stack_modelling {SSDM}

Build an SSDM that assembles multiple algorithms and species.

Description

This is a function to build an SSDM that assembles multiple algorithm and species. The function takes as inputs an occurrence data frame made of presence/absence or presence-only records and a raster object for data extraction and projection. The function returns an S4 Stacked.SDM class object containing the local species richness map, the between-algorithm variance map, and all evaluation tables coming with (model evaluation, algorithm evaluation, algorithm correlation matrix and variable importance), and a list of ensemble SDMs for each species (see ensemble_modelling).

Usage

stack_modelling(
  algorithms,
  Occurrences,
  Env,
  Xcol = "Longitude",
  Ycol = "Latitude",
  Pcol = NULL,
  Spcol = "SpeciesID",
  rep = 10,
  name = NULL,
  save = FALSE,
  path = getwd(),
  PA = NULL,
  cv = "holdout",
  cv.param = c(0.7, 1),
  final.fit.data = "all",
  bin.thresh = "SES",
  metric = NULL,
  thresh = 1001,
  axes.metric = "Pearson",
  uncertainty = TRUE,
  tmp = FALSE,
  SDM.projections = FALSE,
  ensemble.metric = c("AUC"),
  ensemble.thresh = c(0.75),
  weight = TRUE,
  method = "pSSDM",
  rep.B = 1000,
  range = NULL,
  endemism = c("WEI", "Binary"),
  verbose = TRUE,
  GUI = FALSE,
  cores = 0,
  parmode = "species",
  ...
)

Arguments

algorithms

character. Choice of the algorithm(s) to be run (see details below).

Occurrences

data frame. Occurrence table (can be processed first by load_occ).

Env

raster object. Raster object of environmental variables (can be processed first by load_var).

Xcol

character. Name of the column in the occurrence table containing Latitude or X coordinates.

Ycol

character. Name of the column in the occurrence table containing Longitude or Y coordinates.

Pcol

character. Name of the column in the occurrence table specifying whether a line is a presence or an absence. A value of 1 is presence and value of 0 is absence. If NULL presence-only dataset is assumed.

Spcol

character. Name of the column containing species names or IDs.

rep

integer. Number of repetitions for each algorithm.

name

character. Optional name given to the final Ensemble.SDM produced.

save

logical. If set to true, the SSDM is automatically saved.

path

character. If save is true, the path to the directory in which the ensemble SDM will be saved.

PA

list(nb, strat) defining the pseudo-absence selection strategy used in case of presence-only dataset. If PA is NULL, recommended PA selection strategy is used depending on the algorithm (see details below).

cv

character. Method of cross-validation used to evaluate the ensemble SDM (see details below).

cv.param

numeric. Parameters associated with the method of cross-validation used to evaluate the ensemble SDM (see details below).

final.fit.data

strategy used for fitting the final/evaluated Algorithm.SDMs: 'holdout'= use same train and test data as in (last) evaluation, 'all'= train model with all data (i.e. no test data) or numeric (0-1)= sample a custom training fraction (left out fraction is set aside as test data)

bin.thresh

character. Classification threshold (threshold) used to binarize model predictions into presence/absence and compute the confusion matrix (see details below).

metric

(deprecated) character. Classification threshold (SDMTools::optim.thresh) used to binarize model predictions into presence/absence and compute the confusion matrix (see details below). This argument is only kept for backwards compatibility, if possible please use bin.thresh instead.

thresh

(deprecated) integer. Number of equally spaced thresholds in the interval 0-1 (SDMTools::optim.thresh). Only needed when metric is set.

axes.metric

Metric used to evaluate variable relative importance (see details below).

uncertainty

logical. If set to true, generates an uncertainty map and an algorithm correlation matrix.

tmp

logical. If set to true, the habitat suitability map of each algorithms is saved in a temporary file to release memory. But beware: if you close R, temporary files will be deleted. To avoid any loss you can save your SSDM with save.model. Depending on number, resolution and extent of models, temporary files can take a lot of disk space. Temporary files are written in R environment temporary folder.

SDM.projections

logical. If FALSE (default), the Algorithm.SDMs inside the 'sdms' slot will not contain projections (for memory saving purposes).

ensemble.metric

character. Metric(s) used to select the best SDMs that will be included in the ensemble SDM (see details below).

ensemble.thresh

numeric. Threshold(s) associated with the metric(s) used to compute the selection.

weight

logical. Choose whether or not you want the SDMs to be weighted using the selection metric or, alternatively, the mean of the selection metrics.

method

character. Define the method used to create the local species richness map (see details below).

rep.B

integer. If the method used to create the local species richness is the random bernoulli (Bernoulli), rep.B parameter defines the number of repetitions used to create binary maps for each species.

range

integer. Set a value of range restriction (in pixels) around presences occurrences on habitat suitability maps (all further points will have a null probability, see Crisp et al (2011) in references). If NULL, no range restriction will be applied.

endemism

character. Define the method used to create an endemism map (see details below).

verbose

logical. If set to true, allows the function to print text in the console.

GUI

logical. Don't take that argument into account (parameter for the user interface).

cores

integer. Specify the number of CPU cores used to do the computing. You can use detectCores) to automatically use all the available CPU cores.

parmode

character. Parallelization mode: along 'species', 'algorithms' or 'replicates'. Defaults to 'species'.

...

additional parameters for the algorithm modelling function (see details below).

Details

algorithms

'all' allows you to call directly all available algorithms. Currently, available algorithms include Generalized linear model (GLM), Generalized additive model (GAM), Multivariate adaptive regression splines (MARS), Generalized boosted regressions model (GBM), Classification tree analysis (CTA), Random forest (RF), Maximum entropy (MAXENT), Artificial neural network (ANN), and Support vector machines (SVM). Each algorithm has its own parameters settable with the ... (see each algorithm section below to set their parameters).

"PA"

list with two values: nb number of pseudo-absences selected, and strat strategy used to select pseudo-absences: either random selection or disk selection. We set default recommendation from Barbet-Massin et al. (2012) (see reference).

cv

Cross-validation method used to split the occurrence dataset used for evaluation: holdout data are partitioned into a training set and an evaluation set using a fraction (cv.param[1]) and the operation can be repeated (cv.param[2]) times, k-fold data are partitioned into k (cv.param[1]) folds being k-1 times in the training set and once the evaluation set and the operation can be repeated (cv.param[2]) times, LOO (Leave One Out) each point is successively taken as evaluation data.

metric

Choice of the metric used to compute the binary map threshold and the confusion matrix (by default SES as recommended by Liu et al. (2005), see reference below): Kappa maximizes the Kappa, CCR maximizes the proportion of correctly predicted observations, TSS (True Skill Statistic) maximizes the sum of sensitivity and specificity, SES uses the sensitivity-specificity equality, LW uses the lowest occurrence prediction probability, ROC minimizes the distance between the ROC plot (receiving operating curve) and the upper left corner (1,1).

axes.metric

Choice of the metric used to evaluate the variable relative importance (difference between a full model and one with each variable successively omitted): Pearson (computes a simple Pearson's correlation r between predictions of the full model and the one without a variable, and returns the score 1-r: the highest the value, the more influence the variable has on the model), AUC, Kappa, sensitivity, specificity, and prop.correct (proportion of correctly predicted occurrences).

ensemble.metric

Ensemble metric(s) used to select SDMs: AUC, Kappa, sensitivity, specificity, and prop.correct (proportion of correctly predicted occurrences).

method

Choice of the method used to compute the local species richness map (see Calabrese et al. (2014) and D'Amen et al (2015) for more informations, see reference below): pSSDM sum probabilities of habitat suitability maps, Bernoulli drawing repeatedly from a Bernoulli distribution, bSSDM sum the binary map obtained with the thresholding (depending on the metric, see metric parameter), MaximumLikelihood adjust species richness using maximum likelihood parameter estimates on the logit-transformed occurrence probabilities (see Calabrese et al. (2014)), PRR.MEM model richness with a macroecological model (MEM) and adjust each ESDM binary map by ranking habitat suitability and keeping as much as predicted richness of the MEM, PRR.pSSDM model richness with a pSSDM and adjust each ESDM binary map by ranking habitat suitability and keeping as much as predicted richness of the pSSDM

endemism

Choice of the method used to compute the endemism map (see Crisp et al. (2001) for more information, see reference below): NULL No endemism map, WEI (Weighted Endemism Index) Endemism map built by counting all species in each cell and weighting each by the inverse of its range, CWEI (Corrected Weighted Endemism Index) Endemism map built by dividing the weighted endemism index by the total count of species in the cell. First string of the character is the method either WEI or CWEI, and in those cases second string of the vector is used to precise range calculation, whether the total number of occurrences 'NbOcc' whether the surface of the binary map species distribution 'Binary'.

...

See algorithm in detail section

Value

an S4 Stacked.SDM class object viewable with the plot.model function.

Generalized linear model (GLM)

Uses the glm function from the package 'stats'. You can set parameters by supplying glm.args=list(arg1=val1,arg2=val2) (see glm for all settable arguments). The following parameters have defaults:

test

character. Test used to evaluate the SDM, default 'AIC'.

control

list (created with glm.control). Contains parameters for controlling the fitting process. Default is glm.control(epsilon = 1e-08, maxit = 500). 'epsilon' is a numeric and defines the positive convergence tolerance (eps). 'maxit' is an integer giving the maximal number of IWLS (Iterative Weighted Last Squares) iterations.

Generalized additive model (GAM)

Uses the gam function from the package 'mgcv'. You can set parameters by supplying gam.args=list(arg1=val1,arg2=val2) (see gam for all settable arguments). The following parameters have defaults:

test

character. Test used to evaluate the model, default 'AIC'.

control

list (created with gam.control). Contains parameters for controlling the fitting process. Default is gam.control(epsilon = 1e-08, maxit = 500). 'epsilon' is a numeric used for judging the conversion of the GLM IRLS (Iteratively Reweighted Least Squares) loop. 'maxit' is an integer giving the maximum number of IRLS iterations to perform.

Multivariate adaptive regression splines (MARS)

Uses the earth function from the package 'earth'. You can set parameters by supplying mars.args=list(arg1=val1,arg2=val2) (see earth for all settable arguments). The following parameters have defaults:

degree

integer. Maximum degree of interaction (Friedman's mi) ; 1 meaning build an additive model (i.e., no interaction terms). By default, set to 2.

Generalized boosted regressions model (GBM)

Uses the gbm function from the package 'gbm'. You can set parameters by supplying gbm.args=list(arg1=val1,arg2=val2) (see gbm for all settable arguments). The following parameters have defaults:

distribution

character. Automatically detected from the format of the presence column in the occurrence dataset.

n.trees

integer. The total number of trees to fit. This is equivalent to the number of iterations and the number of basis functions in the additive expansion. By default, set to 2500.

n.minobsinnode

integer. minimum number of observations in the trees terminal nodes. Note that this is the actual number of observations, not the total weight. By default, set to 1.

cv.folds

integer. Number of cross-validation folds to perform. If cv.folds>1 then gbm - in addition to the usual fit - will perform a cross-validation. By default, set to 3.

shrinkage

numeric. A shrinkage parameter applied to each tree in the expansion (also known as learning rate or step-size reduction). By default, set to 0.001.

bag.fraction

numeric. Fraction of the training set observations randomly selected to propose the next tree in the expansion.

train.fraction

numeric. Training fraction used to fit the first gbm. The remainder is used to compute out-of-sample estimates of the loss function. By default, set to 1 (since evaluation/holdout is done with SSDM::evaluate.

n.cores

integer. Number of cores to use for parallel computation of the CV folds. By default, set to 1. If you intend to use this, please set ncores=0 to avoid conflicts.

Classification tree analysis (CTA)

Uses the rpart function from the package 'rpart'. You can set parameters by supplying cta.args=list(arg1=val1,arg2=val2) (see rpart for all settable arguments). The following parameters have defaults:

control

list (created with rpart.control). Contains parameters for controlling the rpart fit. The default is rpart.control(minbucket=1, xval=3). 'mibucket' is an integer giving the minimum number of observations in any terminal node. 'xval' is an integer defining the number of cross-validations.

Random Forest (RF)

Uses the randomForest function from the package 'randomForest'. You can set parameters by supplying cta.args=list(arg1=val1,arg2=val2) (see randomForest all settable arguments). The following parameters have defaults:

ntree

integer. Number of trees to grow. This should not be set to a too small number, to ensure that every input row gets predicted at least a few times. By default, set to 2500.

nodesize

integer. Minimum size of terminal nodes. Setting this number larger causes smaller trees to be grown (and thus take less time). By default, set to 1.

Maximum Entropy (MAXENT)

Uses the maxent function from the package 'dismo'. Make sure that you have correctly installed the maxent.jar file in the folder ~\R\library\version\dismo\java available at https://biodiversityinformatics.amnh.org/open_source/maxent/. As with the other algorithms, you can set parameters by supplying maxent.args=list(arg1=val1,arg2=val2). Mind that arguments are passed from dismo to the MAXENT software again as an argument list (see maxent for more details). No specific defaults are set with this method.

Artificial Neural Network (ANN)

Uses the nnet function from the package 'nnet'. You can set parameters by supplying ann.args=list(arg1=val1,arg2=val2) (see nnet for all settable arguments). The following parameters have defaults:

size

integer. Number of units in the hidden layer. By default, set to 6.

maxit

integer. Maximum number of iterations, default 500.

Support vector machines (SVM)

Uses the svm function from the package 'e1071'. You can set parameters by supplying svm.args=list(arg1=val1,arg2=val2) (see svm for all settable arguments). The following parameters have defaults:

type

character. Regression/classification type SVM should be used with. By default, set to "eps-regression".

epsilon

float. Epsilon parameter in the insensitive loss function, default 1e-08.

cross

integer. If an integer value k>0 is specified, a k-fold cross-validation on the training data is performed to assess the quality of the model: the accuracy rate for classification and the Mean Squared Error for regression. By default, set to 3.

kernel

character. The kernel used in training and predicting. By default, set to "radial".

gamma

numeric. Parameter needed for all kernels, default 1/(length(data) -1).

Warning

Depending on the raster object resolution the process can be more or less time and memory consuming.

References

M. D'Amen, A. Dubuis, R. F. Fernandes, J. Pottier, L. Pelissier, & A Guisan (2015) "Using species richness and functional traits prediction to constrain assemblage predicitions from stacked species distribution models" Journal of Biogeography 42(7):1255-1266 http://doc.rero.ch/record/235561/files/pel_usr.pdf

M. Barbet-Massin, F. Jiguet, C. H. Albert, & W. Thuiller (2012) "Selecting pseudo-absences for species distribution models: how, where and how many?" Methods Ecology and Evolution 3:327-338 http://onlinelibrary.wiley.com/doi/10.1111/j.2041-210X.2011.00172.x/full

J.M. Calabrese, G. Certain, C. Kraan, & C.F. Dormann (2014) "Stacking species distribution models and adjusting bias by linking them to macroecological models." Global Ecology and Biogeography 23:99-112 https://onlinelibrary.wiley.com/doi/full/10.1111/geb.12102

M. D. Crisp, S. Laffan, H. P. Linder & A. Monro (2001) "Endemism in the Australian flora" Journal of Biogeography 28:183-198 http://biology-assets.anu.edu.au/hosted_sites/Crisp/pdfs/Crisp2001_endemism.pdf

C. Liu, P. M. Berry, T. P. Dawson, R. & G. Pearson (2005) "Selecting thresholds of occurrence in the prediction of species distributions." Ecography 28:85-393 http://www.researchgate.net/publication/230246974_Selecting_Thresholds_of_Occurrence_in_the_Prediction_of_Species_Distributions

See Also

modelling to build simple SDMs.

Examples

## Not run: 
# Loading data
data(Env)
data(Occurrences)

# SSDM building
SSDM <- stack_modelling(c('CTA', 'SVM'), Occurrences, Env, rep = 1,
                       Xcol = 'LONGITUDE', Ycol = 'LATITUDE',
                       Spcol = 'SPECIES')

# Results plotting
plot(SSDM)

## End(Not run)