Skip to contents

This function adds a presence-only biodiversity dataset to a distribution object.

Usage

add_biodiversity_poipo(
  x,
  poipo,
  name = NULL,
  field_occurrence = "observed",
  formula = NULL,
  family = "poisson",
  link = NULL,
  weight = 1,
  separate_intercept = TRUE,
  docheck = TRUE,
  pseudoabsence_settings = NULL,
  ...
)

# S4 method for BiodiversityDistribution,sf
add_biodiversity_poipo(
  x,
  poipo,
  name = NULL,
  field_occurrence = "observed",
  formula = NULL,
  family = "poisson",
  link = NULL,
  weight = 1,
  separate_intercept = TRUE,
  docheck = TRUE,
  pseudoabsence_settings = NULL,
  ...
)

Arguments

x

distribution() (i.e. BiodiversityDistribution) object.

poipo

A data.frame or sf object of presence-only point occurrences.

name

The name of the biodiversity dataset used as internal identifier.

field_occurrence

A numeric or character location of biodiversity point records.

formula

A character or formula object to be passed. Default is to use all covariates (if specified).

family

A character stating the family to be used (Default: 'Poisson').

link

A character to overwrite the default link function (Default: codeNULL).

weight

A numeric value acting as a multiplier with regards to any weights used in the modelling. Larger weights indicate higher weighting relative to any other datasets. By default set to 1 if only one dataset is added. A vector is also supported but must be of the same length as "poipo". Note: Weights are reformated to the inverse for models with area offsets (e.g. 5 is converted to 1/5).

separate_intercept

A logical value stating whether a separate intercept is to be added in shared likelihood models for engines engine_inla, engine_inlabru and engine_stan. Otherwise ignored.

docheck

logical on whether additional checks should be performed (e.g. intersection tests) (Default: TRUE).

pseudoabsence_settings

Either NULL or a pseudoabs_settings() created settings object.

...

Other parameters passed down to the object. Normally not used unless described in details.

Value

Adds biodiversity data to distribution object.

Details

This function allows to add presence-only biodiversity records to a distribution ibis.iSDM Presence-only data are usually modelled through an inferential model (see Guisan and Zimmerman, 2000) that relate their occurrence in relation to environmental covariates to a selected sample of 'background' points. The most common approach for estimation and the one supported by this type of dataset are poisson-process models (PPM) in which presence-only points are fitted through a down-weighted Poisson regression. See Renner et al. 2015 for an overview.

References

  • Guisan A. and Zimmerman N. 2000. Predictive habitat distribution models in ecology. Ecol. Model. 135: 147–186.

  • Renner, I. W., J. Elith, A. Baddeley, W. Fithian, T. Hastie, S. J. Phillips, G. Popovic, and D. I. Warton. 2015. Point process models for presence-only analysis. Methods in Ecology and Evolution 6:366–379.

See also

Examples

# Load background
background <- terra::rast(system.file('extdata/europegrid_50km.tif',
package='ibis.iSDM',mustWork = TRUE))
# Load virtual species
virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg',
package='ibis.iSDM',mustWork = TRUE),'points',quiet = TRUE)
# Define model
x <- distribution(background) |>
add_biodiversity_poipo(virtual_points, field_occurrence = "Observed")
#> [Setup] 2024-02-06 14:38:47.752742 | Creating distribution object...
#> [Setup] 2024-02-06 14:38:47.753684 | Adding poipo dataset...