of computing resources to be used to parallelize the single models computation
seed.val	(optional, default NULL) An integer value corresponding to the new seed value to be set
do.progress	(optional, default TRUE) A logical value defining whether the progress bar is to be rendered or not
model	a character corresponding to the model name to be computed, must be either ANN, CTA, DNN, FDA, GAM, GBM, GLM, MARS, MAXENT, MAXNET, RF, SRE, XGBOOST
run.name	a character corresponding to the model to be run (sp.name + pa.id + run.id)
dir.name	(optional, default .) A character corresponding to the modeling folder
Data	a data.frame containing observations, coordinates and environmental variables that can be obtained with the get_species_data function
calib.lines.vec	a vector containing calibration / validation lines for the concerned pseudo-absence (or allData) x repetition (or allRun) combination
eval.data	(optional, default NULL) A data.frame containing validation observations, coordinates and environmental variables that can be obtained with the get_eval_data function
weights.vec	a vector containing observation weights the concerned pseudo-absence (or allData) dataset

Value

A list containing for each model a list containing the following elements :

• model : the name of correctly computed model

• calib.failure : the name of incorrectly computed model

• pred : the prediction outputs for calibration data

• pred.eval : the prediction outputs for evaluation data

• evaluation : the evaluation outputs returned by the bm_FindOptimStat function

• var.import : the mean of variables importance returned by the bm_VariablesImportance function

Author(s)

Damien Georges

See Also

rpart, prune, gbm, nnet, earth, fda, mars, maxnet, randomForest, xgboost, bm_ModelingOptions, BIOMOD_Modeling, bm_MakeFormula, bm_SampleFactorLevels, bm_FindOptimStat, bm_VariablesImportance

Other Secondary functions: bm_BinaryTransformation(), bm_CrossValidation(), bm_FindOptimStat(), bm_MakeFormula(), bm_ModelingOptions(), bm_PlotEvalBoxplot(), bm_PlotEvalMean(), bm_PlotRangeSize(), bm_PlotResponseCurves(), bm_PlotVarImpBoxplot(), bm_PseudoAbsences(), bm_RangeSize(), bm_SRE(), bm_SampleBinaryVector(), bm_SampleFactorLevels(), bm_Tuning(), bm_VariablesImportance()

biomodhub/biomod2 documentation built on July 4, 2025, 6:15 p.m.