Package 'ibis.iSDM'

Description

This function adds a presence-absence biodiversity dataset to a distribution object. Opposed to presence-only data, presence-absence biodiversity records usually originate from structured biodiversity surveys where the absence of a species in a given region was specifically assessed.

If it is the analysts choice it is also possible to format presence-only biodiversity data into a presence-absence form, by adding pseudo-absence through add_pseudoabsence. See the help file for more information.

Usage

add_biodiversity_poipa(
  x,
  poipa,
  name = NULL,
  field_occurrence = "observed",
  formula = NULL,
  family = "binomial",
  link = NULL,
  weight = 1,
  separate_intercept = TRUE,
  docheck = TRUE,
  ...
)

## S4 method for signature 'BiodiversityDistribution,sf'
add_biodiversity_poipa(
  x,
  poipa,
  name = NULL,
  field_occurrence = "observed",
  formula = NULL,
  family = "binomial",
  link = NULL,
  weight = 1,
  separate_intercept = TRUE,
  docheck = TRUE,
  ...
)

Arguments

Details

By default, the logit link function is used in a logistic regression setting unless the specific engine does not support generalised linear regressions (e.g. engine_bart).

Value

Adds biodiversity data to distribution object.

References

• 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.

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

See Also

Other add_biodiversity: add_biodiversity_poipo(), add_biodiversity_polpa(), add_biodiversity_polpo()

Examples

## Not run: 
# Define model
x <- distribution(background) |> add_biodiversity_poipa(virtual_species)

## End(Not run)

Description

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 signature '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

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.

Value

Adds biodiversity data to distribution object.

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

Other add_biodiversity: add_biodiversity_poipa(), add_biodiversity_polpa(), add_biodiversity_polpo()

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")

Description

This function can be used to add a sf polygon dataset to an existing distribution object. Presence-absence polygon data assumes that each area within the polygon can be treated as 'presence' for the species, while each area outside the polygon is where the species is absent.

Usage

add_biodiversity_polpa(
  x,
  polpa,
  name = NULL,
  field_occurrence = "observed",
  formula = NULL,
  family = "binomial",
  link = NULL,
  weight = 1,
  simulate = FALSE,
  simulate_points = 100,
  simulate_bias = NULL,
  simulate_strategy = "random",
  separate_intercept = TRUE,
  docheck = TRUE,
  pseudoabsence_settings = NULL,
  ...
)

## S4 method for signature 'BiodiversityDistribution,sf'
add_biodiversity_polpa(
  x,
  polpa,
  name = NULL,
  field_occurrence = "observed",
  formula = NULL,
  family = "binomial",
  link = NULL,
  weight = 1,
  simulate = FALSE,
  simulate_points = 100,
  simulate_bias = NULL,
  simulate_strategy = "random",
  separate_intercept = TRUE,
  docheck = TRUE,
  pseudoabsence_settings = NULL,
  ...
)

Arguments

Details

The default approach for polygon data is to sample presence-absence points across the region of the polygons. This function thus adds as a wrapper to add_biodiversity_poipa() as presence-only points are created by the model. Note if the polygon is used directly in the modelling the link between covariates and polygonal data is established by regular sampling of points within the polygon and is thus equivalent to simulating the points directly.

For an integration of range data as predictor or offset, see add_predictor_range() and add_offset_range() instead.

Value

Adds biodiversity data to distribution object.

See Also

Other add_biodiversity: add_biodiversity_poipa(), add_biodiversity_poipo(), add_biodiversity_polpo()

Examples

## Not run: 
 x <- distribution(background) |>
   add_biodiversity_polpa(protectedArea)

## End(Not run)

Description

This function can be used to add a sf polygon dataset to an existing distribution object. Presence-only polygon data is treated differential than point data in some engines particular through the way that points are generated.

Usage

add_biodiversity_polpo(
  x,
  polpo,
  name = NULL,
  field_occurrence = "observed",
  formula = NULL,
  family = "poisson",
  link = NULL,
  weight = 1,
  simulate = FALSE,
  simulate_points = 100,
  simulate_bias = NULL,
  simulate_strategy = "random",
  separate_intercept = TRUE,
  docheck = TRUE,
  pseudoabsence_settings = NULL,
  ...
)

## S4 method for signature 'BiodiversityDistribution,sf'
add_biodiversity_polpo(
  x,
  polpo,
  name = NULL,
  field_occurrence = "observed",
  formula = NULL,
  family = "poisson",
  link = NULL,
  weight = 1,
  simulate = FALSE,
  simulate_points = 100,
  simulate_bias = NULL,
  simulate_strategy = "random",
  separate_intercept = TRUE,
  docheck = TRUE,
  pseudoabsence_settings = NULL,
  ...
)

Arguments

Details

The default approach for polygon data is to sample presence-only points across the region of the polygons. This function thus adds as a wrapper to add_biodiversity_poipo() as presence-only points are created by the model. If no points are simulated directly (Default) then the polygon is processed by train() by creating regular point data over the supplied predictors.

Use add_biodiversity_polpa() to create binomial distributed inside-outside points for the given polygon!

For an integration of range data as predictor or offset, see

add_predictor_range() and add_offset_range() instead.

Value

Adds biodiversity data to distribution object.

See Also

Other add_biodiversity: add_biodiversity_poipa(), add_biodiversity_poipo(), add_biodiversity_polpa()

Examples

## Not run: 
 x <- distribution(mod) |>
   add_biodiversity_polpo(protectedArea)

## End(Not run)

Description

This function adds a constrain to a BiodiversityScenario object to constrain (future) projections. These constrains can for instance be constraints on a possible dispersal distance, connectivity between identified patches or limitations on species adaptability.

Most constrains require pre-calculated thresholds to present in the BiodiversityScenario object!

Usage

add_constraint(mod, method, ...)

## S4 method for signature 'BiodiversityScenario'
add_constraint(mod, method, ...)

Arguments

Details

Constraints can be added to scenario objects to increase or decrease the suitability of a given area for the target feature. This function acts as a wrapper to add these constraints. Currently supported are the following options:

Dispersal:

• sdd_fixed - Applies a fixed uniform dispersal distance per modelling timestep.

• sdd_nexpkernel - Applies a dispersal distance using a negative exponential kernel from its origin.

• kissmig - Applies the kissmig stochastic dispersal model. Requires `kissmig` package. Applied at each modelling time step.

• migclim - Applies the dispersal algorithm MigClim to the modelled objects. Requires "MigClim" package.

A comprehensive overview of the benefits of including dispersal constrains in species distribution models can be found in Bateman et al. (2013).

Connectivity:

• hardbarrier - Defines a hard barrier to any dispersal events. By definition this sets all values larger than 0 in the barrier layer to 0 in the projection. Barrier has to be provided through the "resistance" parameter.

• resistance - Allows the provision of a static or dynamic layer that is multiplied with the projection at each time step. Can for example be used to reduce the suitability of any given area (using pressures not included in the model). The respective layer(s) have to be provided through the "resistance" parameter. Provided layers are incorporated as abs(resistance - 1) and multiplied with the prediction.

Adaptability:

• nichelimit - Specifies a limit on the environmental niche to only allow a modest amount of extrapolation beyond the known occurrences. This can be particular useful to limit the influence of increasing marginal responses and avoid biologically unrealistic projections.

Boundary and size:

• boundary - Applies a hard boundary constraint on the projection, thus disallowing an expansion of a range outside the provide layer. Similar as specifying projection limits (see distribution), but can be used to specifically constrain a projection within a certain area (e.g. a species range or an island).

• minsize - Allows to specify a certain size that must be satisfied in order for a thresholded patch to be occupied. Can be thought of as a minimum size requirement. See add_constraint_minsize() for the required parameters.

• threshold - Applies the set threshold as a constrain directly on the suitability projections. Requires a threshold to be set.

Value

Adds constraints data to a BiodiversityScenario object.

References

• Bateman, B. L., Murphy, H. T., Reside, A. E., Mokany, K., & VanDerWal, J. (2013). Appropriateness of full‐, partial‐and no‐dispersal scenarios in climate change impact modelling. Diversity and Distributions, 19(10), 1224-1234.

• Nobis MP and Normand S (2014) KISSMig - a simple model for R to account for limited migration in analyses of species distributions. Ecography 37: 1282-1287.

• Mendes, P., Velazco, S. J. E., de Andrade, A. F. A., & Júnior, P. D. M. (2020). Dealing with overprediction in species distribution models: How adding distance constraints can improve model accuracy. Ecological Modelling, 431, 109180.

See Also

Other constraint: add_constraint_MigClim(), add_constraint_adaptability(), add_constraint_boundary(), add_constraint_connectivity(), add_constraint_dispersal(), add_constraint_minsize(), add_constraint_threshold(), simulate_population_steps()

Examples

## Not run: 
# Assumes that a trained 'model' object exists
 mod <- scenario(model) |>
  add_predictors(env = predictors, transform = 'scale', derivates = "none") |>
  add_constraint_dispersal(method = "kissmig", value = 2, pext = 0.1) |>
  project()

## End(Not run)

Description

Adaptability constraints assume that suitable habitat for species in (future) projections might be unsuitable if it is outside the range of conditions currently observed for the species.

Currently only nichelimit is implemented, which adds a simple constrain on the predictor parameter space, which can be defined through the "value" parameter. For example by setting it to 1 (Default), any projections are constrained to be within the range of at maximum 1 standard deviation from the range of covariates used for model training.

Usage

add_constraint_adaptability(
  mod,
  method = "nichelimit",
  names = NULL,
  value = 1,
  increment = 0,
  ...
)

## S4 method for signature 'BiodiversityScenario'
add_constraint_adaptability(
  mod,
  method = "nichelimit",
  names = NULL,
  value = 1,
  increment = 0,
  ...
)

Arguments

See Also

Other constraint: add_constraint(), add_constraint_MigClim(), add_constraint_boundary(), add_constraint_connectivity(), add_constraint_dispersal(), add_constraint_minsize(), add_constraint_threshold(), simulate_population_steps()

Examples

## Not run: 
scenario(fit) |>
 add_constraint_adaptability(value = 1)

## End(Not run)

Description

The purpose of boundary constraints is to limit a future projection within a specified area (such as for example a range or ecoregion). This can help to limit unreasonable projections into geographic space.

Similar to boundary constraints it is also possible to define a "zone" for the scenario projections, similar as was done for model training. The difference to a boundary constraint is that the boundary constraint is applied posthoc as a hard cut on any projection, while the zones would allow any projection (and other constraints) to be applied within the zone. Note: Setting a boundary constraint for future projections effectively potentially suitable areas!

Usage

add_constraint_boundary(mod, layer, ...)

## S4 method for signature 'BiodiversityScenario,sf'
add_constraint_boundary(mod, layer, method = "boundary", ...)

## S4 method for signature 'BiodiversityScenario,ANY'
add_constraint_boundary(mod, layer, method = "boundary", ...)

Arguments

See Also

Other constraint: add_constraint(), add_constraint_MigClim(), add_constraint_adaptability(), add_constraint_connectivity(), add_constraint_dispersal(), add_constraint_minsize(), add_constraint_threshold(), simulate_population_steps()

Examples

## Not run: 
# Add scenario constraint
scenario(fit) |> add_constraint_boundary(range)

## End(Not run)

Description

Adds a connectivity constraint to a scenario object.

Usage

add_constraint_connectivity(mod, method, value = NULL, resistance = NULL, ...)

## S4 method for signature 'BiodiversityScenario'
add_constraint_connectivity(mod, method, value = NULL, resistance = NULL, ...)

Arguments

Details

• hardbarrier - Defines a hard barrier to any dispersal events. By definition this sets all values larger than 0 in the barrier layer to 0 in the projection. Barrier has to be provided through the "resistance" parameter.

• resistance - Allows the provision of a static or dynamic layer that is multiplied with the projection at each time step. Can for example be used to reduce the suitability of any given area (using pressures not included in the model). The respective layer(s) have to be provided through the "resistance" parameter. Provided layers are incorporated as abs(resistance - 1) and multiplied with the prediction.

See Also

Other constraint: add_constraint(), add_constraint_MigClim(), add_constraint_adaptability(), add_constraint_boundary(), add_constraint_dispersal(), add_constraint_minsize(), add_constraint_threshold(), simulate_population_steps()

Description

Add dispersal constraint to an existing scenario

Usage

add_constraint_dispersal(mod, method, value = NULL, type = NULL, ...)

## S4 method for signature 'BiodiversityScenario'
add_constraint_dispersal(mod, method, value = NULL, type = NULL, ...)

Arguments

Details

Dispersal: Parameters for 'method':

• sdd_fixed - Applies a fixed uniform dispersal distance per modelling timestep.

• sdd_nexpkernel - Applies a dispersal distance using a negative exponential kernel from its origin. #' The negative exponential kernel is defined as:

  $f(x) = \frac{1}{2 \pi a^2} e^{-\frac{x}{a}}$

  where $a$ is the mean dispersal distance (in m) divided by 2.

• kissmig - Applies the kissmig stochastic dispersal model. Requires `kissmig` package. Applied at each modelling time step.

• migclim - Applies the dispersal algorithm MigClim to the modelled objects. Requires "MigClim" package.

A comprehensive overview of the benefits of including dispersal constrains in species distribution models can be found in Bateman et al. (2013).

The following additional parameters can bet set:

• pext: numeric indicator for `kissmig` of the probability a colonized cell becomes uncolonised, i.e., the species gets locally extinct (Default: 0.1).

• pcor: numeric probability that corner cells are considered in the 3x3 neighbourhood (Default: 0.2).

Note

Unless otherwise stated, the default unit of supplied distance values (e.g. average dispersal distance) should be in "m".

References

• Bateman, B. L., Murphy, H. T., Reside, A. E., Mokany, K., & VanDerWal, J. (2013). Appropriateness of full‐, partial‐and no‐dispersal scenarios in climate change impact modelling. Diversity and Distributions, 19(10), 1224-1234.

See Also

Other constraint: add_constraint(), add_constraint_MigClim(), add_constraint_adaptability(), add_constraint_boundary(), add_constraint_connectivity(), add_constraint_minsize(), add_constraint_threshold(), simulate_population_steps()

Description

This function adds constrain as defined by the MigClim approach (Engler et al. 2013) to a BiodiversityScenario object to constrain future projections. For a detailed description of MigClim, please the respective reference and the UserGuide. The default parameters chosen here are suggestions.

Usage

add_constraint_MigClim(
  mod,
  rcThresholdMode = "continuous",
  dispSteps = 1,
  dispKernel = c(1, 0.4, 0.16, 0.06, 0.03),
  barrierType = "strong",
  lddFreq = 0,
  lddRange = c(1000, 10000),
  iniMatAge = 1,
  propaguleProdProb = c(0.2, 0.6, 0.8, 0.95),
  replicateNb = 10,
  dtmp = terra::terraOptions(print = F)$tempdir
)

## S4 method for signature 'BiodiversityScenario'
add_constraint_MigClim(
  mod,
  rcThresholdMode = "continuous",
  dispSteps = 1,
  dispKernel = c(1, 0.4, 0.16, 0.06, 0.03),
  barrierType = "strong",
  lddFreq = 0,
  lddRange = c(1000, 10000),
  iniMatAge = 1,
  propaguleProdProb = c(0.2, 0.6, 0.8, 0.95),
  replicateNb = 10,
  dtmp = terra::terraOptions(print = F)$tempdir
)

Arguments

Details

The barrier parameter is defined through "add_barrier".

Value

Adds a MigClim onstrain to a BiodiversityScenario object.

References

• Engler R., Hordijk W. and Guisan A. The MIGCLIM R package – seamless integration of dispersal constraints into projections of species distribution models. Ecography,

• Robin Engler, Wim Hordijk and Loic Pellissier (2013). MigClim: Implementing dispersal into species distribution models. R package version 1.6.

See Also

Other constraint: add_constraint(), add_constraint_adaptability(), add_constraint_boundary(), add_constraint_connectivity(), add_constraint_dispersal(), add_constraint_minsize(), add_constraint_threshold(), simulate_population_steps()

Examples

## Not run: 
# Assumes that a trained 'model' object exists
 mod <- scenario(model) |>
  add_predictors(env = predictors, transform = 'scale',
                 derivates = "none") |>
  add_constraint_MigClim() |>
  project()

## End(Not run)

Description

This function applies a minimum size constraint on a scenario() created object. The rationale here is that for a given species isolated habitat patches smaller than a given size might not be viable / unrealistic for a species to establish a (long-term) presence.

The idea thus is to apply a constraint in that only patches bigger than a certain size are retained between timesteps. It has thus the potential to reduce subsequent colonizations of neighbouring patches.

Usage

add_constraint_minsize(
  mod,
  value,
  unit = "km2",
  establishment_step = FALSE,
  ...
)

## S4 method for signature 'BiodiversityScenario,numeric'
add_constraint_minsize(
  mod,
  value,
  unit = "km2",
  establishment_step = FALSE,
  ...
)

Arguments

Details

Area values in a specific unit need to be supplied.

Note

This function requires that a scenario has a set threshold()!

See Also

Other constraint: add_constraint(), add_constraint_MigClim(), add_constraint_adaptability(), add_constraint_boundary(), add_constraint_connectivity(), add_constraint_dispersal(), add_constraint_threshold(), simulate_population_steps()

Examples

## Not run: 
scenario(fit) |>
 add_predictors(future_covariates) |>
 threshold() |>
 add_constraint_minsize(value = 1000, unit = "km2") |>
 project()

## End(Not run)

Description

This option adds a threshold() constraint to a scenario projection, thus effectively applying the threshold as mask to each projection step made during the scenario projection.

Applying this constraint thus means that the "suitability" projection is clipped to the threshold. This method requires the threshold() set for a scenario object.

It could be in theory possible to re calculate the threshold for each time step based on supplied parameters or even observation records. So far this option has not been necessary to implement.

Usage

add_constraint_threshold(mod, updatevalue = NA, ...)

## S4 method for signature 'BiodiversityScenario'
add_constraint_threshold(mod, updatevalue = NA, ...)

Arguments

Note

Threshold values are taken from the original fitted model.

See Also

Other constraint: add_constraint(), add_constraint_MigClim(), add_constraint_adaptability(), add_constraint_boundary(), add_constraint_connectivity(), add_constraint_dispersal(), add_constraint_minsize(), simulate_population_steps()

Examples

## Not run: 
# Add scenario constraint
scenario(fit) |> threshold() |>
add_constraint_threshold()

## End(Not run)

Description

Sampling and other biases are pervasive drivers of the spatial location of biodiversity datasets. While the integration of other, presumably less biased data can be one way of controlling for sampling biases, another way is to control directly for the bias in the model. Currently supported methods are:

• "partial" - An approach described by Warton et al. (2013) to control the biases in a model, by including a specified variable ("layer") in the model, but "partialling" it out during the projection phase. Specifically the variable is set to a specified value ("bias_value"), which is by default the minimum value observed across the background.

• "offset" - Dummy method that points to the add_offset_bias() functionality (see note). Makes use of offsets to factor out a specified bias variable.

• "proximity" - Use the proximity or distance between points as a weight in the model. This option effectively places greater weight on points farther away. Note: In the best case this can control for spatial bias and aggregation, in the worst case it can place a lot of emphasis on points that likely outliers or misidentification (in terms of species).

See also details for some explanations.

Usage

add_control_bias(
  x,
  layer,
  method = "partial",
  bias_value = NULL,
  maxdist = NULL,
  alpha = 1,
  add = TRUE
)

## S4 method for signature 'BiodiversityDistribution'
add_control_bias(
  x,
  layer,
  method = "partial",
  bias_value = NULL,
  maxdist = NULL,
  alpha = 1,
  add = TRUE
)

Arguments

Details

In the case of "proximity" weights are assigned to each point, placing higher weight on points further away and with less overlap. Weights are are assigned up to a maximum of distance which can be provided by the user (parameter "maxdist"). This distance is ideally informed by some knowledge of the species to be modelled (e.g., maximum dispersal distance). If not provided, it is set to the distance of the centroid of a minimum convex polygon encircling all observations. The parameter "alpha" is a weighting factor which can be used to diminish the effect of neighboring points.
For a given observation $i$, the weight $w$ is defined as

$w_i = 1 / (1 + \epsilon)$

where

$\epsilon = \sum_{n=1}^{N}((1 - d_n)/d_sac)^\alpha$

in which $N$ is the total number of points closer than the maximum distance ($d_sac$) of point $i$, and $d_n$ the distance between focal point $i$ and point $n$.

Value

Adds bias control option to a distribution object.

Note

Covariate transformations applied to other predictors need to be applied to bias too. Another option to consider biases particular in Poisson-point process models is to remove them through an offset. Functionality to do so is available through the add_offset_bias() method. Setting the method to "offset" will automatically point to this option.

References

• Warton, D.I., Renner, I.W. and Ramp, D., 2013. Model-based control of observer bias for the analysis of presence-only data in ecology. PloS one, 8(11), p.e79168.

• Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.A., 2016. Improving niche and range estimates with Maxent and point process models by integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453

• Botella, C., Joly, A., Bonnet, P., Munoz, F., & Monestiez, P. (2021). Jointly estimating spatial sampling effort and habitat suitability for multiple species from opportunistic presence‐only data. Methods in Ecology and Evolution, 12(5), 933-945.

See Also

add_limits_extrapolation()

Examples

## Not run: 
 x <- distribution(background) |>
   add_predictors(covariates) |>
   add_control_bias(biasvariable, bias_value = NULL)

## End(Not run)

Description

In general we understand under latent spatial effects the occurrence of spatial dependency in the observations, which might either be caused by spatial biases, similarities in the underlying sampling processes or unmeasured latent covariates, e.g. those that have not been quantified.

This package supports a range of different spatial effects, however they differ from another by their impact on the estimated prediction. Some effects simply add the spatial dependence as covariate, others make use of spatial random effects to account for spatial dependence in the predictions. By default these effects are added to each dataset as covariate or shared spatial field (e.g. SPDE). See details for an explanation of the available options.

Usage

add_latent_spatial(
  x,
  method = "spde",
  priors = NULL,
  separate_spde = FALSE,
  ...
)

## S4 method for signature 'BiodiversityDistribution'
add_latent_spatial(
  x,
  method = "spde",
  priors = NULL,
  separate_spde = FALSE,
  ...
)

## S4 method for signature 'BiodiversityScenario'
add_latent_spatial(x, layer = NULL, reuse_latent = TRUE, ...)

Arguments

Details

There are several different options some of which depend on the engine used. In case a unsupported method for an engine is chosen this is modified to the next similar method.

Available are:

• "spde" - stochastic partial differential equation (SPDE) for engine_inla and engine_inlabru. SPDE effects aim at capturing the variation of the response variable in space, once all of the covariates are accounted for. Examining the spatial distribution of the spatial error can reveal which covariates might be missing. For example, if elevation is positively correlated with the response variable, but is not included in the model, we could see a higher posterior mean in areas with higher elevation. Note that calculations of SPDE's can be computationally costly.

• "car" - conditional autocorrelative errors (CAR) for engine_inla. Not yet implemented in full.

• "kde" - additional covariate of the kernel density of input point observations.

• "poly" - spatial trend correction by adding coordinates as polynominal transformation. This method assumed that a transformation of spatial coordinates can if - included as additional predictor - explain some of the variance in the distribution. This method does not interact with species occurrences.

• "nnd" - nearest neighbour distance. This function calculates the euclidean distance from each point to the nearest other grid cell with known species occurrence. Originally proposed by Allouche et al. (2008) and can be applied across all datasets in the BiodiversityDistribution) object.

Value

Adds latent spatial effect to a distribution object.

References

• Allouche, O.; Steinitz, O.; Rotem, D.; Rosenfeld, A.; Kadmon, R. (2008). Incorporating distance constraints into species distribution models. Journal of Applied Ecology, 45(2), 599-609. doi:10.1111/j.1365-2664.2007.01445.x

• Mendes, P., Velazco, S. J. E., de Andrade, A. F. A., & Júnior, P. D. M. (2020). Dealing with overprediction in species distribution models: How adding distance constraints can improve model accuracy. Ecological Modelling, 431, 109180.

Examples

## Not run: 
 distribution(background) |> add_latent_spatial(method = "poly")

## End(Not run)

Description

One of the main aims of species distribution models (SDMs) is to project in space and time. For projections a common issue is extrapolation as - unconstrained - SDMs can indicate areas as suitable which are unlikely to be occupied by species or habitats (often due to historic or biotic factors). To some extent this can be related to an insufficient quantification of the niche (e.g. niche truncation by considering only a subset of observations within the actual distribution), in other cases there can also be general barriers or constraints that limit any projections (e.g. islands). This limit method adds some of those options to a model distribution object. Currently supported methods are:

* "zones" - This is a wrapper to allow the addition of zones to a distribution model object, similar to what is also possible via distribution(). Required is a spatial layer that describes a environmental zoning.

* "mcp" - Rather than using an external or additional layer, this option constraints predictions by a certain distance of points in its vicinity. Buffer distances have to be in the unit of the projection used and can be configured via "mcp_buffer".

* "nt2" - Constraints the predictions using the multivariate combination novelty index (NT2) following Mesgaran et al. (2014). This method is also available in the similarity() function.

* "mess" - Constraints the predictions using the Multivariate Environmental Similarity Surfaces (MESS) following Mesgaran et al. (2014). This method is also available in the similarity() function.

* "shape" - This is an implementation of the 'shape' method introduced by Velazco et al. (2023). Through a user defined threshold it effectively limits model extrapolation so that no projections are made beyond the extent judged as defensible and informed by the training observations. Not yet implemented!

See also details for further explanations.

Usage

add_limits_extrapolation(
  x,
  layer,
  method = "mcp",
  mcp_buffer = 0,
  novel = "within",
  limits_clip = FALSE
)

## S4 method for signature 'BiodiversityDistribution'
add_limits_extrapolation(
  x,
  layer,
  method = "mcp",
  mcp_buffer = 0,
  novel = "within",
  limits_clip = FALSE
)

Arguments

Details

For method "zones" a zoning layer can be supplied which is then used to intersect the provided training points with. Any projections made with the model can then be constrained so as to not project into areas that do not consider any training points and are unlikely to have any. Examples for zones are for the separation of islands and mainlands, biomes, or lithological soil conditions.

If no layer is available, it is also possible to constraint predictions by the distance to a minimum convex polygon surrounding the training points with method "mcp" (optionally buffered). This can make sense particular for rare species or those fully sampled across their niche.

For the "NT2" and "MESS" index it is possible to constrain the prediction to conditions within (novel = "within") or also include outside (novel = "outside") conditions.

Value

Adds extrapolation limit option to a distribution object.

Note

The method "zones" is also possible directly within distribution().

References

• Randin, C. F., Dirnböck, T., Dullinger, S., Zimmermann, N. E., Zappa, M., & Guisan, A. (2006). Are niche‐based species distribution models transferable in space?. Journal of biogeography, 33(10), 1689-1703. https://doi.org/10.1111/j.1365-2699.2006.01466.x

• Chevalier, M., Broennimann, O., Cornuault, J., & Guisan, A. (2021). Data integration methods to account for spatial niche truncation effects in regional projections of species distribution. Ecological Applications, 31(7), e02427. https://doi.org/10.1002/eap.2427

• Velazco, S. J. E., Brooke, M. R., De Marco Jr., P., Regan, H. M., & Franklin, J. (2023). How far can I extrapolate my species distribution model? Exploring Shape, a novel method. Ecography, 11, e06992. https://doi.org/10.1111/ecog.06992

• Mesgaran, M. B., R. D. Cousens, B. L. Webber, and J. Franklin. (2014) Here be dragons: a tool for quantifying novelty due to covariate range and correlation change when projecting species distribution models. Diversity and Distributions 20:1147-1159.

Examples

## Not run: 
 # To add a zone layer for extrapolation constraints.
 x <- distribution(background) |>
   add_predictors(covariates) |>
   add_limits_extrapolation(method = "zones", layer = zones)

## End(Not run)

Description

This function allows to specify a file as Log file, which is used to save all console outputs, prints and messages.

Usage

add_log(x, filename)

## S4 method for signature 'BiodiversityDistribution,character'
add_log(x, filename)

Arguments

Value

Adds a log file to a distribution object.

Examples

## Not run: 
 x <- distribution(background) |>
    add_log()
 x

## End(Not run)

Description

Including offsets is another option to integrate spatial prior information in linear and additive regression models. Offsets shift the intercept of the regression fit by a certain amount. Although only one offset can be added to a regression model, it is possible to combine several spatial-explicit estimates into one offset by calculating the sum of all spatial-explicit layers.

Usage

add_offset(x, layer, add = TRUE)

## S4 method for signature 'BiodiversityDistribution,SpatRaster'
add_offset(x, layer, add = TRUE)

## S4 method for signature 'BiodiversityDistribution,sf'
add_offset(x, layer, add = TRUE)

Arguments

Details

This function allows to set any specific offset to a regression model. The offset has to be provided as spatial SpatRaster object. This function simply adds the layer to a distribution() object. Note that any transformation of the offset (such as log) has do be done externally!

If the layer is range and requires additional formatting, consider using the function add_offset_range() which has additional functionalities such such distance transformations.

Value

Adds an offset to a distribution object.

Note

Since offsets only make sense for linear regressions (and not for instance regression tree based methods such as engine_bart()), they do not work for all engines. Offsets specified for non-supported engines are ignored during the estimation

References

• Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.A., 2016. Improving niche and range estimates with Maxent and point process models by integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453

See Also

Other offset: add_offset_bias(), add_offset_elevation(), add_offset_range(), rm_offset()

Examples

## Not run: 
 x <- distribution(background) |>
   add_predictors(covariates) |>
   add_offset(nicheEstimate)

## End(Not run)

Description

Including offsets is another option to integrate spatial prior information in linear and additive regression models. Offsets shift the intercept of the regression fit by a certain amount. Although only one offset can be added to a regression model, it is possible to combine several spatial-explicit estimates into one offset by calculating the sum of all spatial-explicit layers.

Usage

add_offset_bias(x, layer, add = TRUE, points = NULL)

## S4 method for signature 'BiodiversityDistribution,SpatRaster'
add_offset_bias(x, layer, add = TRUE, points = NULL)

Arguments

Details

This functions emulates the use of the add_offset() function, however applies an inverse transformation to remove the provided layer from the overall offset. So if for instance a offset is already specified (such as area), this function removes the provided bias.layer from it via "offset(log(off.area)-log(bias.layer))"

Note that any transformation of the offset (such as log) has do be done externally!

If a generic offset is added, consider using the add_offset() function. If the layer is a expert-based range and requires additional parametrization, consider using the function add_offset_range() or the bossMaps R-package.

Value

Adds a bias offset to a distribution object.

References

• Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.A., 2016. Improving niche and range estimates with Maxent and point process models by integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453

See Also

Other offset: add_offset(), add_offset_elevation(), add_offset_range(), rm_offset()

Examples

## Not run: 
 x <- distribution(background) |>
   add_predictors(covariates) |>
   add_offset_bias(samplingBias)

## End(Not run)

Description

This function implements the elevation preferences offset defined in Ellis‐Soto et al. (2021). The code here was adapted from the Supporting materials script.

Usage

add_offset_elevation(x, elev, pref, rate = 0.0089, add = TRUE)

## S4 method for signature 'BiodiversityDistribution,SpatRaster,numeric'
add_offset_elevation(x, elev, pref, rate = 0.0089, add = TRUE)

Arguments

Details

Specifically this functions calculates a continuous decay and decreasing probability of a species to occur from elevation limits. It requires a SpatRaster with elevation information. A generalized logistic transform (aka Richard's curve) is used to calculate decay from the suitable elevational areas, with the "rate" parameter allowing to vary the steepness of decline.

Note that all offsets created by this function are by default log-transformed before export. In addition this function also mean-centers the output as recommended by Ellis-Soto et al.

Value

Adds a elevational offset to a distribution object.

References

• Ellis‐Soto, D., Merow, C., Amatulli, G., Parra, J.L., Jetz, W., 2021. Continental‐scale 1 km hummingbird diversity derived from fusing point records with lateral and elevational expert information. Ecography (Cop.). 44, 640–652. https://doi.org/10.1111/ecog.05119

• Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.A., 2016. Improving niche and range estimates with Maxent and point process models by integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453

See Also

Other offset: add_offset(), add_offset_bias(), add_offset_range(), rm_offset()

Examples

## Not run: 
 # Adds the offset to a distribution object
 distribution(background) |> add_offset_elevation(dem, pref = c(400, 1200))

## End(Not run)

Description

This function has additional options compared to the more generic add_offset(), allowing customized options specifically for expert-based ranges as offsets or spatialized polygon information on species occurrences. If even more control is needed, the user is informed of the "bossMaps" package Merow et al. (2017). Some functionalities of that package emulated through the "distance_function" set to "log". This tries to fit a 5-parameter logistic function to estimate the distance from the range (Merow et al. 2017).

Usage

add_offset_range(
  x,
  layer,
  distance_max = Inf,
  family = "poisson",
  presence_prop = 0.9,
  distance_clip = FALSE,
  distance_function = "negexp",
  field_occurrence = "observed",
  fraction = NULL,
  point = FALSE,
  add = TRUE
)

## S4 method for signature 'BiodiversityDistribution,SpatRaster'
add_offset_range(x, layer, fraction = NULL, add = TRUE)

## S4 method for signature 'BiodiversityDistribution,sf'
add_offset_range(
  x,
  layer,
  distance_max = Inf,
  family = "poisson",
  presence_prop = 0.9,
  distance_clip = FALSE,
  distance_function = "negexp",
  field_occurrence = "observed",
  fraction = NULL,
  point = FALSE,
  add = TRUE
)

Arguments

Details

The output created by this function creates a SpatRaster to be added to a provided distribution object. Offsets in regression models are likelihood specific as they are added directly to the overall estimate of `y^hat`.

Note that all offsets created by this function are by default log-transformed before export. Background values (e.g. beyond "distance_max") are set to a very small constant (1e-10).

Value

Adds a range offset to a distribution object.

References

• Merow, C., Wilson, A.M., Jetz, W., 2017. Integrating occurrence data and expert maps for improved species range predictions. Glob. Ecol. Biogeogr. 26, 243–258. https://doi.org/10.1111/geb.12539

• Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.A., 2016. Improving niche and range estimates with Maxent and point process models by integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453

See Also

"bossMaps"

Other offset: add_offset(), add_offset_bias(), add_offset_elevation(), rm_offset()

Examples

## Not run: 
 # Train a presence-only model with a simple offset
 fit <- distribution(background) |>
 add_biodiversity_poipo(virtual_points, field_occurrence = "Observed") |>
 add_predictors(predictors) |>
 add_offset_range(virtual_range, distance_max = 5,distance_function = "logcurve",
 distance_clip = TRUE ) |>
 engine_glm() |>
 train()

## End(Not run)

Description

Create lower and upper limits for an elevational range and add them as separate predictors

Usage

add_predictor_elevationpref(x, layer, lower, upper, transform = "none")

## S4 method for signature 'BiodiversityDistribution,ANY,numeric,numeric'
add_predictor_elevationpref(x, layer, lower, upper, transform = "none")

Arguments

Examples

## Not run: 
distribution(background) |>
  add_predictor_elevationpref(elevation, lower = 200, upper = 1000)

## End(Not run)

Description

This function allows to add a species range which is usually drawn by experts in a separate process as spatial explicit prior. Both sf and SpatRaster-objects are supported as input.

Users are advised to look at the "bossMaps" R-package presented as part of Merow et al. (2017), which allows flexible calculation of non-linear distance transforms from the boundary of the range. Outputs of this package could be added directly to this function. Note that this function adds the range as predictor and not as offset. For this purpose a separate function add_offset_range() exists.

Additional options allow to include the range either as "binary" or as "distance" transformed predictor. The difference being that the range is either directly included as presence-only predictor or alternatively with a linear distance transform from the range boundary. The parameter "distance_max" can be specified to constrain this distance transform.

Usage

add_predictor_range(
  x,
  layer,
  method = "distance",
  distance_max = NULL,
  fraction = NULL,
  priors = NULL
)

## S4 method for signature 'BiodiversityDistribution,SpatRaster'
add_predictor_range(
  x,
  layer,
  method = "precomputed_range",
  fraction = NULL,
  priors = NULL
)

## S4 method for signature 'BiodiversityDistribution,sf'
add_predictor_range(
  x,
  layer,
  method = "distance",
  distance_max = Inf,
  fraction = NULL,
  priors = NULL
)

Arguments

References

• Merow, C., Wilson, A. M., & Jetz, W. (2017). Integrating occurrence data and expert maps for improved species range predictions. Global Ecology and Biogeography, 26(2), 243–258. https://doi.org/10.1111/geb.12539

Examples

## Not run: 
distribution(background) |>
  add_predictor_range(range, method = "distance", distance_max = 2)

## End(Not run)

Description

This function allows to add predictors to distribution or BiodiversityScenario objects. Predictors are covariates that in spatial projection have to match the geographic projection of the background layer in the distribution object. This function furthermore allows to transform or create derivates of provided predictors.

Usage

add_predictors(
  x,
  env,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  explode_factors = FALSE,
  priors = NULL,
  state = NULL,
  ...
)

## S4 method for signature 'BiodiversityDistribution,SpatRasterCollection'
add_predictors(
  x,
  env,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  explode_factors = FALSE,
  priors = NULL,
  state = NULL,
  ...
)

## S4 method for signature 'BiodiversityDistribution,SpatRaster'
add_predictors(
  x,
  env,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  explode_factors = FALSE,
  priors = NULL,
  state = NULL,
  ...
)

## S4 method for signature 'BiodiversityDistribution,stars'
add_predictors(
  x,
  env,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  explode_factors = FALSE,
  priors = NULL,
  state = NULL,
  ...
)

## S4 method for signature 'BiodiversityScenario,SpatRaster'
add_predictors(
  x,
  env,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  explode_factors = FALSE,
  priors = NULL,
  state = NULL,
  ...
)

## S4 method for signature 'BiodiversityScenario,stars'
add_predictors(
  x,
  env,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  explode_factors = FALSE,
  priors = NULL,
  state = NULL,
  ...
)

Arguments

Details

A transformation takes the provided rasters and for instance rescales them or transforms them through a principal component analysis (prcomp). In contrast, derivates leave the original provided predictors alone, but instead create new ones, for instance by transforming their values through a quadratic or hinge transformation. Note that this effectively increases the number of predictors in the object, generally requiring stronger regularization by the used Engine. Both transformations and derivates can also be combined. Available options for transformation are:

• 'none' - Leaves the provided predictors in the original scale.

• 'pca' - Converts the predictors to principal components. Note that this results in a renaming of the variables to principal component axes!

• 'scale' - Transforms all predictors by applying scale on them.

• 'norm' - Normalizes all predictors by transforming them to a scale from 0 to 1.

• 'windsor' - Applies a windsorization to the target predictors. By default this effectively cuts the predictors to the 0.05 and 0.95, thus helping to remove extreme outliers.

Available options for creating derivates are:

• 'none' - No additional predictor derivates are created.

• 'quad' - Adds quadratic derivate predictors.

• 'interaction' - Add interacting predictors. Interactions need to be specified ("int_variables")!

• 'thresh' - Add threshold derivate predictors.

• 'hinge' - Add hinge derivate predictors.

• 'kmeans' - Add k-means derived factors.

• 'bin' - Add predictors binned by their percentiles.

Note

Important: Not every Engine supported by the ibis.iSDM R-package allows missing data points among extracted covariates. Thus any observation with missing data is generally removed prior from model fitting. Thus ensure that covariates have appropriate no-data settings (for instance setting NA values to 0 or another out of range constant).

Not every engine does actually need covariates. For instance it is perfectly legit to fit a model with only occurrence data and a spatial latent effect (add_latent_spatial). This correspondents to a spatial kernel density estimate.

Certain names such "offset" are forbidden as predictor variable names. The function will return an error message if these are used.

Some engines use binary variables regardless of the parameter explode_factors set here.

Examples

## Not run: 
 obj <- distribution(background) |>
        add_predictors(covariates, transform = 'scale')
 obj

## End(Not run)

Description

This is a customized function to format and add downscaled land-use shares from the Global Biosphere Management Model (GLOBIOM) to a distribution or BiodiversityScenario in ibis.iSDM. GLOBIOM is a partial-equilibrium model developed at IIASA and represents land-use sectors with a rich set of environmental and socio-economic parameters, where for instance the agricultural and forestry sector are estimated through dedicated process-based models. GLOBIOM outputs are spatial explicit and usually at a half-degree resolution globally. For finer grain analyses GLOBIOM outputs can be produced in a downscaled format with a customized statistical downscaling module.

The purpose of this script is to format the GLOBIOM outputs of DownScale for the use in the ibis.iSDM package.

Usage

add_predictors_globiom(
  x,
  fname,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  priors = NULL,
  ...
)

## S4 method for signature 'BiodiversityDistribution,character'
add_predictors_globiom(
  x,
  fname,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  priors = NULL,
  ...
)

## S4 method for signature 'BiodiversityScenario,character'
add_predictors_globiom(
  x,
  fname,
  names = NULL,
  transform = "none",
  derivates = "none",
  derivate_knots = 4,
  int_variables = NULL,
  bgmask = TRUE,
  harmonize_na = FALSE,
  priors = NULL,
  ...
)

Arguments

Details

See add_predictors() for additional parameters and customizations. For more (manual) control the function for formatting the GLOBIOM data can also be called directly via formatGLOBIOM().

See Also

add_predictors

Examples

## Not run: 
 obj <- distribution(background) |>
        add_predictors_globiom(fname = "", transform = 'none')
 obj

## End(Not run)

Description

This function is a convenience wrapper to add the output from a previous fitted DistributionModel to another BiodiversityDistribution object. Obviously only works if a prediction was fitted in the model. Options to instead add thresholds, or to transform / derivate the model outputs are also supported.

Usage

add_predictors_model(
  x,
  model,
  transform = "scale",
  derivates = "none",
  threshold_only = FALSE,
  priors = NULL,
  ...
)

## S4 method for signature 'BiodiversityDistribution'
add_predictors_model(
  x,
  model,
  transform = "scale",
  derivates = "none",
  threshold_only = FALSE,
  priors = NULL,
  ...
)

Arguments

Details

A transformation takes the provided rasters and for instance rescales them or transforms them through a principal component analysis (prcomp). In contrast, derivates leave the original provided predictors alone, but instead create new ones, for instance by transforming their values through a quadratic or hinge transformation. Note that this effectively increases the number of predictors in the object, generally requiring stronger regularization by the used Engine. Both transformations and derivates can also be combined. Available options for transformation are:

• 'none' - Leaves the provided predictors in the original scale.

• 'pca' - Converts the predictors to principal components. Note that this results in a renaming of the variables to principal component axes!

• 'scale' - Transforms all predictors by applying scale on them.

• 'norm' - Normalizes all predictors by transforming them to a scale from 0 to 1.

• 'windsor' - Applies a windsorization to the target predictors. By default this effectively cuts the predictors to the 0.05 and 0.95, thus helping to remove extreme outliers.

Available options for creating derivates are:

• 'none' - No additional predictor derivates are created.

• 'quad' - Adds quadratic transformed predictors.

• 'interaction' - Add interacting predictors. Interactions need to be specified ("int_variables")!

• 'thresh' - Add threshold transformed predictors.

• 'hinge' - Add hinge transformed predictors.

• 'bin' - Add predictors binned by their percentiles.

Examples

## Not run: 
 # Fit first model
 fit <- distribution(background) |>
        add_predictors(covariates) |>
        add_biodiversity_poipa(species) |>
        engine_glmnet() |>
        train()

 # New model object
 obj <- distribution(background) |>
        add_predictors_model(fit)
 obj

## End(Not run)

Description

This function simply allows to add priors to an existing distribution object. The supplied priors must be a PriorList object created through calling priors.

Usage

add_priors(x, priors = NULL, ...)

## S4 method for signature 'BiodiversityDistribution'
add_priors(x, priors = NULL, ...)

Arguments

Note

Alternatively priors to environmental predictors can also directly added as parameter via add_predictors

See Also

Other prior: BARTPrior(), BARTPriors(), BREGPrior(), BREGPriors(), GDBPrior(), GDBPriors(), GLMNETPrior(), GLMNETPriors(), INLAPrior(), INLAPriors(), STANPrior(), STANPriors(), XGBPrior(), XGBPriors(), get_priors(), priors(), rm_priors()

Examples

## Not run: 
 pp <-  GLMNETPrior("forest")
 x <- distribution(background) |>
  add_priors(pp)


## End(Not run)

Description

For most engines, background or pseudo-absence points are necessary. The distinction lies in how the absence data are handled. For poisson distributed responses, absence points are considered background points over which the intensity of sampling (lambda) is integrated (in a classical Poisson point-process model).

In contrast in binomial distributed responses, the absence information is assumed to be an adequate representation of the true absences and treated by the model as such... Here it is advised to specify absence points in a way that they represent potential true absence, such as for example through targeted background sampling or by sampling them within/outside a given range.

Usage

add_pseudoabsence(
  df,
  field_occurrence = "observed",
  template = NULL,
  settings = getOption("ibis.pseudoabsence")
)

Arguments

Details

A pseudoabs_settings() object can be added to setup how absence points should be sampled. A bias parameter can be set to specify a bias layer to sample from, for instance a layer of accessibility. Note that when modelling several datasets, it might make sense to check across all datasets whether certain areas are truly absent. By default, the pseudo-absence points are not sampled in areas in which there are already presence points.

Value

A data.frame containing the newly created pseudo absence points.

Note

This method removes all columns from the input df object other than the field_occurrence column and the coordinate columns (which will be created if not already present).

References

• Stolar, J., & Nielsen, S. E. (2015). Accounting for spatially biased sampling effort in presence‐only species distribution modelling. Diversity and Distributions, 21(5), 595-608.

• Bird, T.J., Bates, A.E., Lefcheck, J.S., Hill, N.A., Thomson, R.J., Edgar, G.J., Stuart-Smith, R.D., Wotherspoon, S., Krkosek, M., Stuart-Smith, J.F. and Pecl, G.T., 2014. Statistical solutions for error and bias in global citizen science datasets. Biological Conservation, 173, pp.144-154.

Align a SpatRaster object to another by harmonizing geometry and extend.

Description

If the data is not in the same projection as the template, the alignment will be computed by reprojection only. If the data has already the same projection, the data set will be cropped and aggregated prior to resampling in order to reduce computation time.

Usage

alignRasters(data, template, method = "bilinear", func = mean, cl = TRUE)

Arguments

Details

Nearest Neighbour resampling (near) is recommended for discrete and bilinear resampling recommended for continuous data. See also help from terra::resample for other options.

Value

New SpatRaster object aligned to the supplied template layer.

Examples

## Not run: 
 # Align one raster to another
 ras1 <- alignRasters( ras1, ras2, method = "near", cl = FALSE)

## End(Not run)

Description

As Id

Usage

as.Id(x, ...)

## S3 method for class 'character'
as.Id(x, ...)

Arguments

Description

Function to include prior information as split probability for the Bayesian additive regression tree model added via engine_bart.

Priors for engine_bart have to be specified as transition probabilities of variables which are internally used to generate splits in the regression tree. Specifying a prior can thus help to 'enforce' a split with a given variable. These can be numeric and coded as values between 0 and 1.

Usage

BARTPrior(variable, hyper = 0.75, ...)

## S4 method for signature 'character'
BARTPrior(variable, hyper = 0.75, ...)

Arguments

Note

Even if a given variable is included as split in the regression or classification tree, this does not necessarily mean that the prediction changes if the value is non-informative (as the split can occur early on). It does however affect any variable importance estimates calculated from the model.

References

• Chipman, H., George, E., and McCulloch, R. (2009) BART: Bayesian Additive Regression Trees.

• Chipman, H., George, E., and McCulloch R. (2006) Bayesian Ensemble Learning. Advances in Neural Information Processing Systems 19, Scholkopf, Platt and Hoffman, Eds., MIT Press, Cambridge, MA, 265-272.

See Also

Prior.

Other prior: BARTPriors(), BREGPrior(), BREGPriors(), GDBPrior(), GDBPriors(), GLMNETPrior(), GLMNETPriors(), INLAPrior(), INLAPriors(), STANPrior(), STANPriors(), XGBPrior(), XGBPriors(), add_priors(), get_priors(), priors(), rm_priors()

Description

This is a helper function to specify several BARTPrior objects with the same hyper-parameters, but different variables.

Usage

BARTPriors(variable, hyper = 0.75, ...)

## S4 method for signature 'character'
BARTPriors(variable, hyper = 0.75, ...)

Arguments

See Also

Other prior: BARTPrior(), BREGPrior(), BREGPriors(), GDBPrior(), GDBPriors(), GLMNETPrior(), GLMNETPriors(), INLAPrior(), INLAPriors(), STANPrior(), STANPriors(), XGBPrior(), XGBPriors(), add_priors(), get_priors(), priors(), rm_priors()

Description

BiodiversityDataset prototype description

Public fields

Methods

Public methods

• BiodiversityDataset$new()

• BiodiversityDataset$print()

• BiodiversityDataset$set_equation()

• BiodiversityDataset$get_equation()

• BiodiversityDataset$show_equation()

• BiodiversityDataset$get_id()

• BiodiversityDataset$get_type()

• BiodiversityDataset$get_column_occ()

• BiodiversityDataset$get_family()

• BiodiversityDataset$get_link()

• BiodiversityDataset$get_data()

• BiodiversityDataset$get_weight()

• BiodiversityDataset$show()

• BiodiversityDataset$get_observations()

• BiodiversityDataset$mask()

• BiodiversityDataset$clone()

Method new()

Initializes the object and creates an empty list

Usage

BiodiversityDataset$new(
  name,
  id,
  equation,
  family,
  link,
  type,
  weight,
  field_occurrence,
  data,
  use_intercept,
  pseudoabsence_settings
)

Arguments

Returns

NULL

Method print()

Print the names and properties of all Biodiversity datasets contained within

Usage

BiodiversityDataset$print()

Returns

A message on screen

Method set_equation()

Set new equation and writes it into formula

Usage

BiodiversityDataset$set_equation(x)

Arguments

Returns

Invisible

Method get_equation()

Get equation

Usage

BiodiversityDataset$get_equation()

Returns

A placeholder or formula object.

Method show_equation()

Function to print the equation

Usage

BiodiversityDataset$show_equation()

Returns

A message on screen.

Method get_id()

Get Id within the dataset

Usage

BiodiversityDataset$get_id()

Returns

A character with the id.

Method get_type()

Get type of the dataset.

Usage

BiodiversityDataset$get_type(short = FALSE)

Arguments

Returns

A character with the type

Method get_column_occ()

Get field with occurrence information

Usage

BiodiversityDataset$get_column_occ()

Returns

A character with the occurence field

Method get_family()

Get family

Usage

BiodiversityDataset$get_family()

Returns

A character with the family for the dataset

Method get_link()

Get custom link function

Usage

BiodiversityDataset$get_link()

Returns

A character with the family for the dataset

Method get_data()

Get data from the object

Usage

BiodiversityDataset$get_data()

Returns

A sf object with the data

Method get_weight()

Get weight

Usage

BiodiversityDataset$get_weight()

Returns

A numeric with the weights within the dataset.

Method show()

Print input messages

Usage

BiodiversityDataset$show()

Returns

A message on screen.

Method get_observations()

Collect info statistics about number of observations

Usage

BiodiversityDataset$get_observations()

Returns

A numeric with the number of observations.

Method mask()

Convenience function to mask all input datasets.

Usage

BiodiversityDataset$mask(mask, inverse = FALSE, ...)

Arguments

Returns

Invisible

Method clone()

The objects of this class are cloneable with this method.

Usage

BiodiversityDataset$clone(deep = FALSE)

Arguments

Description

Acts a container for a specified set of BiodiversityDataset contained within. Functions are provided to summarize across the BiodiversityDataset-class objects.

Public fields

Methods

Public methods

• BiodiversityDatasetCollection$new()

• BiodiversityDatasetCollection$print()

• BiodiversityDatasetCollection$show()

• BiodiversityDatasetCollection$get_types()

• BiodiversityDatasetCollection$get_names()

• BiodiversityDatasetCollection$set_data()

• BiodiversityDatasetCollection$get_data_object()

• BiodiversityDatasetCollection$get_data()

• BiodiversityDatasetCollection$get_coordinates()

• BiodiversityDatasetCollection$mask()

• BiodiversityDatasetCollection$rm_data()

• BiodiversityDatasetCollection$length()

• BiodiversityDatasetCollection$get_observations()

• BiodiversityDatasetCollection$get_equations()

• BiodiversityDatasetCollection$get_families()

• BiodiversityDatasetCollection$get_links()

• BiodiversityDatasetCollection$get_columns_occ()

• BiodiversityDatasetCollection$get_weights()

• BiodiversityDatasetCollection$get_ids()

• BiodiversityDatasetCollection$get_id_byType()

• BiodiversityDatasetCollection$get_id_byName()

• BiodiversityDatasetCollection$show_equations()

• BiodiversityDatasetCollection$plot()

• BiodiversityDatasetCollection$clone()

Method new()

Initializes the object and creates an empty list

Usage

BiodiversityDatasetCollection$new()

Returns

NULL

Method print()

Print the names and properties of all Biodiversity datasets contained within

Usage

BiodiversityDatasetCollection$print(format = TRUE)

Arguments

Returns

A message on screen

Method show()

Aliases that calls print.

Usage

BiodiversityDatasetCollection$show()

Returns

A message on screen

Method get_types()

Types of all biodiversity datasets included in this

Usage

BiodiversityDatasetCollection$get_types(short = FALSE)

Arguments

Returns

A character vector.

Method get_names()

Get names and format them if necessary

Usage

BiodiversityDatasetCollection$get_names(format = FALSE)

Arguments

Returns

A character vector.

Method set_data()

Add a new Biodiversity dataset to this collection.

Usage

BiodiversityDatasetCollection$set_data(x, value)

Arguments

Returns

Invisible

Method get_data_object()

Get a specific Biodiversity dataset by id

Usage

BiodiversityDatasetCollection$get_data_object(id)

Arguments

Returns

Returns a BiodiversityDataset.

Method get_data()

Get all biodiversity observations from a given dataset.

Usage

BiodiversityDatasetCollection$get_data(id)

Arguments

Returns

Returns all data from a set BiodiversityDataset.

Method get_coordinates()

Get coordinates for a given biodiversity dataset. Else return a wkt object

Usage

BiodiversityDatasetCollection$get_coordinates(id)

Arguments

Returns

All coordinates from a given object in data.frame.

Method mask()

Convenience function to mask all input datasets.

Usage

BiodiversityDatasetCollection$mask(mask, inverse = FALSE)

Arguments

Returns

Invisible

Method rm_data()

Remove a specific biodiversity dataset by id

Usage

BiodiversityDatasetCollection$rm_data(id)

Arguments

Returns

Invisible

Method length()

Number of Biodiversity Datasets in connection

Usage

BiodiversityDatasetCollection$length()

Returns

A numeric with the number of datasets.

Method get_observations()

Get number of observations of all datasets

Usage

BiodiversityDatasetCollection$get_observations()

Returns

A numeric with the number of observations across datasets.

Method get_equations()

Get equations from all datasets

Usage

BiodiversityDatasetCollection$get_equations()

Returns

A list vector with all equations across datasets.

Method get_families()

Get families from datasets.

Usage

BiodiversityDatasetCollection$get_families()

Returns

A list vector with all families across datasets.

Method get_links()

Get custom link functions

Usage

BiodiversityDatasetCollection$get_links()

Returns

A list vector with all link functions across datasets.

Method get_columns_occ()

Get fields with observation columns

Usage

BiodiversityDatasetCollection$get_columns_occ()

Returns

A list vector with the names of observation columns.

Method get_weights()

Get the weights across datasets.

Usage

BiodiversityDatasetCollection$get_weights()

Returns

A list vector with the weights if set per dataset.

Method get_ids()

Get ids of all assets in the collection.

Usage

BiodiversityDatasetCollection$get_ids()

Returns

A list vector with the ids of all datasets.

Method get_id_byType()

Search for a specific biodiversity dataset with type

Usage

BiodiversityDatasetCollection$get_id_byType(type)

Arguments

Returns

A character with the id(s) of datasets with the given type.

Method get_id_byName()

Get id by name

Usage

BiodiversityDatasetCollection$get_id_byName(name)

Arguments

Returns

A character with the id(s) of datasets with the given name.

Method show_equations()

Show equations of all datasets

Usage

BiodiversityDatasetCollection$show_equations(msg = TRUE)

Arguments

Returns

Shows equations on screen or as character.

Method plot()

Plot the whole collection

Usage

BiodiversityDatasetCollection$plot()

Returns

Invisible

Method clone()

The objects of this class are cloneable with this method.

Usage

BiodiversityDatasetCollection$clone(deep = FALSE)

Arguments

Note

This can likely be beautified further.

Description

Base R6 class for any biodiversity distribution objects. Serves as container that supplies data and functions to other R6 classes. Generally stores all objects and parameters added to a model.

Details

Run names() on a distribution object to show all available functions.

Public fields

Methods

Public methods

• BiodiversityDistribution$new()

• BiodiversityDistribution$print()

• BiodiversityDistribution$show()

• BiodiversityDistribution$name()

• BiodiversityDistribution$show_background_info()

• BiodiversityDistribution$set_limits()

• BiodiversityDistribution$get_limits()

• BiodiversityDistribution$rm_limits()

• BiodiversityDistribution$get_predictor_names()

• BiodiversityDistribution$set_latent()

• BiodiversityDistribution$get_latent()

• BiodiversityDistribution$rm_latent()

• BiodiversityDistribution$get_priors()

• BiodiversityDistribution$set_priors()

• BiodiversityDistribution$set_biodiversity()

• BiodiversityDistribution$set_predictors()

• BiodiversityDistribution$set_engine()

• BiodiversityDistribution$get_engine()

• BiodiversityDistribution$rm_engine()

• BiodiversityDistribution$get_prior_variables()

• BiodiversityDistribution$set_offset()

• BiodiversityDistribution$get_offset()

• BiodiversityDistribution$rm_offset()

• BiodiversityDistribution$plot_offsets()

• BiodiversityDistribution$get_offset_type()

• BiodiversityDistribution$set_control()

• BiodiversityDistribution$get_control()

• BiodiversityDistribution$rm_control()

• BiodiversityDistribution$plot_bias()

• BiodiversityDistribution$get_log()

• BiodiversityDistribution$set_log()

• BiodiversityDistribution$get_extent()

• BiodiversityDistribution$get_projection()

• BiodiversityDistribution$get_resolution()

• BiodiversityDistribution$rm_predictors()

• BiodiversityDistribution$rm_priors()

• BiodiversityDistribution$show_biodiversity_length()

• BiodiversityDistribution$show_biodiversity_equations()

• BiodiversityDistribution$get_biodiversity_equations()

• BiodiversityDistribution$get_biodiversity_types()

• BiodiversityDistribution$get_biodiversity_ids()

• BiodiversityDistribution$get_biodiversity_names()

• BiodiversityDistribution$plot()

• BiodiversityDistribution$summary()

• BiodiversityDistribution$clone()

Method new()

Initializes the object and creates an BiodiversityDataset by default.

Usage

BiodiversityDistribution$new(background, limits, biodiversity, ...)

Arguments

Returns

NULL

Method print()

Looks for and returns the properties of all contained objects.

Usage

BiodiversityDistribution$print()

Returns

A message on screen

Method show()

An alias for print

Usage

BiodiversityDistribution$show()

Returns

A message on screen

Method name()

Returns self-describing name

Usage

BiodiversityDistribution$name()

Returns

A character with the name

Method show_background_info()

Summarizes extent and projection from set background

Usage

BiodiversityDistribution$show_background_info()

Returns

A character with the name

Method set_limits()

Specify new limits to the background

Usage

BiodiversityDistribution$set_limits(x)

Arguments

Returns

This object.

Method get_limits()

Get provided limits if set or a waiver

Usage

BiodiversityDistribution$get_limits()

Returns

A list or waiver.

Method rm_limits()

Remove limits if set.

Usage

BiodiversityDistribution$rm_limits()

Returns

This object.

Method get_predictor_names()

Function for querying predictor names if existing

Usage

BiodiversityDistribution$get_predictor_names()

Returns

A character vector.

Method set_latent()

Adding latent factors to the object.

Usage

BiodiversityDistribution$set_latent(type, method = NULL, separate_spde = FALSE)

Arguments

Returns

This object.

Method get_latent()

Get latent factors if found in object.

Usage

BiodiversityDistribution$get_latent()

Returns

A character with those objects.

Method rm_latent()

Remove latent factors if found in object.

Usage

BiodiversityDistribution$rm_latent()

Returns

This object.

Method get_priors()

Get prior object if found in object.

Usage

BiodiversityDistribution$get_priors()

Returns

This object.

Method set_priors()

Specify new prior object. Overwrites existing ones

Usage

BiodiversityDistribution$set_priors(x)

Arguments

Returns

This object.

Method set_biodiversity()

Adds a new biodiversity object to the existing empty collection.

Usage

BiodiversityDistribution$set_biodiversity(id, p)

Arguments

Returns

This object.

Method set_predictors()

Set a new Predictor object to this object.

Usage

BiodiversityDistribution$set_predictors(x)

Arguments

Returns

This object.

Method set_engine()

Set a new Engine object to this object.

Usage

BiodiversityDistribution$set_engine(x)

Arguments

Returns

This object.

Method get_engine()

Gets the name of the current engine if set.

Usage

BiodiversityDistribution$get_engine()

Returns

A character with the engine name

Method rm_engine()

Removes the current engine if set.

Usage

BiodiversityDistribution$rm_engine()

Returns

This object

Method get_prior_variables()

Get prior variables

Usage

BiodiversityDistribution$get_prior_variables()

Returns

A character with the variable names for which priors have been added.

Method set_offset()

Specify new offsets.

Usage

BiodiversityDistribution$set_offset(x)

Arguments

Returns

This object.

Method get_offset()

Get offset (print name)

Usage

BiodiversityDistribution$get_offset()

Returns

A character with all the offsets in here.

Method rm_offset()

Remove offsets if found.

Usage

BiodiversityDistribution$rm_offset(what = NULL)

Arguments

Returns

This object.

Method plot_offsets()

Plot offset if found.

Usage

BiodiversityDistribution$plot_offsets()

Returns

A graphical element.

Method get_offset_type()

Get offset parameters if found

Usage

BiodiversityDistribution$get_offset_type()

Returns

A list with the offset parameters if found.

Method set_control()

Set new bias control

Usage

BiodiversityDistribution$set_control(type = "bias", x, method, value)

Arguments

Returns

This object.

Method get_control()

Get bias control (print name)

Usage

BiodiversityDistribution$get_control(type = "bias")

Arguments

Returns

A character with the bias object if found.

Method rm_control()

Remove bias controls if found.

Usage

BiodiversityDistribution$rm_control()

Returns

This object.

Method plot_bias()

Plot bias variable if set.

Usage

BiodiversityDistribution$plot_bias()

Returns

A graphical element.

Method get_log()

Returns the output filename of the current log object if set.

Usage

BiodiversityDistribution$get_log()

Returns

A character where the output is returned.

Method set_log()

Set a new log object

Usage

BiodiversityDistribution$set_log(x)

Arguments

Returns

This object

Method get_extent()

Get extent

Usage

BiodiversityDistribution$get_extent()

Returns

Background extent or NULL.

Method get_projection()

Get projection from the background in crs format.

Usage

BiodiversityDistribution$get_projection()

Returns

A character of the projection

Method get_resolution()

Return resolution of the background object.

Usage

BiodiversityDistribution$get_resolution()

Returns

A vector with the resolution.

Method rm_predictors()

Remove predictiors. Either all of them or specific ones.

Usage

BiodiversityDistribution$rm_predictors(names)

Arguments

Returns

This object.

Method rm_priors()

Remove priors. Either all of them or specific ones.

Usage

BiodiversityDistribution$rm_priors(names = NULL)

Arguments

Returns

This object.

Method show_biodiversity_length()

Show number of biodiversity records

Usage

BiodiversityDistribution$show_biodiversity_length()

Returns

A numeric with sum of biodiversity records

Method show_biodiversity_equations()

Show Equations of biodiversity records

Usage

BiodiversityDistribution$show_biodiversity_equations()

Returns

A message on screen.

Method get_biodiversity_equations()

Get equations of biodiversity records

Usage

BiodiversityDistribution$get_biodiversity_equations()

Returns

A list vector.

Method get_biodiversity_types()

Query all biodiversity types in this object

Usage

BiodiversityDistribution$get_biodiversity_types()

Returns

A character vector.

Method get_biodiversity_ids()

Return all biodiversity dataset ids in the object

Usage

BiodiversityDistribution$get_biodiversity_ids()

Returns

A list for the ids in the biodiversity datasets

Method get_biodiversity_names()

Return all the character names of all biodiversity datasets

Usage

BiodiversityDistribution$get_biodiversity_names()

Returns

A list with the names in the biodiversity datasets

Method plot()

Plots the content of this class.

Usage

BiodiversityDistribution$plot()

Returns

A message.

Method summary()

Summary function for this object.

Usage

BiodiversityDistribution$summary()

Returns

A message.

Method clone()

The objects of this class are cloneable with this method.

Usage

BiodiversityDistribution$clone(deep = FALSE)

Arguments

Note

Not implemented yet.

Not implemented yet.

See Also

add_limits_extrapolation()

add_latent_spatial()

add_priors()

add_biodiversity_poipa(), add_biodiversity_poipo(), add_biodiversity_polpa(), add_biodiversity_polpo()

add_predictors()

add_offset()

Examples

# Query available functions and entries
background <- terra::rast(system.file('extdata/europegrid_50km.tif',
package='ibis.iSDM',mustWork = TRUE))
# Define model
x <- distribution(background)
names(x)

Description

Base R6 class for any biodiversity scenario objects. Serves as container that supplies data and functions to other R6 classes and functions.

Public fields

Methods

Public methods

• BiodiversityScenario$new()

• BiodiversityScenario$print()

• BiodiversityScenario$verify()

• BiodiversityScenario$show()

• BiodiversityScenario$get_projection()

• BiodiversityScenario$get_resolution()

• BiodiversityScenario$get_model()

• BiodiversityScenario$get_limits()

• BiodiversityScenario$rm_limits()

• BiodiversityScenario$get_predictor_names()

• BiodiversityScenario$get_timeperiod()

• BiodiversityScenario$get_constraints()

• BiodiversityScenario$rm_constraints()

• BiodiversityScenario$get_threshold()

• BiodiversityScenario$get_thresholdvalue()

• BiodiversityScenario$apply_threshold()

• BiodiversityScenario$set_predictors()

• BiodiversityScenario$set_constraints()

• BiodiversityScenario$get_simulation()

• BiodiversityScenario$set_simulation()

• BiodiversityScenario$get_predictors()

• BiodiversityScenario$rm_predictors()

• BiodiversityScenario$get_data()

• BiodiversityScenario$rm_data()

• BiodiversityScenario$set_data()

• BiodiversityScenario$set_latent()

• BiodiversityScenario$get_latent()

• BiodiversityScenario$rm_latent()

• BiodiversityScenario$plot()

• BiodiversityScenario$plot_threshold()

• BiodiversityScenario$plot_migclim()

• BiodiversityScenario$plot_animation()

• BiodiversityScenario$plot_relative_change()

• BiodiversityScenario$summary()

• BiodiversityScenario$summary_beforeafter()

• BiodiversityScenario$plot_scenarios_slope()

• BiodiversityScenario$calc_scenarios_slope()

• BiodiversityScenario$mask()

• BiodiversityScenario$get_centroid()

• BiodiversityScenario$save()

• BiodiversityScenario$clone()

Method new()

Initializes the object and creates an empty list

Usage

BiodiversityScenario$new()

Returns

NULL

Method print()

Print the names and properties of all scenarios.

Usage

BiodiversityScenario$print()

Returns

A message on screen

Method verify()

Verify that set Model exist and check self-validity

Usage

BiodiversityScenario$verify()

Returns

Invisible

Method show()

Show the name of the Model

Usage

BiodiversityScenario$show()

Returns

Model objectname

Method get_projection()

Get projection of the projection.

Usage

BiodiversityScenario$get_projection()

Returns

A sf object with the geographic projection

Method get_resolution()

Get resultion of the projection.

Usage

BiodiversityScenario$get_resolution()

Returns

A numeric indication of the resolution.

Method get_model()

Get the actual model used for projection

Usage

BiodiversityScenario$get_model(copy = FALSE)

Arguments

Returns

A DistributionModel object.

Method get_limits()

Get provided projection limits if set.

Usage

BiodiversityScenario$get_limits()

Returns

A sf object or NULL.

Method rm_limits()

Remove current limits.

Usage

BiodiversityScenario$rm_limits()

Returns

Invisible

Method get_predictor_names()

Get names of predictors for scenario object.

Usage

BiodiversityScenario$get_predictor_names()

Returns

A character vector with the names.

Method get_timeperiod()

Get time period of projection.

Usage

BiodiversityScenario$get_timeperiod(what = "range")

Arguments

Returns

A time period from start to end.

Method get_constraints()

Get constrains for model

Usage

BiodiversityScenario$get_constraints()

Returns

A list with the constraints within the scenario.

Method rm_constraints()

Remove contraints from model

Usage

BiodiversityScenario$rm_constraints()

Returns

Invisible

Method get_threshold()

Get thresholds if specified.

Usage

BiodiversityScenario$get_threshold()

Returns

A list with method and value for the threshold.

Method get_thresholdvalue()

Duplicate function for internal consistency to return threshold

Usage

BiodiversityScenario$get_thresholdvalue()

Returns

A list with method and value for the threshold.

Method apply_threshold()

Apply a new threshold to the projection.

Usage

BiodiversityScenario$apply_threshold(tr = new_waiver())

Arguments

Returns

This object.

Method set_predictors()

Set new predictors to this object.

Usage

BiodiversityScenario$set_predictors(x)

Arguments

Returns

This object.

Method set_constraints()

Set new constrains

Usage

BiodiversityScenario$set_constraints(x)

Arguments

Returns

This object.

Method get_simulation()

Get simulation options and parameters if gound

Usage

BiodiversityScenario$get_simulation()

Returns

A list with the parameters.

Method set_simulation()

Set simulation objects.

Usage

BiodiversityScenario$set_simulation(x)

Arguments

Returns

This object.

Method get_predictors()

Get Predictors from the object.

Usage

BiodiversityScenario$get_predictors()

Returns

A predictor dataset.

Method rm_predictors()

Remove predictors from the object.

Usage

BiodiversityScenario$rm_predictors(names)

Arguments

Returns

This object.

Method get_data()

Get scenario predictions or any other data

Usage

BiodiversityScenario$get_data(what = "scenarios")

Arguments

Returns

This object.

Method rm_data()

Remove scenario predictions

Usage

BiodiversityScenario$rm_data()

Arguments

Returns

Invisible

Method set_data()

Set new data in object.

Usage

BiodiversityScenario$set_data(x)

Arguments

Returns

This object.

Method set_latent()

Adding latent factors to the object.

Usage

BiodiversityScenario$set_latent(latent)

Arguments

Returns

This object.

Method get_latent()

Get latent factors if found in object.

Usage

BiodiversityScenario$get_latent()

Returns

A list with the latent settings

Method rm_latent()

Remove latent factors if found in object.

Usage

BiodiversityScenario$rm_latent()

Returns

This object.

Method plot()

Plot the predictions made here.

Usage

BiodiversityScenario$plot(what = "suitability", which = NULL, ...)

Arguments

Returns

A graphical representation

Method plot_threshold()

Convenience function to plot thresholds if set

Usage

BiodiversityScenario$plot_threshold(which = NULL)

Arguments

Returns

A graphical representation

Method plot_migclim()

Plot Migclim results if existing.

Usage

BiodiversityScenario$plot_migclim()

Returns

A graphical representation

Method plot_animation()

Plot animation of scenarios if possible

Usage

BiodiversityScenario$plot_animation(what = "suitability", fname = NULL)

Arguments