Package 'flexsdm'

Description

A data set containing localities and environmental condition of an Abies (fir tree) species in California, USA

Usage

abies

Format

A tibble object with 5000 rows and 10 variables:

ID

presences and absences records ID

pr_ab

presence and absences denoted by 1 and 0 respectively

x y

columns with coordinates in Albers Equal Area Conic coordinate system

from column aet to landform

columns with values for environmental variables at each locality

...

Examples

require(dplyr)
data("abies")
abies

Description

A data set containing environmental conditions of background points

Usage

backg

Format

A tibble object with 5000 rows and 10 variables:

pr_ab

background point denoted by 0

x y

columns with geographical coordinates

from column aet to landform

columns with values of environmental variables at coordinate locations

...

Examples

require(dplyr)
data("backg")
backg

Description

This function offers different methods to define the calibration area. The output could be used with other flexsdm functions like sample_backgroud, sample_pseudoabs, and sdm_predict, among others

Usage

calib_area(data, x, y, method, groups = NULL, crs = NULL)

Arguments

Value

A SpatVector

Examples

data("spp")
sp1 <- spp[spp$species == "sp1" & spp$pr_ab == 1, ]
clusters <- terra::vect(system.file("external/clusters.shp", package = "flexsdm"))

# Calibration area: buffer of 40 km around the records
ca_toy <- calib_area(
  data = sp1,
  x = "x",
  y = "y",
  method = c("buffer", width = 40000),
  crs = terra::crs(clusters)
)
ca_toy


require(terra)
require(dplyr)
data("spp")
clusters <- system.file("external/clusters.shp", package = "flexsdm")
clusters <- terra::vect(clusters)


single_spp <-
  spp %>%
  dplyr::filter(species == "sp1") %>%
  dplyr::filter(pr_ab == 1) %>%
  dplyr::select(-pr_ab)


plot(clusters)
points(single_spp[-1], col = "red")
crs(clusters, proj = TRUE) # coordinate reference system (CRS) used for this points database
# note that the unit of this CRS is in m, consequently the buffer width
# will be interpreted in m too

# buffer method
ca_1 <- calib_area(
  data = single_spp,
  x = "x",
  y = "y",
  method = c("buffer", width = 40000),
  crs = crs(clusters)
)
plot(ca_1)
points(single_spp[, 2:3], pch = 19, cex = 0.5)

# mcp method
ca_2 <- calib_area(
  data = single_spp,
  x = "x",
  y = "y",
  method = "mcp",
  crs = crs(clusters)
)
plot(ca_2)
points(single_spp[, 2:3], pch = 19, cex = 0.5)

# mcp method for different groups
single_spp <- single_spp %>% mutate(groups = ifelse(x > 150000, "a", "b"))

plot(single_spp[, 2:3], pch = 19, col = "blue")
points(single_spp[single_spp$groups == "a", 2:3], col = "red", pch = 19)
points(single_spp[, 2:3])

ca_2.1 <- calib_area(
  data = single_spp,
  x = "x",
  y = "y",
  method = c("mcp"),
  crs = crs(clusters),
  groups = "groups"
)
plot(ca_2.1)
points(single_spp[, 2:3], pch = 19, cex = 0.5)

# bmcp method
ca_3 <- calib_area(
  data = single_spp,
  x = "x",
  y = "y",
  method = c("bmcp", width = 30000),
  crs = crs(clusters)
)
plot(ca_3)
points(single_spp[, 2:3], pch = 19, cex = 0.5)

# bmcp method for different groups
ca_3.1 <- calib_area(
  data = single_spp,
  x = "x",
  y = "y",
  method = c("bmcp", width = 30000),
  crs = crs(clusters),
  groups = "groups"
)
plot(ca_3.1)
points(single_spp[, 2:3], pch = 19, cex = 0.5)

# mask method
plot(clusters)
names(clusters)

ca_3.1 <- calib_area(
  data = single_spp,
  x = "x",
  y = "y",
  method = c("mask", clusters, "clusters"),
)
plot(ca_3.1)
points(single_spp[, 2:3], pch = 19, cex = 0.5, col = "red")

Description

Collinearity reduction of predictor variables

Usage

correct_colinvar(
  env_layer,
  method,
  proj = NULL,
  save_proj = NULL,
  restric_to_region = NULL,
  restric_pca_proj = FALSE,
  maxcell = NULL,
  based_on_points = FALSE,
  data = NULL,
  x = NULL,
  y = NULL
)

Arguments

Details

In the case of having environmental variables for the current conditions and other time periods (future or present), it is recommended to perform the PCA analysis with the current environmental condition and project the PCA for the other time periods. To do so, it is necessary to use “proj” argument. Path to a folder (e.g., projections) that contains sub-folders for the different projection scenarios (e.g., years and emissions). Within each sub-folder must be stored single or multiband rasters with the environmental variables.

For example:

C:/Users/my_pc/projections/
|– MRIESM_2050_ssp126
| |– var1.tif
| |– var2.tif
| '– var3.tif
|– MRIESM_2080_ssp585
| |– var1.tif
| |– var2.tif
| '– var3.tif
'– UKESM_2050_ssp370
|– var1.tif
|– var2.tif
'– var3.tif

If pca method is run with time projections, correct_colinvar function will create the Projection_PCA folder (in the folder given in the save_proj argument, or in the temporary directory if save_proj is NULL; the exact path is in the proj element returned by the function) with the same system of sub-folders and multiband raster with the principal components (pcs.tif)

C:/Users/my_pc/Projection_PCA/
|– MRIESM_2050_ssp126
| '– pcs.tif # a multiband tif with principal components
|– MRIESM_2080_ssp585
| '– pcs.tif
'– UKESM_2050_ssp370
'– pcs.tif

Perform collinearity reduction based on points

Evaluating collinearity based on all environmental conditions of a calibration area or study area could yield different results than evaluating collinearity based on points used to construct the models. If you want to perform collinearity reduction based on species points data, it is strongly recommended to use all the point data used for modeling (i.e., presence + absence or presence + pseudo-absence/background points).

Value

#' If 'pearson', returns a list with the following elements:

• cor_table: a matrix object with pairwise correlation values of the environmental variables

• cor_variables: a list object with the same length of the number of environmental values containing the pairwise relations that exceeded the correlation threshold for each one of the environmental variables

If 'vif' method, returns a list with the following elements:

• env_layer: a SpatRaster object with selected environmental variables

• removed_variables: a character vector with removed environmental variables

• vif_table: a data frame with VIF values for all environmental variables

If 'pca' method, returns a list with the following elements:

• env_layer: SpatRaster with scores of selected principal component (PC) that sum up 95% of the whole variation or original environmental variables

• coefficients: a matrix with the coefficient of principal component (PC) for predictors

• cumulative_variance: a tibble with the cumulative variance explained in selected principal component (PC)

If 'fa' method, returns a list with the following elements:

• env_layer: SpatRaster with scores of selected variables due to correlation to factors.

• number_factors: number of factors selected according to the Broken-Stick criteria,

• removed_variables: removed variables,

• uniqueness: uniqueness of each environmental variable according to the factorial analysis,

• loadings: environmental variables loadings in each of the chosen factors

Examples

# Toy raster: coarser resolution to keep this example fast
somevar <- terra::rast(system.file("external/somevar.tif", package = "flexsdm"))
somevar <- terra::aggregate(somevar, fact = 6)

# Perform Pearson collinearity control
var <- correct_colinvar(env_layer = somevar, method = c("pearson", th = "0.7"))
var$cor_table
var$cor_variables

# Perform VIF collinearity control
var <- correct_colinvar(env_layer = somevar, method = c("vif", th = "8"))
var$vif_table


require(terra)
require(dplyr)

somevar <- system.file("external/somevar.tif", package = "flexsdm")
somevar <- terra::rast(somevar)

# Perform pearson collinearity control
var <- correct_colinvar(env_layer = somevar, method = c("pearson", th = "0.7"))
var$cor_table
var$cor_variables

# For all correct_colinvar methods it is possible to take a sample or raster to reduce memory
var <- correct_colinvar(env_layer = somevar, method = c("pearson", th = "0.7"), maxcell = 10000)
var$cor_table
var$cor_variables

# Perform vif collinearity control
var <- correct_colinvar(env_layer = somevar, method = c("vif", th = "8"))
var$env_layer
var$removed_variables
var$vif_table

# Perform pca collinearity control
var <- correct_colinvar(env_layer = somevar, method = c("pca"))
plot(var$env_layer)
var$env_layer
var$coefficients
var$cumulative_variance


# Perform pca collinearity control with different projections
## Below will be created a set of folders to simulate the structure of the
## directory where environmental variables are stored for different scenarios
dir_sc <- file.path(tempdir(), "projections")
dir.create(dir_sc)
dir_sc <- file.path(dir_sc, c("scenario_1", "scenario_2"))
sapply(dir_sc, dir.create)

somevar <-
  system.file("external/somevar.tif", package = "flexsdm")
somevar <- terra::rast(somevar)

terra::writeRaster(somevar, file.path(dir_sc[1], "somevar.tif"), overwrite = TRUE)
terra::writeRaster(somevar, file.path(dir_sc[2], "somevar.tif"), overwrite = TRUE)

## Perform pca with projections
dir_w_proj <- dirname(dir_sc[1])
dir_w_proj
var <- correct_colinvar(env_layer = somevar, method = "pca", proj = dir_w_proj)
var$env_layer
var$coefficients
var$cumulative_variance
var$proj


# Perform fa colinearity control
var <- correct_colinvar(env_layer = somevar, method = c("fa"))
var$env_layer
var$number_factors
var$removed_variables
var$uniqueness
var$loadings

## %######################################################%##
#                                                          #
####            Other option to perform PCA             ####
####      considering cell restricted to a region       ####
#                                                          #
## %######################################################%##
data("abies")

# Define a calibration area
abies2 <- abies %>%
  dplyr::select(x, y, pr_ab) %>%
  dplyr::filter(pr_ab == 1)

plot(somevar[[1]])
points(abies2[-3])
ca <- calib_area(abies2, x = "x", y = "y", method = c("mcp"), crs = crs(somevar))
plot(ca, add = TRUE)

# Full geographical range to perform PCA
pca_fr <- correct_colinvar(
  env_layer = somevar,
  method = c("pca"),
  maxcell = NULL,
  restric_to_region = NULL,
  restric_pca_proj = FALSE
)

# Perform PCA only with cell delimited by polygon used in restric_to_region
pca_rr <- correct_colinvar(
  env_layer = somevar,
  method = c("pca"),
  maxcell = NULL,
  restric_to_region = ca,
  restric_pca_proj = FALSE
)

# Perform and predicted PCA only with cell delimited by polygon used in restric_to_region
pca_rrp <- correct_colinvar(
  env_layer = somevar,
  method = c("pca"),
  maxcell = NULL,
  restric_to_region = ca,
  restric_pca_proj = TRUE
)

plot(pca_fr$env_layer) # PCA with all cells
plot(pca_rr$env_layer) # PCA with calibration area cell but predicted for entire region
plot(pca_rrp$env_layer) # PCA performed and predicted for cells within calibration area (ca)


## %######################################################%##
#                                                          #
####       Use correct_colinvar with points data        ####
#                                                          #
## %######################################################%##
data("abies")

# Presence-absence database
abies2 <- abies %>%
  dplyr::select(x, y, pr_ab)

# Perform collinearity control
# Pearson
correct_colinvar(
  env_layer = somevar,
  method = c("pearson", th = "0.6"),
  based_on_points = TRUE,
  data = abies2,
  x = "x",
  y = "y"
)

# VIF
correct_colinvar(
  env_layer = somevar,
  method = c("vif", th = "8"),
  based_on_points = TRUE,
  data = abies2,
  x = "x",
  y = "y"
)

# PCA
correct_colinvar(
  env_layer = somevar,
  method = c("pca"),
  based_on_points = TRUE,
  data = abies2,
  x = "x",
  y = "y"
)

# FA
correct_colinvar(
  env_layer = somevar,
  method = "fa",
  based_on_points = TRUE,
  data = abies2,
  x = "x",
  y = "y"
)

Description

Calculate data to construct Partial dependence surface plot (i.e., bivariate dependence plot) for two predictor set

Usage

data_bpdp(
  model,
  predictors,
  resolution = 50,
  training_data = NULL,
  training_boundaries = NULL,
  projection_data = NULL,
  clamping = FALSE
)

Arguments

Value

A list with two tibbles "pdpdata" and "resid".

• pspdata: has data to construct partial dependence surface plot, the first two column includes values of the selected environmental variables, the third column with predicted suitability.

• training_boundaries: has data to plot boundaries of training data.

See Also

data_pdp, p_bpdp, p_pdp

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

glm_toy <- fit_glm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec"
)

bpdp_toy <- data_bpdp(
  model = glm_toy$model,
  predictors = c("aet", "cwd"),
  resolution = 10,
  training_boundaries = "rectangle",
  training_data = abies_toy
)
names(bpdp_toy)
bpdp_toy$pspdata


library(terra)
library(dplyr)

somevar <- system.file("external/somevar.tif", package = "flexsdm")
somevar <- terra::rast(somevar) # environmental data
names(somevar) <- c("aet", "cwd", "tmx", "tmn")
data(abies)

abies2 <- abies %>%
  select(x, y, pr_ab)

abies2 <- sdm_extract(abies2,
  x = "x",
  y = "y",
  env_layer = somevar
)
abies2 <- part_random(abies2,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 5)
)

m <- fit_svm(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmx", "tmn"),
  partition = ".part",
  thr = c("max_sens_spec")
)

df <- data_bpdp(
  model = m$model,
  predictors = c("aet", "cwd"),
  resolution = 50,
  projection_data = somevar,
  training_boundaries = "rectangle",
  training_data = abies2,
  clamping = TRUE
)

df
names(df)
df$pspdata
df$training_boundaries

# see p_bpdp to construct partial dependence plot with ggplot2

Description

Calculate data to construct partial dependence plots for a given predictor

Usage

data_pdp(
  model,
  predictors,
  resolution = 50,
  resid = FALSE,
  training_data = NULL,
  projection_data = NULL,
  clamping = FALSE
)

Arguments

Value

A list with two tibbles "pdpdata" and "resid".

• pdpdata: has data to construct partial dependence plots, the first column includes values of the selected environmental variable, the second column with predicted suitability, and the third column with range type, with two values Training and Projecting, referring to suitability calculated within and outside the range of training conditions. Third column is only returned if "projection_data" argument is used

• resid: has data to plot residuals. The first column includes values of the selected environmental variable and the second column with predicted suitability.

See Also

data_bpdp, p_bpdp, p_pdp

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

glm_toy <- fit_glm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec"
)

pdp_toy <- data_pdp(
  model = glm_toy$model,
  predictors = "aet",
  resolution = 10,
  training_data = abies_toy
)
pdp_toy


library(terra)
library(dplyr)

somevar <- system.file("external/somevar.tif", package = "flexsdm")
somevar <- terra::rast(somevar) # environmental data
names(somevar) <- c("aet", "cwd", "tmx", "tmn")
data(abies)

abies2 <- abies %>%
  select(x, y, pr_ab)

abies2 <- sdm_extract(abies2,
  x = "x",
  y = "y",
  env_layer = somevar
)
abies2 <- part_random(abies2,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 5)
)

svm_t1 <- fit_svm(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmx", "tmn"),
  partition = ".part",
  thr = c("max_sens_spec")
)

df <- data_pdp(
  model = svm_t1$model,
  predictors = c("aet"),
  resolution = 100,
  resid = TRUE,
  projection_data = somevar,
  training_data = abies2,
  clamping = FALSE
)

df
names(df)
df$pdpdata
df$resid

plot(df$pdpdata[1:2], type = "l")
points(df$resid[1:2], cex = 0.5)

# see p_pdp to construct partial dependence plot with ggplot2

Description

This function performs different methods for detecting outliers in species distribution data based on the environmental conditions of occurrences. Some methods need presence and absence data (e.g. Two-class Support Vector Machine and Random Forest) while other only use presences (e.g. Reverse Jackknife, Box-plot, and Random Forest outliers) . Outlier detection can be a useful procedure in occurrence data cleaning (Chapman 2005, Liu et al., 2018).

Usage

env_outliers(data, x, y, pr_ab, id, env_layer)

Arguments

Details

This function will apply outliers detection methods to occurrence data. Box-plot and Reverse Jackknife method will test outliers for each variable individually, if an occurrence behaves as an outlier for at least one variable it will be highlighted as an outlier. If the user uses only presence data, Support Vector Machine and Random Forest Methods will not be performed. Support Vector Machine and Random Forest are performed with default hyper-parameter values. In the case of a species with < 7 occurrences, the function will not perform any methods (i.e. the additional columns will have 0 values); nonetheless, it will return a tibble with the additional columns with 0 and 1. For further information about these methods, see Chapman (2005), Liu et al. (2018), and Velazco et al. (2022).

Value

A tibble object with the same database used in 'data' argument and with seven additional columns, where 1 and 0 denote that a presence was detected or not as outliers

• .out_bxpt: outliers detected with Box-plot method

• .out_jack: outliers detected with Reverse Jackknife method

• .out_svm: outliers detected with Support Vector Machine method

• .out_rf: outliers detected with Random Forest method

• .out_rfout: outliers detected with Random Forest Outliers method

• .out_sum: frequency of a presences records was detected as outliers based on the previews methods (values between 0 and 6).

References

• Chapman, A. D. (2005). Principles and methods of data cleaning: Primary Species and Species- Occurrence Data. version 1.0. Report for the Global Biodiversity Information Facility, Copenhagen. p72. http://www.gbif.org/document/80528

• Liu, C., White, M., & Newell, G. (2018). Detecting outliers in species distribution data. Journal of Biogeography, 45(1), 164 - 176. https://doi.org/10.1111/jbi.13122

• Velazco, S.J.E.; Bedrij, N.A.; Keller, H.A.; Rojas, J.L.; Ribeiro, B.R.; De Marco, P. (2022) Quantifying the role of protected areas for safeguarding the uses of biodiversity. Biological Conservation, xx(xx) xx-xx. https://doi.org/10.1016/j.biocon.2022.109525

Examples

# Toy data: small raster and records of one species to keep this example fast
data("spp")
somevar <- terra::rast(system.file("external/somevar.tif", package = "flexsdm"))
somevar <- terra::aggregate(somevar, fact = 6) # coarser resolution
sp3 <- spp[spp$species == "sp3", ]
sp3$idd <- seq_len(nrow(sp3)) # unique id for each record

outs <- env_outliers(
  data = sp3,
  pr_ab = "pr_ab",
  x = "x",
  y = "y",
  id = "idd",
  env_layer = somevar
)
outs


require(dplyr)
require(terra)
require(ggplot2)

# Environmental variables
somevar <- system.file("external/somevar.tif", package = "flexsdm")
somevar <- terra::rast(somevar)

# Species occurrences
data("spp")
spp
spp1 <- spp %>% dplyr::filter(species == "sp1")

somevar[[1]] %>% plot()
points(spp1 %>% filter(pr_ab == 1) %>% select(x, y), col = "blue", pch = 19)
points(spp1 %>% filter(pr_ab == 0) %>% select(x, y), col = "red", cex = 0.5)

spp1 <- spp1 %>% mutate(idd = 1:nrow(spp1))

# Detect outliers
outs_1 <- env_outliers(
  data = spp1,
  pr_ab = "pr_ab",
  x = "x",
  y = "y",
  id = "idd",
  env_layer = somevar
)

# How many outliers were detected by different methods?
out_pa <- outs_1 %>%
  dplyr::select(starts_with("."), -.out_sum) %>%
  apply(., 2, function(x) sum(x, na.rm = TRUE))
out_pa

# How many outliers were detected by the sum of different methods?
outs_1 %>%
  dplyr::group_by(.out_sum) %>%
  dplyr::count()

# Let explor where are locate records highlighted as outliers
outs_1 %>%
  dplyr::filter(pr_ab == 1, .out_sum > 0) %>%
  ggplot(aes(x, y)) +
  geom_point(aes(col = factor(.out_sum))) +
  facet_wrap(. ~ factor(.out_sum))

# Detect outliers only with presences
outs_2 <- env_outliers(
  data = spp1 %>% dplyr::filter(pr_ab == 1),
  pr_ab = "pr_ab",
  x = "x",
  y = "y",
  id = "idd",
  env_layer = somevar
)

# How many outliers were detected by different methods
out_p <- outs_2 %>%
  dplyr::select(starts_with("."), -.out_sum) %>%
  apply(., 2, function(x) sum(x, na.rm = TRUE))

# How many outliers were detected by the sum of different methods?
outs_2 %>%
  dplyr::group_by(.out_sum) %>%
  dplyr::count()

# Let explor where are locate records highlighted as outliers
outs_2 %>%
  dplyr::filter(pr_ab == 1, .out_sum > 0) %>%
  ggplot(aes(x, y)) +
  geom_point(aes(col = factor(.out_sum))) +
  facet_wrap(. ~ factor(.out_sum))


# Comparison of function outputs when using it with
# presences-absences or only presences data.

bind_rows(out_p, out_pa)
# Because the second case only were used presences, outliers methods
# based in Random Forest (.out_rf) and Support Vector Machines (.out_svm)
# were not performed.

Description

This function constructs Generalized Additive Models using the Ensembles of Small Models (ESM) approach (Breiner et al., 2015, 2018).

Usage

esm_gam(data, response, predictors, partition, thr = NULL, k = 2)

Arguments

Details

This method consists of creating bivariate models with all pair-wise combinations of predictors and perform an ensemble based on the average of suitability weighted by Somers' D metric (D = 2 x (AUC -0.5)). ESM is recommended for modeling species with few occurrences. This function does not allow categorical variables because the use of these types of variables could be problematic when using with few occurrences. For further detail see Breiner et al. (2015, 2018).

This function fits GAM using mgvc package, with Binomial distribution family and thin plate regression spline as a smoothing basis (see ?mgvc::s).

Value

A list object with:

• esm_model: A list with "gam" class object from mgcv package for each bivariate model. This object can be used for predicting an ensemble of small models with the sdm_predict function.

• predictors: A tibble with variables use for modeling.

• performance: Performance metrics (see sdm_eval). Threshold dependent metrics are calculated based on the threshold specified in the argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

References

• Breiner, F. T., Guisan, A., Bergamini, A., & Nobis, M. P. (2015). Overcoming limitations of modelling rare species by using ensembles of small models. Methods in Ecology and Evolution, 6(10), 1210-218. https://doi.org/10.1111/2041-210X.12403

• Breiner, F. T., Nobis, M. P., Bergamini, A., & Guisan, A. (2018). Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution, 9(4), 802-808. https://doi.org/10.1111/2041-210X.12957

See Also

esm_gau, esm_gbm, esm_glm, esm_max, esm_net, and esm_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

esm_toy <- esm_gam(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = NULL,
  k = 3
)
esm_toy$performance


data("abies")
require(dplyr)

# Using k-fold partition method
set.seed(10)
abies2 <- abies %>%
  na.omit() %>%
  group_by(pr_ab) %>%
  dplyr::slice_sample(n = 10) %>%
  group_by()

abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)
abies2

# Without threshold specification and with kfold
esm_gam_t1 <- esm_gam(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin", "ppt_djf", "ppt_jja", "pH", "awc", "depth"),
  partition = ".part",
  thr = NULL
)

esm_gam_t1$esm_model # bivariate model
esm_gam_t1$predictors
esm_gam_t1$performance
esm_gam_t1$performance_part

# Test with rep_kfold partition
abies2 <- abies2 %>% select(-starts_with("."))

set.seed(10)
abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 2)
)
abies2

esm_gam_t2 <- esm_gam(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin", "ppt_djf", "ppt_jja", "pH", "awc", "depth"),
  partition = ".part",
  thr = NULL
)
esm_gam_t2$esm_model # bivariate model
esm_gam_t2$predictors
esm_gam_t2$performance

# Test with other bootstrap
abies2 <- abies2 %>% select(-starts_with("."))

set.seed(10)
abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "boot", replicates = 3, proportion = 0.7)
)
abies2

esm_gam_t3 <- esm_gam(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin", "ppt_djf", "ppt_jja", "pH", "awc", "depth"),
  partition = ".part",
  thr = NULL
)
esm_gam_t3$esm_model # bivariate model
esm_gam_t3$predictors
esm_gam_t3$performance

Description

This function constructs Gaussian Process models using the Ensembles of Small Models (ESM) approach (Breiner et al., 2015, 2018).

Usage

esm_gau(data, response, predictors, partition, thr = NULL, background = NULL)

Arguments

Details

This method consists of creating bivariate models with all the pair-wise combinations of predictors and performs an ensemble based on the average of suitability weighted by Somers' D metric (D = 2 x (AUC -0.5)). ESM is recommended for modeling species with few occurrences. This function does not allow categorical variables because the use of these types of variables could be problematic when using with few occurrences. For further detail see Breiner et al. (2015, 2018).

Value

A list object with:

• esm_model: A list with "graf" class object for each bivariate model. This object can be used for predicting ensembles of small models with sdm_predict function.

• predictors: A tibble with variables use for modeling.

• performance: Performance metric (see sdm_eval). Those threshold dependent metric are calculated based on the threshold specified in the argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

References

• Breiner, F. T., Guisan, A., Bergamini, A., & Nobis, M. P. (2015). Overcoming limitations of modelling rare species by using ensembles of small models. Methods in Ecology and Evolution, 6(10), 1210-218. https://doi.org/10.1111/2041-210X.12403

• Breiner, F. T., Nobis, M. P., Bergamini, A., & Guisan, A. (2018). Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution, 9(4), 802-808. https://doi.org/10.1111/2041-210X.12957

See Also

esm_gam, esm_gbm, esm_glm, esm_max, esm_net, and esm_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

esm_toy <- esm_gau(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = NULL
)
esm_toy$performance


data("abies")
require(dplyr)

# Using k-fold partition method
set.seed(10)
abies2 <- abies %>%
  na.omit() %>%
  group_by(pr_ab) %>%
  dplyr::slice_sample(n = 10) %>%
  group_by()

abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 5)
)
abies2

# Without threshold specification and with kfold
esm_gau_t1 <- esm_gau(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin", "ppt_djf", "ppt_jja", "pH", "awc", "depth"),
  partition = ".part",
  thr = NULL
)

esm_gau_t1$esm_model # bivariate model
esm_gau_t1$predictors
esm_gau_t1$performance
esm_gau_t1$performance_part

Description

This function constructs Generalized Boosted Regression using the Ensembles of Small Models (ESM) approach (Breiner et al., 2015, 2018).

Usage

esm_gbm(
  data,
  response,
  predictors,
  partition,
  thr = NULL,
  n_trees = 100,
  n_minobsinnode = NULL,
  shrinkage = 0.1
)

Arguments

Details

This method consists of creating bivariate models with all the pair-wise combinations of predictors and perform an ensemble based on the average of suitability weighted by Somers' D metric (D = 2 x (AUC -0.5)). ESM is recommended for modeling species with few occurrences. This function does not allow categorical variables because the use of these types of variables could be problematic when using with few occurrences. For further detail see Breiner et al. (2015, 2018).

Value

A list object with:

• esm_model: A list with "gbm" class object from gbm package for each bivariate model. This object can be used for predicting ensembles of small models with sdm_predict function.

• predictors: A tibble with variables use for modeling.

• performance: Performance metrics (see sdm_eval). Threshold dependent metrics are calculated based on the threshold specified in thr argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

References

• Breiner, F. T., Guisan, A., Bergamini, A., & Nobis, M. P. (2015). Overcoming limitations of modelling rare species by using ensembles of small models. Methods in Ecology and Evolution, 6(10), 1210-218. https://doi.org/10.1111/2041-210X.12403

• Breiner, F. T., Nobis, M. P., Bergamini, A., & Guisan, A. (2018). Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution, 9(4), 802-808. https://doi.org/10.1111/2041-210X.12957

See Also

esm_gam, esm_gau, esm_glm, esm_max, esm_net, and esm_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

esm_toy <- esm_gbm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = NULL,
  n_trees = 20,
  n_minobsinnode = 3,
  shrinkage = 0.1
)
esm_toy$performance


data("abies")
require(dplyr)

# Using k-fold partition method
set.seed(10)
abies2 <- abies %>%
  na.omit() %>%
  group_by(pr_ab) %>%
  dplyr::slice_sample(n = 10) %>%
  group_by()

abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 5)
)
abies2

# Without threshold specification and with kfold
esm_gbm_t1 <- esm_gbm(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin", "ppt_djf", "ppt_jja", "pH", "awc", "depth"),
  partition = ".part",
  thr = NULL,
  n_trees = 100,
  n_minobsinnode = NULL,
  shrinkage = 0.1
)

esm_gbm_t1$esm_model # bivariate model
esm_gbm_t1$predictors
esm_gbm_t1$performance
esm_gbm_t1$performance_part

Description

This function constructs Generalized Linear Models using the Ensembles of Small Models (ESM) approach (Breiner et al., 2015, 2018).

Usage

esm_glm(
  data,
  response,
  predictors,
  partition,
  thr = NULL,
  poly = 0,
  inter_order = 0
)

Arguments

Details

This method consists of creating bivariate models with all the pair-wise combinations of predictors and perform an ensemble based on the average of suitability weighted by Somers' D metric (D = 2 x (AUC -0.5)). ESM is recommended for modeling species with few occurrences. This function does not allow categorical variables because the use of these types of variables could be problematic when using with few occurrences. For further detail see Breiner et al. (2015, 2018).

Value

A list object with:

• esm_model: A list with "glm" class object from stats package for each bivariate model. This object can be used for predicting ensembles of small models with sdm_predict function.

• predictors: A tibble with variables use for modeling.

• performance: Performance metric (see sdm_eval). Those threshold dependent metric are calculated based on the threshold specified in thr argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

References

• Breiner, F. T., Guisan, A., Bergamini, A., & Nobis, M. P. (2015). Overcoming limitations of modelling rare species by using ensembles of small models. Methods in Ecology and Evolution, 6(10), 1210-218. https://doi.org/10.1111/2041-210X.12403

• Breiner, F. T., Nobis, M. P., Bergamini, A., & Guisan, A. (2018). Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution, 9(4), 802-808. https://doi.org/10.1111/2041-210X.12957

See Also

esm_gam, esm_gau, esm_gbm, esm_max, esm_net, and esm_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

esm_toy <- esm_glm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = NULL,
  poly = 1,
  inter_order = 0
)
esm_toy$performance


data("abies")
require(dplyr)

# Using k-fold partition method
set.seed(10)
abies2 <- abies %>%
  na.omit() %>%
  group_by(pr_ab) %>%
  dplyr::slice_sample(n = 10) %>%
  group_by()

abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 5)
)
abies2

# Without threshold specification and with kfold
esm_glm_t1 <- esm_glm(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin", "ppt_djf", "ppt_jja", "pH", "awc", "depth"),
  partition = ".part",
  thr = NULL,
  poly = 0,
  inter_order = 0
)

esm_glm_t1$esm_model # bivariate model
esm_glm_t1$predictors
esm_glm_t1$performance
esm_glm_t1$performancePart

Description

This function constructs Maxent Models using the Ensemble of Small Model (ESM) approach (Breiner et al., 2015, 2018).

Usage

esm_max(
  data,
  response,
  predictors,
  partition,
  thr = NULL,
  background = NULL,
  clamp = TRUE,
  classes = "default",
  pred_type = "cloglog",
  regmult = 2.5
)

Arguments

Details

This method consists of creating bivariate models with all the pair-wise combinations of predictors and perform an ensemble based on the average of suitability weighted by Somers' D metric (D = 2 x (AUC -0.5)). ESM is recommended for modeling species with few occurrences. This function does not allow categorical variables because the use of these types of variables could be problematic when using with few occurrences. For further detail see Breiner et al. (2015, 2018). This function use a default regularization multiplier equal to 2.5 (see Breiner et al., 2018)

When the argument “classes” is set as default MaxEnt will use different features combination depending of the number of presences (np) with the follow rule: if np < 10 classes = "l", if np between 10 and 15 classes = "lq", if np between 15 and 80 classes = "lqh", and if np >= 80 classes = "lqph"

When presence-absence (or presence-pseudo-absence) data are used in data argument in addition to background points, the function will fit models with presences and background points and validate with presences and absences. This procedure makes maxent comparable to other presences-absences models (e.g., random forest, support vector machine). If only presences and background points data are used, function will fit and validate model with presences and background data. If only presence-absences are used in data argument and without background, function will fit model with the specified data (not recommended).

Value

A list object with:

• esm_model: A list with "maxnet" class object from maxnet package for each bivariate model. This object can be used for predicting ensembles of small models with sdm_predict function.

• predictors: A tibble with variables use for modeling.

• performance: Performance metrics (see sdm_eval). Those threshold dependent metric are calculated based on the threshold specified in the argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

References

• Breiner, F. T., Guisan, A., Bergamini, A., & Nobis, M. P. (2015). Overcoming limitations of modelling rare species by using ensembles of small models. Methods in Ecology and Evolution, 6(10), 1210-218. https://doi.org/10.1111/2041-210X.12403

• Breiner, F. T., Nobis, M. P., Bergamini, A., & Guisan, A. (2018). Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution, 9(4), 802-808. https://doi.org/10.1111/2041-210X.12957

See Also

esm_gam, esm_gau, esm_gbm, esm_glm, esm_net, and esm_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

# Use the same records as background points (toy example only)
backg_toy <- abies_toy
backg_toy$pr_ab <- 0

esm_toy <- esm_max(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = NULL,
  background = backg_toy,
  clamp = TRUE,
  classes = "lq",
  pred_type = "cloglog",
  regmult = 1
)
esm_toy$performance


data("abies")
data("backg")
require(dplyr)

# Using k-fold partition method
set.seed(10)
abies2 <- abies %>%
  na.omit() %>%
  group_by(pr_ab) %>%
  dplyr::slice_sample(n = 10) %>%
  group_by()

abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 2)
)
abies2

set.seed(10)
backg2 <- backg %>%
  na.omit() %>%
  group_by(pr_ab) %>%
  dplyr::slice_sample(n = 100) %>%
  group_by()

backg2 <- part_random(
  data = backg2,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 2)
)
backg2

# Without threshold specification and with kfold
esm_max_t1 <- esm_max(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin", "ppt_djf", "ppt_jja", "pH", "awc", "depth"),
  partition = ".part",
  thr = NULL,
  background = backg2,
  clamp = TRUE,
  classes = "default",
  pred_type = "cloglog",
  regmult = 1
)

esm_max_t1$esm_model # bivariate model
esm_max_t1$predictors
esm_max_t1$performance
esm_max_t1$performance_part

Description

This function constructs Neural Networks using the Ensembles of Small Models (ESM) approach (Breiner et al., 2015, 2018).

Usage

esm_net(data, response, predictors, partition, thr = NULL, size = 2, decay = 0)

Arguments

Details

This method consists of creating bivariate models with all the pair-wise combinations of predictors and perform an ensemble based on the average of suitability weighted by Somers' D metric (D = 2 x (AUC -0.5)). ESM is recommended for modeling species with few occurrences. This function does not allow categorical variables because the use of these types of variables could be problematic when using with few occurrences. Further detail see Breiner et al. (2015, 2018).

Value

A list object with:

• esm_model: A list with "nnet" class object from nnet package for each bivariate model. This object can be used for predicting ensemble of small model with sdm_predict function.

• predictors: A tibble with variables use for modeling.

• performance: Performance metric (see sdm_eval). Those threshold dependent metric are calculated based on the threshold specified in thr argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

References

• Breiner, F. T., Guisan, A., Bergamini, A., & Nobis, M. P. (2015). Overcoming limitations of modelling rare species by using ensembles of small models. Methods in Ecology and Evolution, 6(10), 1210-218. https://doi.org/10.1111/2041-210X.12403

• Breiner, F. T., Nobis, M. P., Bergamini, A., & Guisan, A. (2018). Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution, 9(4), 802-808. https://doi.org/10.1111/2041-210X.12957

See Also

esm_gam, esm_gau, esm_gbm, esm_glm, esm_max, and esm_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

esm_toy <- esm_net(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = NULL,
  size = 2,
  decay = 1
)
esm_toy$performance


data("abies")
require(dplyr)

# Using k-fold partition method
set.seed(10)
abies2 <- abies %>%
  na.omit() %>%
  group_by(pr_ab) %>%
  dplyr::slice_sample(n = 10) %>%
  group_by()

abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 5)
)
abies2

# Without threshold specification and with kfold
esm_net_t1 <- esm_net(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin", "ppt_djf", "ppt_jja", "pH", "awc", "depth"),
  partition = ".part",
  thr = NULL
)

esm_net_t1$esm_model # bivariate model
esm_net_t1$predictors
esm_net_t1$performance
esm_net_t1$performance_part

Description

This function constructs Support Vector Machine models using the Ensembles of Small Models (ESM) approach (Breiner et al., 2015, 2018).

Usage

esm_svm(
  data,
  response,
  predictors,
  partition,
  thr = NULL,
  sigma = "automatic",
  C = 1
)

Arguments

Details

This method consists of creating bivariate models with all the pair-wise combinations of predictors and perform an ensemble based on the average of suitability weighted by Somers' D metric (D = 2 x (AUC -0.5)). ESM is recommended for modeling species with few occurrences. This function does not allow categorical variables because the use of these types of variables could be problematic when using with few occurrences. Further detail see Breiner et al. (2015, 2018). This function constructs 'C-svc' classification type and uses Radial Basis kernel "Gaussian" function (rbfdot). See details in ksvm

Value

A list object with:

• esm_model: A list with "ksvm" class object from ksvm package for each bivariate model. This object can be used for predicting ensemble of small model with sdm_predict function.

• predictors: A tibble with variables use for modeling.

• performance: Performance metric (see sdm_eval). Those threshold dependent metric are calculated based on the threshold specified in thr argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

References

• Breiner, F. T., Guisan, A., Bergamini, A., & Nobis, M. P. (2015). Overcoming limitations of modelling rare species by using ensembles of small models. Methods in Ecology and Evolution, 6(10), 1210-218. https://doi.org/10.1111/2041-210X.12403

• Breiner, F. T., Nobis, M. P., Bergamini, A., & Guisan, A. (2018). Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution, 9(4), 802-808. https://doi.org/10.1111/2041-210X.12957

See Also

esm_gam, esm_gau, esm_gbm, esm_glm, esm_max,, and esm_net.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

esm_toy <- esm_svm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = NULL,
  sigma = 0.1,
  C = 2
)
esm_toy$performance


data("abies")
require(dplyr)

# Using k-fold partition method
set.seed(10)
abies2 <- abies %>%
  na.omit() %>%
  group_by(pr_ab) %>%
  dplyr::slice_sample(n = 10) %>%
  group_by()

abies2 <- part_random(
  data = abies2,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 5)
)
abies2

# Without threshold specification and with kfold
esm_svm_t1 <- esm_svm(
  data = abies2,
  response = "pr_ab",
  predictors = c(
    "aet", "cwd", "tmin", "ppt_djf", "ppt_jja",
    "pH", "awc", "depth"
  ),
  partition = ".part",
  thr = NULL
)

esm_svm_t1$esm_model # bivariate model
esm_svm_t1$predictors
esm_svm_t1$performance
esm_svm_t1$performance_part

Description

Measure extrapolation comparing environmental data used for modeling calibration and area for model projection. This function use the Shape metric proposed by Velazco et al., 2023 (doi:10.1111/ecog.06992)

Usage

extra_eval(
  training_data,
  pr_ab,
  projection_data,
  metric = "mahalanobis",
  univar_comb = FALSE,
  aggreg_factor = 1
)

Arguments

Details

This function measure model extrapolation base on the Shape metric (Velazco et al., 2023; doi:10.1111/ecog.06992). Shape is a model-agnostic approach that calculates the extrapolation degree for a given projection data point by its multivariate distance to the nearest training data point. Such distances are relativized by a factor that reflects the dispersion of the training data in environmental space. Distinct from other approaches (e.g., MESS-Multivariate Environmental Similarity Surfaces, EO-Environmental Overlap, MOP-Mobility-Oriented Parity, EXDET-Extrapolation Detection, or AOA-Area of Applicability), Shape incorporates an adjustable threshold to control the binary discrimination between acceptable and unacceptable extrapolation degrees (see extra_truncate).

See this vignette at flexsdm website for further details about Shape metric, model truncation, and tools to explore model extrapolation.

Value

A SpatRaster or tibble object with extrapolation values measured by Shape metric. Also it is possible estimate univariate and combinatorial extrapolation metric (see 'univar_comb' argument).

References

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

See Also

extra_truncate, p_extra, p_pdp, p_bpdp

Examples

# Toy data: small raster and records of one species to keep this example fast
data("spp")
somevar <- terra::rast(system.file("external/somevar.tif", package = "flexsdm"))
somevar <- terra::aggregate(somevar, fact = 6) # coarser resolution
sp3 <- spp[spp$species == "sp3", ]
sp3 <- sdm_extract(data = sp3, x = "x", y = "y", env_layer = somevar)

extr <- extra_eval(
  training_data = sp3,
  pr_ab = "pr_ab",
  projection_data = somevar,
  metric = "mahalanobis"
)
extr


require(dplyr)
require(terra)

data(spp)
f <- system.file("external/somevar.tif", package = "flexsdm")
somevar <- terra::rast(f)
names(somevar) <- c("aet", "cwd", "tmx", "tmn")


spp$species %>% unique()
sp <- spp %>%
  dplyr::filter(species == "sp3", pr_ab == 1) %>%
  dplyr::select(x, y, pr_ab)

# Calibration area based on some criterion such as dispersal ability
ca <- calib_area(sp,
  x = "x", y = "y",
  method = c("bmcp", width = 50000),
  crs = crs(somevar)
)

plot(somevar[[1]])
points(sp)
plot(ca, add = TRUE)


# Sampling pseudo-absences
set.seed(10)
psa <- sample_pseudoabs(
  data = sp,
  x = "x",
  y = "y",
  n = nrow(sp) * 2,
  method = "random",
  rlayer = somevar,
  calibarea = ca
)

# Merge presences and absences databases to get a complete calibration data
sp_pa <- dplyr::bind_rows(sp, psa)
sp_pa

# Get environmental condition of calibration area
sp_pa_2 <- sdm_extract(
  data = sp_pa,
  x = "x",
  y = "y",
  env_layer = somevar
)
sp_pa_2

# Measure degree of extrapolation based on Mahalanobis and
# for a projection area based on a SpatRaster object
extr <-
  extra_eval(
    training_data = sp_pa_2,
    projection_data = somevar,
    pr_ab = "pr_ab",
    aggreg_factor = 1,
    metric = "mahalanobis"
  )
plot(extr, main = "Extrapolation pattern")


# Let's fit, predict and truncate a model with extra_truncate
sp_pa_2 <- part_random(
  data = sp_pa_2,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 5)
)

a_model <- fit_glm(
  data = sp_pa_2,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmx", "tmn"),
  partition = ".part",
  thr = c("max_sorensen")
)

predsuit <- sdm_predict(
  models = a_model,
  pred = somevar,
  thr = "max_sorensen"
)
predsuit # list with a raster with two layer
plot(predsuit[[1]])

# Truncate a model based on a given value of extrapolation
# using 'extra_truncate' function
oldpar <- par(mfrow = c(1, 2))
plot(extr, main = "Extrapolation")
plot(predsuit[[1]][[1]], main = "Suitability")
par(oldpar) # restore graphical parameters

predsuit_2 <- extra_truncate(
  suit = predsuit[[1]],
  extra = extr,
  threshold = c(50, 100, 200)
)
predsuit_2 # a list of continuous and binary models with
# different truncated at different extrapolation thresholds

plot(predsuit_2$`50`)
plot(predsuit_2$`100`)
plot(predsuit_2$`200`)


## %######################################################%##
####        Measure degree of extrapolation for         ####
####        projection area based on data.frame         ####
## %######################################################%##

extr_df <-
  extra_eval(
    training_data = sp_pa_2,
    projection_data = as.data.frame(somevar, xy = TRUE),
    pr_ab = "pr_ab",
    aggreg_factor = 1,
    metric = "mahalanobis"
  )
extr_df
# see 'p_extra()' to explore extrapolation or suitability pattern in the
# environmental and/or geographical space

## %######################################################%##
####             Explore Shape metric with              ####
####     univariate and combinatorial extrapolation     ####
## %######################################################%##
extr <-
  extra_eval(
    training_data = sp_pa_2,
    projection_data = somevar,
    pr_ab = "pr_ab",
    aggreg_factor = 1,
    metric = "mahalanobis",
    univar_comb = TRUE
  )

extr
plot(extr) # In the second layer, values equal to 1 and 2
# depict univariate and combinatorial extrapolation, respectively

Description

Exclusion of suitability predictions in environmental conditions assumed to be extrapolative.

Usage

extra_truncate(suit, extra, threshold = 50, trunc_value = 0)

Arguments

Details

Exclusion of suitability predictions in environmental conditions assumed to be extrapolative. In this function it is possible to use any metric measuring degree of extrapolation (e.g., MESS-Multivariate Environmental Similarity Surfaces, EO-Environmental Overlap, MOP-Mobility-Oriented Parity, EXDET-Extrapolation Detection, or AOA-Area of Applicability). However, we recommend to use Shape approach (see extra_eval, and Velazco et al., 2023; doi:10.1111/ecog.06992).

This function truncates suitability predictions assigning a given value, generally 0 or NA. Usage trunc_value = NA. Default 0.

To those cells assumed to be extrapolative, i.e., higher than a given threshold of a given extrapolation metric.

See this vignette at flexsdm website for further details about Shape metric, model truncation, and tools to explore model extrapolation.

Value

A SpatRaster object with truncated suitability values

See Also

extra_eval, p_extra, p_pdp, p_bpdp

Examples

# Toy data: small raster and records of one species to keep this example fast
data("spp")
somevar <- terra::rast(system.file("external/somevar.tif", package = "flexsdm"))
somevar <- terra::aggregate(somevar, fact = 6) # coarser resolution
sp3 <- spp[spp$species == "sp3", ]
sp3 <- sdm_extract(data = sp3, x = "x", y = "y", env_layer = somevar)

# Extrapolation (Shape metric) in the projection area
extr <- extra_eval(
  training_data = sp3,
  pr_ab = "pr_ab",
  projection_data = somevar,
  metric = "mahalanobis"
)

# Any suitability layer can be truncated; here, a toy layer rescaled to 0-1
suit <- somevar[[1]]
suit <- suit / terra::global(suit, "max", na.rm = TRUE)[[1]]
names(suit) <- "suit"

# Suitability is set to 0 where extrapolation is higher than the threshold
suit_trunc <- extra_truncate(
  suit = suit,
  extra = extr,
  threshold = 50,
  trunc_value = 0
)
suit_trunc # one raster for each threshold value

# see more examples in extra_eval function

Description

Fit and validate Domain models

Usage

fit_dom(
  data,
  response,
  predictors,
  predictors_f = NULL,
  partition = NULL,
  thr = NULL
)

Arguments

Details

This function fits and validates Domain models. The Domain model is a simple model that uses the Gower distance to calculate environmental similarity between the presence data and test data (Carpenter et al., 1993). Gower range of values area based on presences data. Gower distance are transformed to max(0, 1 - Gower). This involves subtracting the distance from 1 and then ensuring the result is not negative (clamping it at zero). Gower distance is calculated with map_env_dist function

This function fit and validate Domain models. The Domain model is a simple model that uses the Gower distance to calculate the similarity between the presences training and presence-absences test data.

Value

A list object with:

• model: A tibble with presences. This object can be used for predicting.

• predictors: A tibble with quantitative (c column names) and qualitative (f column names) variables use for modeling.

• performance: Performance metric (see sdm_eval). Threshold dependent metrics are calculated based on the threshold specified in the argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

• data_ens: Predicted suitability for each test partition. This database is used in fit_ensemble

References

• Carpenter, G., Gillison, A.N., Winter, J., 1993. DOMAIN: a flexible modelling procedure for mapping potential distributions of plants and animals. Biodiversity & Conservation 2, 667–680

See Also

fit_gam, fit_gau, fit_gbm, fit_glm, fit_max, fit_net, fit_raf, and fit_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

dom_toy <- fit_dom(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec"
)
dom_toy$performance


require(dplyr)
require(terra)

data("spp")
somevar <- system.file("external/somevar.tif", package = "flexsdm")
somevar <- terra::rast(somevar)

# Extract data
some_sp <- spp %>%
  filter(species == "sp2")

some_sp <-
  sdm_extract(
    data = some_sp,
    x = "x",
    y = "y",
    env_layer = somevar
  )

# Partition
some_sp <- part_random(
  data = some_sp,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 5)
)


## %######################################################%##
#                                                          #
####                Fit a Domain model                  ####
#                                                          #
## %######################################################%##
# Fit some models
mdom <- fit_dom(
  data = some_sp,
  response = "pr_ab",
  predictors = c("CFP_1", "CFP_2", "CFP_3", "CFP_4"),
  predictors_f = NULL,
  partition = ".part",
  thr = c("max_sens_spec")
)

mdom

# Predict model
ind_p <- sdm_predict(
  models = mdom,
  pred = somevar,
  thr = "max_sens_spec",
  con_thr = TRUE,
  predict_area = NULL
)
plot(ind_p$dom)

## %######################################################%##
#                                                          #
####             Explore Domain suitabiltiy             ####
####             in the environmental space             ####
#                                                          #
## %######################################################%##

p_extra(
  training_data = some_sp %>% dplyr::filter(pr_ab == 1), # select only presences
  x = "x",
  y = "y",
  pr_ab = "pr_ab",
  extra_suit_data = ind_p$dom$dom,
  projection_data = somevar,
  geo_space = FALSE,
  prop_points = 0.3,
  alpha_p = 0.8,
  color_p = "black",
  color_gradient = c("#000033", "#1400FF", "#C729D6", "#FF9C63", "#FFFF60")
)

p_extra(
  training_data = some_sp %>% dplyr::filter(pr_ab == 1), # select only presences
  x = "x",
  y = "y",
  pr_ab = "pr_ab",
  predictors = c("CFP_1", "CFP_2"), # Just the first two predictors
  extra_suit_data = ind_p$dom$dom > 0.96, # a binary map
  projection_data = somevar,
  geo_space = TRUE,
  prop_points = 0.4,
  alpha_p = 0.8,
  color_p = "black",
  color_gradient = c("#1400FF", "#C729D6")
)

Description

Ensemble model fitting and validation

Usage

fit_ensemble(
  models,
  ens_method = c("mean", "meanw", "meansup", "meanthr", "median"),
  thr = NULL,
  thr_model = NULL,
  metric = NULL
)

Arguments

Value

A list object with:

• models: A list of models used for performing ensemble.

• thr_metric: Threshold and metric specified in the function.

• predictors: A tibble of quantitative (column names with c) and qualitative (column names with f) variables used in each models.

• performance: A tibble with performance metrics (see sdm_eval).

• performance_part: Performance metric for each replica and partition (see sdm_eval). Those metrics that are threshold-dependent are calculated based on the threshold specified in the argument.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

glm_toy <- fit_glm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec"
)
svm_toy <- fit_svm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec"
)

ens_toy <- fit_ensemble(
  models = list(glm_toy, svm_toy),
  ens_method = "mean",
  thr = NULL,
  thr_model = "max_sens_spec",
  metric = "TSS"
)
ens_toy$performance


require(dplyr)
require(terra)

# Environmental variables
somevar <-
  system.file("external/somevar.tif", package = "flexsdm")
somevar <- terra::rast(somevar)

# Species occurrences
data("spp")
set.seed(1)
some_sp <- spp %>%
  dplyr::filter(species == "sp2") %>%
  sdm_extract(
    data = .,
    x = "x",
    y = "y",
    env_layer = somevar,
    variables = names(somevar),
    filter_na = TRUE
  ) %>%
  part_random(
    data = .,
    pr_ab = "pr_ab",
    method = c(method = "kfold", folds = 3)
  )


# gam
mglm <- fit_glm(
  data = some_sp,
  response = "pr_ab",
  predictors = c("CFP_1", "CFP_2", "CFP_3", "CFP_4"),
  partition = ".part",
  poly = 2
)
mraf <- fit_raf(
  data = some_sp,
  response = "pr_ab",
  predictors = c("CFP_1", "CFP_2", "CFP_3", "CFP_4"),
  partition = ".part",
)
mgbm <- fit_gbm(
  data = some_sp,
  response = "pr_ab",
  predictors = c("CFP_1", "CFP_2", "CFP_3", "CFP_4"),
  partition = ".part"
)

# Fit and validate ensemble model
mensemble <- fit_ensemble(
  models = list(mglm, mraf, mgbm),
  ens_method = "meansup",
  thr = NULL,
  thr_model = "max_sens_spec",
  metric = "TSS"
)

mensemble

Description

Fit and validate Generalized Additive Models

Usage

fit_gam(
  data,
  response,
  predictors,
  predictors_f = NULL,
  select_pred = FALSE,
  partition = NULL,
  thr = NULL,
  fit_formula = NULL,
  k = -1
)

Arguments

Details

This function fits GAM using mgvc package, with Binomial distribution family and thin plate regression spline as a smoothing basis (see ?mgvc::s).

Value

A list object with:

• model: A "gam" class object from mgcv package. This object can be used for predicting.

• predictors: A tibble with quantitative (c column names) and qualitative (f column names) variables use for modeling.

• performance: Performance metric (see sdm_eval). Threshold dependent metrics are calculated based on the threshold specified in the argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

• data_ens: Predicted suitability for each test partition. This database is used in fit_ensemble

See Also

fit_gau, fit_gbm, fit_glm, fit_max, fit_net, fit_raf, and fit_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

gam_toy <- fit_gam(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec",
  k = 3
)
gam_toy$performance


require(dplyr)
data("abies")

# Using k-fold partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)
abies2

gam_t1 <- fit_gam(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  select_pred = FALSE,
  partition = ".part",
  thr = "max_sens_spec"
)
gam_t1$model
gam_t1$predictors
gam_t1$performance
gam_t1$performance_part

# Specifying the formula explicitly
require(mgcv)
gam_t2 <- fit_gam(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  select_pred = FALSE,
  partition = ".part",
  thr = "max_sens_spec",
  fit_formula = stats::formula(pr_ab ~ s(aet) +
    s(ppt_jja) +
    s(pH) + landform)
)

gam_t2$model
gam_t2$predictors
gam_t2$performance %>% dplyr::select(ends_with("_mean"))

# Using repeated k-fold partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 2)
)
abies2

gam_t3 <- fit_gam(
  data = abies2,
  response = "pr_ab",
  predictors = c("ppt_jja", "pH", "awc"),
  predictors_f = c("landform"),
  select_pred = FALSE,
  partition = ".part",
  thr = "max_sens_spec"
)
gam_t3

Description

Fit and validate Gaussian Process models

Usage

fit_gau(
  data,
  response,
  predictors,
  predictors_f = NULL,
  background = NULL,
  partition = NULL,
  thr = NULL
)

Arguments

Value

A list object with:

• model: A "graf" class object. This object can be used for predicting.

• predictors: A tibble with quantitative (c column names) and qualitative (f column names) variables use for modeling.

• performance: Performance metrics (see sdm_eval). Threshold dependent metrics are calculated based on the threshold criteria specified in the argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

• data_ens: Predicted suitability for each test partition. This database is used in fit_ensemble

See Also

fit_gam, fit_glm, fit_gbm, fit_max, fit_net, fit_raf, and fit_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

gau_toy <- fit_gau(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec"
)
gau_toy$performance


data("abies")
set.seed(1)
abies <- abies[sample(nrow(abies), 400), ] # subsample to speed up this example

# Using k-fold partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)
abies2

bg <- abies2
bg$pr_ab <- 0


gaup_t1 <- fit_gau(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  partition = ".part",
  background = bg,
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen")
)

gaup_t1$model
gaup_t1$predictors
gaup_t1$performance
gaup_t1$performance_part
gaup_t1$data_ens

# Using bootstrap partition method only with presence-absence
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "boot", replicates = 2, proportion = 0.7)
)
abies2

gaup_t2 <- fit_gau(
  data = abies2,
  response = "pr_ab",
  predictors = c("ppt_jja", "pH", "awc"),
  predictors_f = c("landform"),
  partition = ".part",
  thr = c(type = c("lpt", "max_sens_spec", "sensitivity"), sens = "0.8")
)
gaup_t2

Description

Fit and validate Generalized Boosted Regression models

Usage

fit_gbm(
  data,
  response,
  predictors,
  predictors_f = NULL,
  fit_formula = NULL,
  partition = NULL,
  thr = NULL,
  n_trees = 100,
  n_minobsinnode = as.integer(nrow(data) * 0.9/4),
  shrinkage = 0.1
)

Arguments

Value

A list object with:

• model: A "gbm" class object from gbm package. This object can be used for predicting.

• predictors: A tibble with quantitative (c column names) and qualitative (f column names) variables use for modeling.

• performance: Performance metric (see sdm_eval). Threshold dependent metrics are calculated based on the threshold specified in thr argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

• data_ens: Predicted suitability for each test partition based on the best model. This database is used in fit_ensemble

See Also

fit_gam, fit_gau, fit_glm, fit_max, fit_net, fit_raf, and fit_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

gbm_toy <- fit_gbm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec",
  n_trees = 20,
  n_minobsinnode = 3
)
gbm_toy$performance


data("abies")

# Using k-fold partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 10)
)
abies2

gbm_t1 <- fit_gbm(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  partition = ".part",
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen")
)
gbm_t1$model
gbm_t1$predictors
gbm_t1$performance
gbm_t1$performance_part
gbm_t1$data_ens

# Using bootstrap partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "boot", replicates = 10, proportion = 0.7)
)
abies2

gbm_t2 <- fit_gbm(
  data = abies2,
  response = "pr_ab",
  predictors = c("ppt_jja", "pH", "awc"),
  predictors_f = c("landform"),
  partition = ".part",
  thr = "max_sens_spec"
)
gbm_t2

Description

Fit and validate Generalized Linear Models

Usage

fit_glm(
  data,
  response,
  predictors,
  predictors_f = NULL,
  select_pred = FALSE,
  partition = NULL,
  thr = NULL,
  fit_formula = NULL,
  poly = 2,
  inter_order = 0
)

Arguments

Value

A list object with:

• model: A "glm" class object from stats package. This object can be used for predicting.

• predictors: A tibble with quantitative (c column names) and qualitative (f column names) variables use for modeling.

• performance: Performance metrics (see sdm_eval). Threshold dependent metric are calculated based on the threshold specified in thr argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

• data_ens: Predicted suitability for each test partition. This database is used in fit_ensemble

See Also

fit_gam, fit_gau, fit_gbm, fit_max, fit_net, fit_raf, and fit_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

glm_toy <- fit_glm(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec",
  poly = 1
)
glm_toy$performance


data("abies")
abies

# Using k-fold partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 5)
)
abies2

glm_t1 <- fit_glm(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  select_pred = FALSE,
  partition = ".part",
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen"),
  poly = 0,
  inter_order = 0
)
glm_t1$model
glm_t1$predictors
glm_t1$performance
glm_t1$performance_part
glm_t1$data_ens

# Using second order polynomial terms and first-order interaction terms
glm_t2 <- fit_glm(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  select_pred = FALSE,
  partition = ".part",
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen"),
  poly = 2,
  inter_order = 1
)

# Using repeated k-fold partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "rep_kfold", folds = 3, replicates = 5)
)
abies2

# Using third order polynomial terms and second-order interaction terms
glm_t3 <- fit_glm(
  data = abies2,
  response = "pr_ab",
  predictors = c("ppt_jja", "pH", "awc"),
  predictors_f = c("landform"),
  select_pred = FALSE,
  partition = ".part",
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen"),
  poly = 3,
  inter_order = 2
)

Description

Fit and validate Maximum Entropy models

Usage

fit_max(
  data,
  response,
  predictors,
  predictors_f = NULL,
  fit_formula = NULL,
  partition = NULL,
  background = NULL,
  thr = NULL,
  clamp = TRUE,
  classes = "default",
  pred_type = "cloglog",
  regmult = 1
)

Arguments

Details

When the argument “classes” is set as default MaxEnt will use different features combination depending of the number of presences (np) with the follow rule: if np < 10 classes = "l", if np between 10 and 15 classes = "lq", if np between 15 and 80 classes = "lqh", and if np >= 80 classes = "lqph"

When presence-absence (or presence-pseudo-absence) data are used in data argument in addition to background points, the function will fit models with presences and background points and validate with presences and absences. This procedure makes maxent comparable to other presences-absences models (e.g., random forest, support vector machine). If only presences and background points data are used, function will fit and validate model with presences and background data. If only presence-absences are used in data argument and without background, function will fit model with the specified data (not recommended).

Value

A list object with:

• model: A "maxnet" class object from maxnet package. This object can be used for predicting.

• predictors: A tibble with quantitative (c column names) and qualitative (f column names) variables use for modeling.

• performance: Performance metrics (see sdm_eval). Threshold dependent metrics are calculated based on the threshold specified in thr argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

• data_ens: Predicted suitability for each test partition based on the best model. This database is used in fit_ensemble

See Also

fit_gam, fit_gau, fit_gbm, fit_glm, fit_net, fit_raf, and fit_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

# Use the same records as background points (toy example only)
backg_toy <- abies_toy
backg_toy$pr_ab <- 0

max_toy <- fit_max(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  background = backg_toy,
  thr = "max_sens_spec",
  clamp = TRUE,
  classes = "lq",
  pred_type = "cloglog",
  regmult = 1
)
max_toy$performance


data("abies")
data("backg")
set.seed(1)
backg <- backg[sample(nrow(backg), 1000), ] # subsample to speed up this example
abies # environmental conditions of presence-absence data
backg # environmental conditions of background points

# Using k-fold partition method
# Note that the partition method, number of folds or replications must
# be the same for presence-absence and background points datasets
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)
abies2

backg2 <- part_random(
  data = backg,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)
backg2

max_t1 <- fit_max(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  partition = ".part",
  background = backg2,
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen"),
  clamp = TRUE,
  classes = "default",
  pred_type = "cloglog",
  regmult = 1
)
length(max_t1)

max_t1$model
max_t1$predictors
max_t1$performance
max_t1$performance_part
max_t1$data_ens

Description

Fit and validate Neural Networks models

Usage

fit_net(
  data,
  response,
  predictors,
  predictors_f = NULL,
  fit_formula = NULL,
  partition = NULL,
  thr = NULL,
  size = 2,
  decay = 0.1
)

Arguments

Value

A list object with:

• model: A "nnet.formula" "nnet" class object from nnet package. This object can be used for predicting.

• predictors: A tibble with quantitative (c column names) and qualitative (f column names) variables use for modeling.

• performance: Performance metrics (see sdm_eval). Threshold dependent metric are calculated based on the threshold specified in the argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

• data_ens: Predicted suitability for each test partition. This database is used in fit_ensemble

See Also

fit_gam, fit_gau, fit_gbm, fit_glm, fit_max, fit_raf, and fit_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

net_toy <- fit_net(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec",
  size = 2,
  decay = 1
)
net_toy$performance


data("abies")

# Using k-fold partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 10)
)
abies2

nnet_t1 <- fit_net(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  partition = ".part",
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen"),
  fit_formula = NULL
)

nnet_t1$model
nnet_t1$predictors
nnet_t1$performance
nnet_t1$performance_part
nnet_t1$data_ens

# Using bootstrap partition method and only with presence-absence
# and get performance for several method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "boot", replicates = 10, proportion = 0.7)
)
abies2

nnet_t2 <- fit_net(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  partition = ".part",
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen"),
  fit_formula = NULL
)
nnet_t2

Description

Fit and validate Random Forests models

Usage

fit_raf(
  data,
  response,
  predictors,
  predictors_f = NULL,
  fit_formula = NULL,
  partition = NULL,
  thr = NULL,
  mtry = sqrt(length(c(predictors, predictors_f))),
  ntree = 500
)

Arguments

Value

A list object with:

• model: A "randomForest" class object from randomForest package. This object can be used for predicting.

• predictors: A tibble with quantitative (c column names) and qualitative (f column names) variables use for modeling.

• performance: Performance metrics (see sdm_eval). Threshold dependent metrics are calculated based on the threshold specified in the argument.

• performance_part: Performance metric for each replica and partition (see sdm_eval).

• data_ens: Predicted suitability for each test partition. This database is used in fit_ensemble

See Also

fit_gam, fit_gau, fit_gbm, fit_glm, fit_max, fit_net, and fit_svm.

Examples

# Toy data: a small subset of 'abies' to keep this example fast
data("abies")
abies_toy <- abies[c(1:30, 701:730), ]
abies_toy <- part_random(
  data = abies_toy,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 3)
)

raf_toy <- fit_raf(
  data = abies_toy,
  response = "pr_ab",
  predictors = c("aet", "cwd", "tmin"),
  partition = ".part",
  thr = "max_sens_spec",
  mtry = 2,
  ntree = 50
)
raf_toy$performance


data("abies")

# Using k-fold partition method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "kfold", folds = 10)
)
abies2

rf_t1 <- fit_raf(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  partition = ".part",
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen"),
  fit_formula = NULL
)

rf_t1$model
rf_t1$predictors
rf_t1$performance
rf_t1$performance_part
rf_t1$data_ens

# Using bootstrap partition method and only with presence-absence
# and get performance for several method
abies2 <- part_random(
  data = abies,
  pr_ab = "pr_ab",
  method = c(method = "boot", replicates = 10, proportion = 0.7)
)
abies2

rf_t2 <- fit_raf(
  data = abies2,
  response = "pr_ab",
  predictors = c("aet", "ppt_jja", "pH", "awc", "depth"),
  predictors_f = c("landform"),
  partition = ".part",
  thr = c("max_sens_spec", "equal_sens_spec", "max_sorensen"),
  fit_formula = NULL,
  mtry = 2,
  ntree = 500
)
rf_t2