BIOMOD_EnsembleForecasting: Ensemble projections of species over space and time

Description

This function use projections of individual models and ensemble models from code{BIOMOD_EnsembleModeling} to build an ensemble of species' projections over space and time.

Usage

BIOMOD_EnsembleForecasting( projection.output,
                            EM.output,
                            total.consensus = FALSE,
                            binary.meth = NULL,
                            filtered.meth = NULL,
                            ...)

Arguments

projection.output

a "BIOMOD.projection.out" returned by BIOMOD_Projection

EM.output

a "BIOMOD.EnsembleModeling.out" returned by BIOMOD_EnsembleModeling

total.consensus

Logical. If TRUE, an optional projection averaging all ensemble-models projections will be built

binary.meth

vector specifying the names of evaluation metrics and associated thresholds to transform the probabilities of presence into presence and absence (binary transformation).

filtered.meth

vector specifying the names of evaluation metrics and associated thresholds to transform into 0 the probabilities of presence lower than the thresholds.

...

further arguments (see details)

Value

Nothing returned but specific projection files are saved on the hard drive projection folder. This files are either an array or a RasterStack depending the original projections data type. Load these created files to plot and work with them.

Details

This function requires to have successfully run biomod2 modeling, ensemble-modeling and projection steps. Ensemble projections will be created in respect to projection.output projections, which are combined following EM.output ensemble-modeling rules.

The total.consensus projection is basically the mean of all projections (for having only one output).

Examples

Run this code

# 0. Load data & Selecting Data

# species occurrences
species_occ <- read.csv(system.file("external/species/species_occ.csv",package="biomod2"))

# we consider only presences of MyocastorCoypus species
myRespName <- 'MyocastorCoypus'
myRespCoord <- species_occ[which(!is.na(species_occ[,myRespName])),c('x','y')]
myResp <- as.numeric(na.omit(species_occ[,myRespName]))

# Environmental variables extracted from BIOCLIM (bio_3, bio_4, bio_7, bio_11 & bio_12)
myExpl = raster::stack(system.file("external/climat/current/bio3.grd",package="biomod2"),
                       system.file("external/climat/current/bio4.grd",package="biomod2"),
                       system.file("external/climat/current/bio7.grd",package="biomod2"),
                       system.file("external/climat/current/bio11.grd",package="biomod2"),
                       system.file("external/climat/current/bio12.grd",package="biomod2"))

# 1. Formatting Data
myBiomodData <- BIOMOD_FormatingData(resp.var = myResp,
                                     expl.var = myExpl,
                                     resp.xy = myRespCoord,
                                     resp.name = myRespName,
                                     PA.nb.rep = 1,
                                     PA.nb.absences = 200,
                                     PA.strategy = 'random')
                                                                     
# 2. Defining Models Options using default options.
myBiomodOption <- BIOMOD_ModelingOptions()

# 3. Running the models 
myBiomodModelOut <- BIOMOD_Modeling( myBiomodData, 
                                       models = c('SRE','RF'), 
                                       models.options = myBiomodOption, 
                                       NbRunEval=2, 
                                       DataSplit=80, 
                                       Yweights=NULL, 
                                       VarImport=0, 
                                       models.eval.meth = c('TSS'),
                                       SaveObj = TRUE,
                                       rescal.all.models = FALSE,
                                       do.full.models = FALSE)
                                       
# 4. Creating the ensemble models 
myBiomodEM <- BIOMOD_EnsembleModeling( modeling.output = myBiomodModelOut,
                                       chosen.models = grep('_RF', getModelsBuiltModels(myBiomodModelOut), value=TRUE),
                                       em.by = 'algo',
                                       eval.metric = c('TSS'),
                                       eval.metric.quality.threshold = c(0.7),
                                       prob.mean = FALSE,
                                       prob.cv = FALSE,
                                       prob.ci = FALSE,
                                       prob.ci.alpha = 0.05,
                                       prob.median = FALSE,
                                       committee.averaging = FALSE,
                                       prob.mean.weight = TRUE,
                                       prob.mean.weight.decay = 'proportional' )
                                       
# 5. Individual models projections on current environmental conditions
myBiomodProjection <- BIOMOD_Projection(modeling.output = myBiomodModelOut,
                                        new.env = myExpl,
                                        proj.name = 'current',
                                        selected.models = grep('_RF', getModelsBuiltModels(myBiomodModelOut), value=TRUE),
                                        compress = 'NULL',
                                        build.clamping.mask = FALSE)
                                          

# 4. Creating the ensemble projections
BIOMOD_EnsembleForecasting( projection.output = myBiomodProjection,
                            EM.output = myBiomodEM)