Movatterモバイル変換

Type:	Package
Title:	Spatial and Environmental Blocking for K-Fold and LOOCross-Validation
Version:	3.2-0
Date:	2025-08-20
URL:	https://github.com/rvalavi/blockCV
BugReports:	https://github.com/rvalavi/blockCV/issues
Maintainer:	Roozbeh Valavi <valavi.r@gmail.com>
Description:	Creating spatially or environmentally separated folds for cross-validation to provide a robust error estimation in spatially structured environments; Investigating and visualising the effective range of spatial autocorrelation in continuous raster covariates and point samples to find an initial realistic distance band to separate training and testing datasets spatially described in Valavi, R. et al. (2019) <doi:10.1111/2041-210X.13107>.
License:	GPL (≥ 3)
Encoding:	UTF-8
Depends:	R (≥ 3.5.0)
Imports:	sf (≥ 1.0), sp, terra (≥ 1.6-41), ggplot2 (≥ 3.3.6),cowplot, automap (≥ 1.0-16), Rcpp (≥ 1.0.2)
Suggests:	shiny (≥ 1.7), tmap (≥ 2.0), biomod2, gstat, methods,knitr, rmarkdown, testthat (≥ 3.0.0)
RoxygenNote:	7.3.2
VignetteBuilder:	knitr
Config/testthat/edition:	3
LinkingTo:	Rcpp
NeedsCompilation:	yes
Packaged:	2025-08-20 01:17:51 UTC; val085
Author:	Roozbeh Valavi [aut, cre], Jane Elith [aut], José Lahoz-Monfort [aut], Ian Flint [aut], Gurutzeta Guillera-Arroita [aut]
Repository:	CRAN
Date/Publication:	2025-08-21 13:40:07 UTC

blockCV: Spatial and Environmental Blocking for K-Fold and LOO Cross-Validation

Description

Simple random selection of training and testing folds in the structured environment leads toan underestimation of error in the evaluation of spatialpredictions and may result in inappropriate model selection (Telford and Birks, 2009; Roberts et al., 2017). The use of spatial andenvironmental blocks to separate training and testing sets has been suggested as a good strategy for realistic error estimation in datasetswith dependence structures, and more generally as a robust method for estimating the predictive performance of models used to predict mappeddistributions (Roberts et al., 2017). The packageblockCV offersa range of functions for generating train and test foldsfork-fold andleave-one-out (LOO) cross-validation (CV). It allows for separationof data spatially and environmentally, with various options for block construction.Additionally, it includes a function for assessing the level of spatial autocorrelationin response or raster covariates, to aid in selecting an appropriate distance band fordata separation. TheblockCV package is suitable for the evaluation of a variety ofspatial modelling applications, including classification of remote sensing imagery,soil mapping, and species distribution modelling (SDM). It also provides support fordifferent SDM scenarios, including presence-absence and presence-background speciesdata, rare and common species, and raster data for predictor variables.

Author(s)

Roozbeh Valavi, Jane Elith, José Lahoz-Monfort, Ian Flint, and Gurutzeta Guillera-Arroita

References

Valavi, R., Elith, J., Lahoz-Monfort, J. J., & Guillera-Arroita, G. (2019). blockCV: An R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models. Methods in Ecology and Evolution, 10(2), 225-232. doi:10.1111/2041-210X.13107.

See Also

cv_spatial,cv_cluster,cv_buffer, andcv_nndm for blocking strategies.

Use distance (buffer) around records to separate train and test folds

Description

This function is deprecated and will be removed in future updates! Please usecv_buffer instead!

Usage

buffering(  speciesData,  species = NULL,  theRange,  spDataType = "PA",  addBG = TRUE,  progress = TRUE)

Arguments

See Also

cv_buffer

Explore spatial block size

Description

This function assists selection of block size. It allows the user to visualise the blocksinteractively, viewing the impact of block size on number and arrangement of blocks inthe landscape (and optionally on the distribution of species data in those blocks).Slide to the selected block size, and clickApply Changes to change the block size.

Usage

cv_block_size(r, x = NULL, column = NULL, min_size = NULL, max_size = NULL)

Arguments

Value

an interactive shiny session

Examples

if(interactive()){library(blockCV)# import presence-absence species datapoints <- read.csv(system.file("extdata/", "species.csv", package = "blockCV"))pa_data <- sf::st_as_sf(points, coords = c("x", "y"), crs = 7845)# manually choose the size of spatial blockscv_block_size(x = pa_data,              column = "occ",              min_size = 2e5,              max_size = 9e5)}

Use buffer around records to separate train and test folds (a.k.a. buffered/spatial leave-one-out)

Description

This function generates spatially separated train and test folds by considering buffers ofthe specified distance (size parameter) around each observation point.This approach is a form ofleave-one-out cross-validation. Each fold is generated by excludingnearby observations around each testing point within the specified distance (ideally the range ofspatial autocorrelation, seecv_spatial_autocor). In this method, the testing set neverdirectly abuts a training sample (e.g. presence or absence; 0s and 1s). For more information see the details section.

Usage

cv_buffer(  x,  column = NULL,  size,  presence_bg = FALSE,  add_bg = FALSE,  progress = TRUE,  report = TRUE)

Arguments

Details

When working with presence-background (presence and pseudo-absence) species distributiondata (should be specified bypresence_bg = TRUE argument), only presence records are usedfor specifying the folds (recommended). Consider a target presence point. The buffer is defined around this target point,using the specified range (size). By default, the testing fold comprises only the target presence point (all backgroundpoints within the buffer are also added whenadd_bg = TRUE).Any non-target presence points inside the buffer are excluded.All points (presence and background) outside of buffer are used for the training set.The methods cycles through all thepresence data, so the number of folds is equal tothe number of presence points in the dataset.

For presence-absence data (and all other types of data), folds are created based on all records, bothpresences and absences. As above, a target observation (presence or absence) forms a test point, allpresence and absence points other than the target point within the buffer are ignored, and the trainingset comprises all presences and absences outside the buffer. Apart from the folds, the numberoftraining-presence,training-absence,testing-presence andtesting-absencerecords is stored and returned in therecords table. Ifcolumn = NULL andpresence_bg = FALSE,the procedure is like presence-absence data. All other data types (continuous, count or multi-class responses) should bedone bypresence_bg = FALSE.

Value

An object of class S3. A list of objects including:

• folds_list - a list containing the folds. Each fold has two vectors with the training (first) and testing (second) indices

• k - number of the folds

• size - the defined range of spatial autocorrelation)

• column - the name of the column if provided

• presence_bg - whether this was treated as presence-background data

• records - a table with the number of points in each category of training and testing

References

Radosavljevic, A., & Anderson, R. P. (2014). Making better Maxent models of speciesdistributions: Complexity, overfitting and evaluation. Journal of Biogeography, 41, 629–643. https://doi.org/10.1111/jbi.12227

See Also

cv_nndm,cv_spatial, andcv_spatial_autocor

Examples

library(blockCV)# import presence-absence species datapoints <- read.csv(system.file("extdata/", "species.csv", package = "blockCV"))# make an sf object from data.framepa_data <- sf::st_as_sf(points, coords = c("x", "y"), crs = 7845)bloo <- cv_buffer(x = pa_data,                  column = "occ",                  size = 350000, # size in metres no matter the CRS                  presence_bg = FALSE)

Use environmental or spatial clustering to separate train and test folds

Description

This function uses clustering methods to specify sets of similar environmentalconditions based on the input covariates, or cluster of spatial coordinates of the sample data.Sample data (i.e. species data) corresponding to any ofthese groups or clusters are assigned to a fold. Clustering is doneusingkmeans for both approaches. The only requirement isx that leads toa clustering of the confidantes of sample data. Otherwise, by providingr, environmentalclustering is done.

Usage

cv_cluster(  x,  column = NULL,  r = NULL,  k = 5L,  scale = TRUE,  raster_cluster = FALSE,  num_sample = 10000L,  biomod2 = TRUE,  report = TRUE,  ...)

Arguments

Details

As k-means algorithms use Euclidean distance to estimate clusters, the input raster covariates should be quantitative variables.Since variables with wider ranges of values might dominate the clusters and bias the environmental clustering (Hastie et al., 2009),all the input rasters are first scaled and centred (scale = TRUE) within the function.

Ifraster_cluster = TRUE, the clustering is done in the raster space. In this approach the clusters will be consistent throughout the regionand different sample datasets in the same region (for comparison). However, this may result in a cluster(s)that covers none of the species records (the spatial location of response samples),especially when species data is not dispersed throughout the region or the number of clusters (k or folds) is high. In thiscase, the number of folds is less than specifiedk. Ifraster_cluster = FALSE, the clustering will be done inspecies points and the number of the folds will be the same ask.

Note that the input raster layer should cover all the species points, otherwise an error will rise. The records with no rastervalue should be deleted prior to the analysis or another raster layer must be provided.

Value

An object of class S3. A list of objects including:

• folds_list - a list containing the folds. Each fold has two vectors with the training (first) and testing (second) indices

• folds_ids - a vector of values indicating the number of the fold for each observation (each number corresponds to the same point in x)

• biomod_table - a matrix with the folds to be used inbiomod2 package

• k - number of the folds

• column - the name of the column if provided

• type - indicates whether spatial or environmental clustering was done.

• records - a table with the number of points in each category of training and testing

References

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction ( 2nd ed., Vol. 1).

See Also

cv_buffer andcv_spatial

Examples

library(blockCV)# import presence-absence species datapoints <- read.csv(system.file("extdata/", "species.csv", package = "blockCV"))# make an sf object from data.framepa_data <- sf::st_as_sf(points, coords = c("x", "y"), crs = 7845)# load raster datapath <- system.file("extdata/au/", package = "blockCV")files <- list.files(path, full.names = TRUE)covars <- terra::rast(files)# spatial clusteringset.seed(6)sc <- cv_cluster(x = pa_data,                 column = "occ", # optional; name of the column with response                 k = 5)# environmental clusteringset.seed(6)ec <- cv_cluster(r = covars, # if provided will be used for environmental clustering                 x = pa_data,                 column = "occ", # optional; name of the column with response                 k = 5,                 scale = TRUE)

Use the Nearest Neighbour Distance Matching (NNDM) to separate train and test folds

Description

A fast implementation of the Nearest Neighbour Distance Matching (NNDM) algorithm (Milà et al., 2022) in C++. Similartocv_buffer, this is a variation of leave-one-out (LOO) cross-validation. It tries to match thenearest neighbour distance distribution function between the test and training data to the nearest neighbourdistance distribution function between the target prediction and training points (Milà et al., 2022).

Usage

cv_nndm(  x,  column = NULL,  r,  size,  num_sample = 10000,  sampling = "random",  min_train = 0.05,  presence_bg = FALSE,  add_bg = FALSE,  plot = TRUE,  report = TRUE)

Arguments

Details

When working with presence-background (presence and pseudo-absence) species distributiondata (should be specified bypresence_bg = TRUE argument), only presence records are usedfor specifying the folds (recommended). The testing fold comprises only the targetpresence point (optionally,all background points within the distance are also included whenadd_bg = TRUE; this is thedistance that matches the nearest neighbour distance distribution function of training-testing presences andtraining-presences and prediction points; often lower thansize).Any non-target presence points inside the distance are excluded.All points (presence and background) outside of distance are used for the training set.The methods cycles through all the presence data, so the number of folds is equal tothe number of presence points in the dataset.

For all other types of data (including presence-absence, count, continuous, and multi-class)setpresence_bg = FALE, and the function behaves similar to the methodsexplained by Milà and colleagues (2022).

Value

An object of class S3. A list of objects including:

• folds_list - a list containing the folds. Each fold has two vectors with the training (first) and testing (second) indices

• k - number of the folds

• size - the distance band to separated trainig and testing folds)

• column - the name of the column if provided

• presence_bg - whether this was treated as presence-background data

• records - a table with the number of points in each category of training and testing

References

C. Milà, J. Mateu, E. Pebesma, and H. Meyer, Nearest Neighbour Distance MatchingLeave-One-Out Cross-Validation for map validation, Methods in Ecology and Evolution (2022).

See Also

cv_buffer andcv_spatial_autocor

Examples

library(blockCV)# import presence-absence species datapoints <- read.csv(system.file("extdata/", "species.csv", package = "blockCV"))# make an sf object from data.framepa_data <- sf::st_as_sf(points, coords = c("x", "y"), crs = 7845)# load raster datapath <- system.file("extdata/au/bio_5.tif", package = "blockCV")covar <- terra::rast(path)nndm <- cv_nndm(x = pa_data,                column = "occ", # optional                r = covar,                size = 350000, # size in metres no matter the CRS                num_sample = 10000,                sampling = "regular",                min_train = 0.1)

Visualising folds created by blockCV in ggplot

Description

This function visualises the folds create by blockCV. It also accepts a rasterlayer to be used as background in the output plot.

Usage

cv_plot(  cv,  x,  r = NULL,  nrow = NULL,  ncol = NULL,  num_plots = 1:10,  max_pixels = 3e+05,  remove_na = TRUE,  raster_colors = gray.colors(10, alpha = 1),  points_colors = c("#E69F00", "#56B4E9"),  points_alpha = 0.7,  label_size = 4)

Arguments

Value

a ggplot object

Examples

library(blockCV)# import presence-absence species datapoints <- read.csv(system.file("extdata/", "species.csv", package = "blockCV"))pa_data <- sf::st_as_sf(points, coords = c("x", "y"), crs = 7845)# spatial clusteringsc <- cv_cluster(x = pa_data, k = 5)# now plot the create foldscv_plot(cv = sc,        x = pa_data, # sample points        nrow = 2,        points_alpha = 0.5)

Compute similarity measures to evaluate possible extrapolation in testing folds

Description

This function evaluates environmental similarity between training and testing folds,helping to detect potential extrapolation in the testing data. It supports threesimilarity measures: Multivariate Environmental Similarity Surface (MESS), Manhattandistance (L1), and Euclidean distance (L2).

Usage

cv_similarity(  cv,  x,  r,  num_plot = seq_along(cv$folds_list),  method = "MESS",  num_sample = 10000L,  jitter_width = 0.1,  points_size = 2,  points_alpha = 0.7,  points_colors = NULL,  progress = TRUE)

Arguments

Details

The MESS is calculated as described in Elith et al. (2010). MESS representshow similar a point in a testing fold is to a training fold (as a referenceset of points), with respect to a set of predictor variables inr.The negative values are the sites where at least one variable has a value that is outsidethe range of environments over the reference set, so these are novel environments.

When using the L1 (Manhattan) or L2 (Euclidean) distance options (experimental), thefunction performs the following steps for each test sample:

• 1. Calculates the minimum distance between each test sample and all training samplesin the same fold using the selected metric (L1 or L2).

• 2. Calculates a baseline distance: the average of the minimum distances between a setof random background samples (defined bynum_sample) from the raster and all training/testsamples combined.

• 3. Computes a similarity score by subtracting the test sample’s minimum distance fromthe baseline average. A higher score indicates the test sample is more similar tothe training data, while lower or negative scores indicate novelty.

This provides a simple, distance-based novelty metric, useful for assessingextrapolation or dissimilarity in prediction scenarios. Note that this approach isexperimental.

Value

a ggplot object

References

Elith, J., Kearney, M., & Phillips, S. (2010). The art of modelling range-shifting species: The art of modelling range-shifting species. Methods in Ecology and Evolution, 1(4), 330–342.

See Also

cv_spatial,cv_cluster,cv_buffer, andcv_nndm

Examples

library(blockCV)# import presence-absence species datapoints <- read.csv(system.file("extdata/", "species.csv", package = "blockCV"))# make an sf object from data.framepa_data <- sf::st_as_sf(points, coords = c("x", "y"), crs = 7845)# load raster datapath <- system.file("extdata/au/", package = "blockCV")files <- list.files(path, full.names = TRUE)covars <- terra::rast(files)# hexagonal spatial blocking by specified size and random assignmentsb <- cv_spatial(x = pa_data,                 column = "occ",                 size = 450000,                 k = 5,                 iteration = 1)# compute extrapolationcv_similarity(cv = sb, r = covars, x = pa_data)

Use spatial blocks to separate train and test folds

Description

This function creates spatially separated folds based on a distance to number of row and/or column.It assigns blocks to the training and testing foldsrandomly,systematically orin acheckerboard pattern. The distance (size)should be inmetres, regardless of the unit of the reference system ofthe input data (for more information see the details section). By default,the function creates blocks according to the extent and shape of the spatial sample data (x e.g.the species occurrence), Alternatively, blocks can be created based onr assuming that theuser has considered the landscape for the given species and case study.Blocks can also be offset so the origin is not at the outer corner of the rasters.Instead of providing a distance, the blocks can also be created by specifying a number of rows and/orcolumns and divide the study area into vertical or horizontal bins, as presented in Wenger & Olden (2012)and Bahn & McGill (2012). Finally, the blocks can be specified by a user-defined spatial polygon layer.

Usage

cv_spatial(  x,  column = NULL,  r = NULL,  k = 5L,  hexagon = TRUE,  flat_top = FALSE,  size = NULL,  rows_cols = c(10, 10),  selection = "random",  iteration = 100L,  user_blocks = NULL,  folds_column = NULL,  deg_to_metre = 111325,  biomod2 = TRUE,  offset = c(0, 0),  extend = 0,  seed = NULL,  progress = TRUE,  report = TRUE,  plot = TRUE,  ...)

Arguments

Details

To maintain consistency, all functions in this package usemeters as their unit ofmeasurement. However, when the input map has a geographic coordinate system (in decimal degrees),the block size is calculated by dividing thesize parameter bydeg_to_metre (whichdefaults to 111325 meters, the standard distance of one degree of latitude on the Equator).In reality, this value varies by a factor of the cosine of the latitude. So, an alternative sensiblevalue could becos(mean(sf::st_bbox(x)[c(2,4)]) * pi/180) * 111325.

Theoffset can be used to change the spatial position of the blocks. It can also be used toassess the sensitivity of analysis results to shifting in the blocking arrangements.These options are available whensize is defined. By default the region islocated in the middle of the blocks and by setting the offsets, the blocks will shift.

Roberts et. al. (2017) suggest that blocks should be substantially bigger than the range of spatialautocorrelation (in model residual) to obtain realistic error estimates, while a buffer with the size ofthe spatial autocorrelation range would result in a good estimation of error. This is because of the so-callededge effect (O'Sullivan & Unwin, 2014), whereby points located on the edges of the blocks of opposite sets arenot separated spatially. Blocking with a buffering strategy overcomes this issue (seecv_buffer).

Value

An object of class S3. A list of objects including:

• folds_list - a list containing the folds. Each fold has two vectors with the training (first) and testing (second) indices

• folds_ids - a vector of values indicating the number of the fold for each observation (each number corresponds to the same point in species data)

• biomod_table - a matrix with the folds to be used inbiomod2 package

• k - number of the folds

• size - input size, if not null

• column - the name of the column if provided

• blocks - spatial polygon of the blocks

• records - a table with the number of points in each category of training and testing

References

Bahn, V., & McGill, B. J. (2012). Testing the predictive performance of distribution models. Oikos, 122(3), 321-331.

O'Sullivan, D., Unwin, D.J., (2010). Geographic Information Analysis, 2nd ed. John Wiley & Sons.

Roberts et al., (2017). Cross-validation strategies for data with temporal, spatial, hierarchical,or phylogenetic structure. Ecography. 40: 913-929.

Wenger, S.J., Olden, J.D., (2012). Assessing transferability of ecological models: an underappreciated aspect of statisticalvalidation. Methods Ecol. Evol. 3, 260-267.

See Also

cv_buffer andcv_cluster;cv_spatial_autocor andcv_block_size for selecting block size

ForCV.user.table seeBIOMOD_Modeling inbiomod2 package

Examples

library(blockCV)# import presence-absence species datapoints <- read.csv(system.file("extdata/", "species.csv", package = "blockCV"))# make an sf object from data.framepa_data <- sf::st_as_sf(points, coords = c("x", "y"), crs = 7845)# hexagonal spatial blocking by specified size and random assignmentsb1 <- cv_spatial(x = pa_data,                  column = "occ",                  size = 450000,                  k = 5,                  selection = "random",                  iteration = 50)# spatial blocking by row/column and systematic fold assignmentsb2 <- cv_spatial(x = pa_data,                  column = "occ",                  rows_cols = c(8, 10),                  k = 5,                  hexagon = FALSE,                  selection = "systematic")

Measure spatial autocorrelation in spatial response data or predictor raster files

Description

This function provides a quantitative basis for choosing block size. The spatial autocorrelation in either thespatial sample points or all continuous predictor variables available as raster layers is assessed and reported.The response (as defined becolumn) in spatial sample points can be binary such as species distribution data,or continuous response like soil organic carbon. The function estimates spatial autocorrelationranges of all inputraster layers or the response data. This is the range over which observations are independent and is determined byconstructing the empirical variogram, a fundamental geostatistical tool for measuring spatial autocorrelation.The empirical variogram models the structure of spatial autocorrelation by measuring variability between all possiblepairs of points (O'Sullivan and Unwin, 2010). Results are plotted. See the details section for further information.

Usage

cv_spatial_autocor(  r,  x,  column = NULL,  num_sample = 5000L,  deg_to_metre = 111325,  plot = TRUE,  progress = TRUE,  ...)

Arguments

Details

The input raster layers should be continuous for computing the variograms and estimating the range of spatialautocorrelation. The input rasters should also have a specified coordinate reference system. However, if the referencesystem is not specified, the function attempts to guess it based on the extent of the map. It assumes an un-projectedreference system for layers with extent lying between -180 and 180.

Variograms are calculated based on the distances between pairs of points, so un-projected rasters (in degrees) willnot give an accurate result (especially over large latitudinal extents). For un-projected rasters,the great circle distance(rather than Euclidean distance) is used to calculate the spatial distances between pairs of points. Toenable more accurate estimate, it is recommended to transform un-projected maps (geographic coordinatesystem / latitude-longitude) to a projected metric reference system (e.g. UTM or Lambert) where it is possible.SeeautofitVariogram fromautomap andvariogram fromgstat packagesfor further information.

Value

An object of class S3. A list object including:

• range - the suggested range (i.e. size), which is the median of all calculated ranges in case of 'r'.

• range_table - a table of input covariates names and their autocorrelation range

• plots - the output plot (the plot is shown by default)

• num_sample - number sample of 'r' used for analysis

• variograms - fitted variograms for all layers

References

O'Sullivan, D., Unwin, D.J., (2010). Geographic Information Analysis, 2nd ed. John Wiley & Sons.

Roberts et al., (2017). Cross-validation strategies for data with temporal, spatial, hierarchical,or phylogenetic structure. Ecography. 40: 913-929.

See Also

cv_block_size

Examples

library(blockCV)# import presence-absence species datapoints <- read.csv(system.file("extdata/", "species.csv", package = "blockCV"))# make an sf object from data.framepa_data <- sf::st_as_sf(points, coords = c("x", "y"), crs = 7845)# load raster datapath <- system.file("extdata/au/", package = "blockCV")files <- list.files(path, full.names = TRUE)covars <- terra::rast(files)# spatial autocorrelation of a binary/continuous responsesac1 <- cv_spatial_autocor(x = pa_data,                           column = "occ", # binary or continuous data                           plot = TRUE)# spatial autocorrelation of continuous raster filessac2 <- cv_spatial_autocor(r = covars,                           num_sample = 5000,                           plot = TRUE)# show the resultsummary(sac2)

Use environmental clustering to separate train and test folds

Description

This function is deprecated and will be removed in future updates! Please usecv_cluster instead!

Usage

envBlock(  rasterLayer,  speciesData,  species = NULL,  k = 5,  standardization = "normal",  rasterBlock = TRUE,  sampleNumber = 10000,  biomod2Format = TRUE,  numLimit = 0,  verbose = TRUE)

Arguments

See Also

cv_cluster

Explore the generated folds

Description

This function is deprecated! Please usecv_plot function for plotting the folds.

Usage

foldExplorer(blocks, rasterLayer, speciesData)

Arguments

Explore spatial block size

Description

This function is deprecated and will be removed in future updates! Please usecv_block_size instead!

Usage

rangeExplorer(  rasterLayer,  speciesData = NULL,  species = NULL,  rangeTable = NULL,  minRange = NULL,  maxRange = NULL)

Arguments

See Also

cv_block_size

Measure spatial autocorrelation in the predictor raster files

Description

This function is deprecated and will be removed in future updates! Please usecv_spatial_autocor instead!

Usage

spatialAutoRange(  rasterLayer,  sampleNumber = 5000L,  border = NULL,  speciesData = NULL,  doParallel = NULL,  nCores = NULL,  showPlots = TRUE,  degMetre = 111325,  maxpixels = 1e+05,  plotVariograms = FALSE,  progress = TRUE)

Arguments

See Also

cv_spatial_autocor

Use spatial blocks to separate train and test folds

Description

This function is deprecated and will be removed in future updates! Please usecv_spatial instead!

Usage

spatialBlock(  speciesData,  species = NULL,  rasterLayer = NULL,  theRange = NULL,  rows = NULL,  cols = NULL,  k = 5L,  selection = "random",  iteration = 100L,  blocks = NULL,  foldsCol = NULL,  numLimit = 0L,  maskBySpecies = TRUE,  degMetre = 111325,  border = NULL,  showBlocks = TRUE,  biomod2Format = TRUE,  xOffset = 0,  yOffset = 0,  extend = 0,  seed = 42,  progress = TRUE,  verbose = TRUE)

Arguments

See Also

cv_spatial