evaluate {SSDM}

Evaluate

Description

Evaluation of SDM or ESDM habitat suitability predictions or evalaution of SSDM floristic composition with Pottier et al, 2013 method (see reference below)

Usage

evaluate(obj, ...)

## S4 method for signature 'Algorithm.SDM'
evaluate(
  obj,
  cv,
  cv.param,
  final.fit.data = "all",
  bin.thresh = "SES",
  metric = NULL,
  thresh = 1001,
  Env,
  ...
)

## S4 method for signature 'MAXENT.SDM'
evaluate(
  obj,
  cv,
  cv.param,
  final.fit.data = "all",
  bin.thresh = "SES",
  metric = NULL,
  thresh = 1001,
  Env,
  ...
)

## S4 method for signature 'Stacked.SDM'
evaluate(obj, ...)

Arguments

obj

Stacked.SDM. SSDM to evaluate

...

arguments for internal use (get_model), such as argument lists to be passed to the source functions (e.g. glm.args=list(test="AIC",singular.ok=FALSE))

cv

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

cv.param

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

final.fit.data

strategy used for fitting the final model to be returned: '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 (including related scores such as TPR, TNR, omission rate, Kappa, etc.).

metric

(deprecated) character. Classification threshold (SDMTools::optim.thresh) used to binarize model predictions into presence/absence and compute the confusion matrix (including related scores such as TPR, TNR, omission rate, Kappa, etc.).

thresh

(deprecated) integer. Number of equally spaced thresholds in the interval 0-1 (SDMTools::optim.thresh).

Env

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

Value

SDM/ESDM/SSDM evaluation in a data.frame

References

Pottier, J., Dubuis, A., Pellissier, L., Maiorano, L., Rossier, L., Randin, C. F., Guisan, A. (2013). The .accuracy of plant assemblage prediction from species distribution models varies along environmental gradients. Global Ecology and Biogeography, 22(1), 52-63. https://doi.org/10.1111/j.1466-8238.2012.00790.x

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')

# Evaluation
evaluate(SSDM)


## End(Not run)