ecospat.ESM.Modeling {ecospat}

Ensemble of Small Models: Calibration of Simple Bivariate Models

Description

This function calibrates simple bivariate models as in Lomba et al. 2010 and Breiner et al. 2015.

Usage

    ecospat.ESM.Modeling( data, 
                          NbRunEval, 
                          DataSplit, 
                          DataSplitTable, 
                          Prevalence,
                          weighting.score, 
                          models, 
                          tune,
                          modeling.id, 
                          models.options, 
                          which.biva, 
                          parallel, 
                          cleanup,
                          Yweights)

Arguments

data

BIOMOD.formated.data object returned by BIOMOD_FormatingData

NbRunEval

number of dataset splitting replicates for the model evaluation (same as in biomod2)

DataSplit

percentage of dataset observations retained for the model training (same as in biomod2)

DataSplitTable

a matrix or data.frame filled with TRUE/FALSE to specify which part of data must be used for models calibration (TRUE) and for models validation (FALSE). Each column corresponds to a 'RUN'. For a presence-absence dataset, column names must be formatted as: _allData_RUNx with x an integer. For a presence-only dataset, column names must be formatted as: _PA1_RUNx with x an integer. If filled, arguments NbRunEval and DataSplit will be ignored.

Prevalence

either NULL or a 0-1 numeric used to build 'weighted response weights'. In contrast to Biomod the default is 0.5 (weighting presences equally to the absences). If NULL each observation (presence or absence) has the same weight (independent of the number of presences and absences).

weighting.score

evaluation score used to weight single models to build ensembles: 'AUC', 'SomersD' (2xAUC-1), 'Kappa', 'TSS' or 'Boyce'

models

vector of models names choosen among 'GLM', 'GBM', 'GAM', 'CTA', 'ANN', 'SRE', 'FDA', 'MARS', 'RF','MAXENT', 'MAXNET' (same as in biomod2)

tune

logical. if true model tuning will be used to estimate optimal parameters for the models (Default: False).

modeling.id

character, the ID (=name) of modeling procedure. A random number by default.

models.options

BIOMOD.models.options object returned by BIOMOD_ModelingOptions (same as in biomod2)

Yweights

response points weights. This argument will only affect models that allow case weights.

which.biva

integer. which bivariate combinations should be used for modeling? Default: all

parallel

logical. If TRUE, the parallel computing is enabled (highly recommended)

cleanup

No more available. Please use terra::TmpFiles instead

Details

The basic idea of ensemble of small models (ESMs) is to model a species distribution based on small, simple models, for example all possible bivariate models (i.e. models that contain only two predictors at a time out of a larger set of predictors), and then combine all possible bivariate models into an ensemble (Lomba et al. 2010; Breiner et al. 2015).

The ESM set of functions could be used to build ESMs using simple bivariate models which are averaged using weights based on model performances (e.g. AUC) according to Breiner et al. (2015). They provide full functionality of the approach described in Breiner et al. (2015).

The argument which.biva allows to split model runs, e.g. if which.biva is 1:3, only the three first bivariate variable combinations will be modeled. This allows to run different biva splits on different computers. However, it is better not to use this option if all models are run on a single computer. Default: running all biva models. NOTE: Make sure to give each of your biva runs a unique modeling.id. Please avoid space characters in your working directory path if you are using MAXENT because this can cause an error.

Value

A BIOMOD.models.out object (same as in biomod2) See "BIOMOD.models.out" for details.

Author(s)

Frank Breiner [e-mail] and Mirko Di Febbraro [e-mail] with contributions of Olivier Broennimann [e-mail] and Flavien Collart

References

Lomba, A., L. Pellissier, C.F. Randin, J. Vicente, F. Moreira, J. Honrado and A. Guisan. 2010. Overcoming the rare species modelling paradox: A novel hierarchical framework applied to an Iberian endemic plant. Biological Conservation, 143,2647-2657.

Breiner F.T., A. Guisan, A. Bergamini and M.P. Nobis. 2015. Overcoming limitations of modelling rare species by using ensembles of small models. Methods in Ecology and Evolution, 6,1210-1218.

Breiner F.T., Nobis M.P., Bergamini A., Guisan A. 2018. Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution. doi:10.1111/2041-210X.12957

See Also

ecospat.ESM.Projection, ecospat.ESM.EnsembleModeling, ecospat.ESM.EnsembleProjection, ecospat.ESM.EnsembleEvaluation, ecospat.ESM.threshold,ecospat.ESM.VarContrib, ecospat.ESM.responsePlot

BIOMOD_FormatingData, BIOMOD_ModelingOptions, BIOMOD_Modeling,BIOMOD_Projection

Examples

   
library(biomod2)

# Loading test data
data(ecospat.testNiche.inv)
inv <- ecospat.testNiche.inv

# species occurrences
xy <- inv[,1:2]
sp_occ <- inv[11]

# env data
current <- inv[3:8]

### Formating the data with the BIOMOD_FormatingData() function from the package biomod2
sp <- 1
myBiomodData <- biomod2::BIOMOD_FormatingData( resp.var = as.numeric(sp_occ[,sp]),
                                      expl.var = current,
                                      resp.xy = xy,
                                      resp.name = colnames(sp_occ)[sp])

### Calibration of simple bivariate models
my.ESM <- ecospat.ESM.Modeling( data=myBiomodData,
                                models=c('GLM'),
                                NbRunEval=2,
                                DataSplit=70,
                                weighting.score=c("AUC"),
                                parallel=FALSE)  

### Ensemble models
my.ESM_EF <- ecospat.ESM.EnsembleModeling(my.ESM,weighting.score=c("SomersD"),threshold=0)

### thresholds to produce binary maps
my.ESM_thresholds <- ecospat.ESM.threshold(my.ESM_EF)

### Evaluation of bivariate and ensemble models based on standard cross-validation
my.ESM_EF$ESM.evaluations
my.ESM_thresholds

### Evaluation of the ensemble models based on the pooling procedure 
my.ESM_evaluations <- ecospat.ESM.EnsembleEvaluation(ESM.modeling.output= my.ESM,
                                                     ESM.EnsembleModeling.output = my.ESM_EF,
                                                     metrics= c("AUC","MaxTSS"),
                                                     EachSmallModels = FALSE)
my.ESM_evaluations$ESM.evaluations

### Projection of simple bivariate models into new space 
my.ESM_proj_current<-ecospat.ESM.Projection(ESM.modeling.output=my.ESM,
                                            new.env=current)
### Projection of calibrated ESMs into new space 
my.ESM_EFproj_current <- ecospat.ESM.EnsembleProjection(ESM.prediction.output=my.ESM_proj_current,
                                                        ESM.EnsembleModeling.output=my.ESM_EF)
### Binary Projection based on max TSS of calibrated ESMs into new space                                                
my.ESM_EFproj_current_binary <- (my.ESM_EFproj_current > (my.ESM_thresholds$TSS.th*1000))*1

## get the variable contributions of ESMs
ecospat.ESM.VarContrib(my.ESM,my.ESM_EF)                                                      

## get the response plots of ESMs
my.ESM_responsePlot<-ecospat.ESM.responsePlot(my.ESM_EF,my.ESM,fixed.var.metric = 'mean')