Learn R Programming

biomod2 (version 4.2-5)

bm_PlotResponseCurves: Plot response curves

Description

This function represents response curves of species distribution models, from BIOMOD.models.out or BIOMOD.ensemble.models.out objects that can be obtained from BIOMOD_Modeling or BIOMOD_EnsembleModeling functions. Response curves can be represented in either 2 or 3 dimensions (meaning 1 or 2 explanatory variables at a time, see Details).

Usage

bm_PlotResponseCurves(
  bm.out,
  models.chosen = "all",
  new.env = get_formal_data(bm.out, "expl.var"),
  show.variables = get_formal_data(bm.out, "expl.var.names"),
  fixed.var = "mean",
  do.bivariate = FALSE,
  do.plot = TRUE,
  do.progress = TRUE,
  ...
)

Value

A list containing a data.frame with variables and predicted values and the corresponding ggplot object representing response curves.

Arguments

bm.out

a BIOMOD.models.out or BIOMOD.ensemble.models.out object that can be obtained with the BIOMOD_Modeling or BIOMOD_EnsembleModeling functions

models.chosen

a vector containing model names to be kept, must be either all or a sub-selection of model names that can be obtained with the get_built_models function

new.env

a matrix, data.frame or SpatRaster object containing the new explanatory variables (in columns or layers, with names matching the variables names given to the BIOMOD_FormatingData function to build bm.out) that will be used to project the species distribution model(s)
Note that old format from raster are still supported such as RasterStack objects.

show.variables

a vector containing the names of the explanatory variables present into new.env parameter and to be plotted

fixed.var

a character corresponding to the statistic to be used to fix as constant the remaining variables other than the one used to predict response, must be either mean, median, min, max

do.bivariate

(optional, default FALSE)
A logical value defining whether the response curves are to be represented in 3 dimensions (meaning 2 explanatory variables at a time) or not (meaning only 1)

do.plot

(optional, default TRUE)
A logical value defining whether the plot is to be rendered or not

do.progress

(optional, default TRUE)
A logical value defining whether the progress bar is to be rendered or not

...

some additional arguments (see Details)

Author

Damien Georges, Maya Gueguen

Details

This function is an adaptation of the Evaluation Strip method proposed by Elith et al. (2005). To build the predicted response curves :

  • n-1 variables are set constant to a fixed value determined by the fixed.var parameter (in the case of categorical variable, the most represented class is taken)

  • the remaining variable is made to vary throughout its range given by the new.env parameter

  • predicted values are computed with these n-1 fixed variables, and this studied variable varying

If do.bivariate = TRUE, 2 variables are varying at the same time.

The response curves obtained show the sensibility of the model to the studied variable.
Note that this method does not account for interactions between variables.

... can take the following values :

  • main : a character corresponding to the graphic title

References

  • Elith, J., Ferrier, S., Huettmann, FALSE. and Leathwick, J. R. 2005. The evaluation strip: A new and robust method for plotting predicted responses from species distribution models. Ecological Modelling, 186, 280-289.

See Also

BIOMOD.models.out, BIOMOD.ensemble.models.out, BIOMOD_Modeling, BIOMOD_EnsembleModeling

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

Other Plot functions: bm_PlotEvalBoxplot(), bm_PlotEvalMean(), bm_PlotRangeSize(), bm_PlotVarImpBoxplot()

Examples

Run this code
library(terra)

# Load species occurrences (6 species available)
data(DataSpecies)
head(DataSpecies)

# Select the name of the studied species
myRespName <- 'GuloGulo'

# Get corresponding presence/absence data
myResp <- as.numeric(DataSpecies[, myRespName])

# Get corresponding XY coordinates
myRespXY <- DataSpecies[, c('X_WGS84', 'Y_WGS84')]

# Load environmental variables extracted from BIOCLIM (bio_3, bio_4, bio_7, bio_11 & bio_12)
data(bioclim_current)
myExpl <- terra::rast(bioclim_current)

# \dontshow{
myExtent <- terra::ext(0,30,45,70)
myExpl <- terra::crop(myExpl, myExtent)
# }

# ---------------------------------------------------------------#
file.out <- paste0(myRespName, "/", myRespName, ".AllModels.models.out")
if (file.exists(file.out)) {
  myBiomodModelOut <- get(load(file.out))
} else {

  # Format Data with true absences
  myBiomodData <- BIOMOD_FormatingData(resp.var = myResp,
                                       expl.var = myExpl,
                                       resp.xy = myRespXY,
                                       resp.name = myRespName)

  # Model single models
  myBiomodModelOut <- BIOMOD_Modeling(bm.format = myBiomodData,
                                      modeling.id = 'AllModels',
                                      models = c('RF', 'GLM'),
                                      CV.strategy = 'random',
                                      CV.nb.rep = 2,
                                      CV.perc = 0.8,
                                      OPT.strategy = 'bigboss',
                                      metric.eval = c('TSS','ROC'),
                                      var.import = 3,
                                      seed.val = 42)
}


# ---------------------------------------------------------------#
# Represent response curves
mods <- get_built_models(myBiomodModelOut, run = 'RUN1')
bm_PlotResponseCurves(bm.out = myBiomodModelOut, 
                      models.chosen = mods,
                      fixed.var = 'median')
## fixed.var can also be set to 'min', 'max' or 'mean'
# bm_PlotResponseCurves(bm.out = myBiomodModelOut, 
#                       models.chosen = mods,
#                       fixed.var = 'min')

# Bivariate case (one model)
# variables can be selected with argument 'show.variables'
# models can be selected with argument 'models.chosen'
mods <- get_built_models(myBiomodModelOut, full.name = 'GuloGulo_allData_RUN2_RF')
bm_PlotResponseCurves(bm.out = myBiomodModelOut, 
                      show.variables = c("bio4","bio12","bio11"),
                      models.chosen = mods,
                      fixed.var = 'median',
                      do.bivariate = TRUE)
                                      
                                      

Run the code above in your browser using DataLab