spatialData: Cool Spatial Datasets • spatialData

spatialData is a data-only R package providing ready-to-use spatial datasets for ecological modeling. It was originally developed to supply example data for the R packages collinear and spatialRF, but the datasets are equally suited for teaching spatial analysis and species distribution modeling. Each dataset comes pre-processed with response variables and environmental predictors, so you can jump straight into the analysis without spending time on data preparation.

Installation

Install the development version from GitHub:

# Option 1: pak (recommended)
# install.packages("pak")
pak::pkg_install("blasbenito/spatialData")

# Option 2: remotes
# install.packages("remotes")
remotes::install_github("blasbenito/spatialData")

Datasets

All datasets are loaded lazily via data(). Most are sf data frames with point or polygon geometries; interaction is a plain data frame.

Dataset	Description	Spatial scope	Temporal scope	Rows	Responses	Predictors	CRS	Geometry
`neanderthal`	Neanderthal presence/absence and paleoclimate predictors	Europe	~120,000 BP (MIS 5e)	245	1	25	EPSG:4326	POINT
`quercus`	Distribution of European oaks and bioglimatic predictors	Europe	present	6,728	1	31	EPSG:4326	POINT
`vi`	NDVI records with environmental predictors	Global	1999–2019	9,265	5	58	EPSG:4326	POINT
`plantae`	Plant diversity of the global ecoregions	Global	2020	662	53	84	EPSG:4326	POINT (centroids)
`trees`	Tree species richness and environmental predictors	Americas	2012	3,373	1	50	EPSG:4326	POLYGON
`communities`	Plant community presence and climate predictors	Sierra Nevada, SE Spain	2009	7,300	6	9	EPSG:25830	POINT
`interaction`	Butterfly and host plant presence and environmental predictors	Sierra Nevada, SE Spain	2014	1000	3	10	EPSG:25830	POINT
`linaria`	Linaria nigricans and greenhouse records with environmental predictors	Eastern Andalusia, Spain		7,386	2	20	EPSG:25830	POINT
`andalusia`	Plant species presences and and environmental predictors	Andalusia, Spain	2010	8,666	2	20	EPSG:25830	POINT

Extra Data

Several datasets ship with companion download functions that retrieve larger or complementary files from spatialDataExtra.

Dataset	Function	Description	Format	Geometry / Bands	Resolution	CRS
`neanderthal`	`neanderthal_extra()`	25-band palaeoclimate raster (bioclim + topography)	GeoTIFF	25 bands	0.18°	EPSG:4326
`quercus`	`quercus_extra()`	31-band bioclimatic/environmental raster	GeoTIFF	31 bands	0.167°	EPSG:4326
`vi`	`vi_extra()`	Extended NDVI point dataset (30,000 records)	GeoPackage	POINT	30,000 rows	EPSG:4326
`plantae`	`plantae_extra()`	Ecoregion polygons with full diversity data	GeoPackage	MULTIPOLYGON	662 features	EPSG:4326
`trees`	`trees_extra()`	Individual tree species presence points	GeoPackage	POINT	523,308 rows	EPSG:4326
`communities`	`communities_extra_2010()`	Baseline (2010) climate raster for Sierra Nevada	GeoTIFF	9 bands	100 m	EPSG:25830
`communities`	`communities_extra_2050()`	Projected (2050) climate raster for Sierra Nevada	GeoTIFF	9 bands	100 m	EPSG:25830
`communities`	`communities_extra_2100()`	Projected (2100) climate raster for Sierra Nevada	GeoTIFF	9 bands	100 m	EPSG:25830
`interaction`	`interaction_extra()`	10-band environmental raster for Sierra Nevada	GeoTIFF	10 bands	100 m	EPSG:25830
`linaria`	`linaria_extra()`	20-band environmental raster for Eastern Andalusia	GeoTIFF	20 bands	400 m	EPSG:25830
`andalusia`	`andalusia_extra()`	20-band environmental raster for Andalusia	GeoTIFF	20 bands	400 m	EPSG:25830

Citation

The license of spatialData requires the following citation:

citation("spatialData")
#> To cite package 'spatialData' in publications use:
#> 
#>   Benito B (2025). "spatialData: Spatial Datasets for Ecological
#>   Modeling." doi:10.5281/zenodo.XXXXXXX
#>   <https://doi.org/10.5281/zenodo.XXXXXXX>, R package version 0.0.1,
#>   <https://blasbenito.github.io/spatialData>.
#> 
#> A BibTeX entry for LaTeX users is
#> 
#>   @Misc{,
#>     title = {spatialData: Spatial Datasets for Ecological Modeling},
#>     author = {Blas M. Benito},
#>     year = {2025},
#>     note = {R package version 0.0.1},
#>     url = {https://blasbenito.github.io/spatialData},
#>     doi = {10.5281/zenodo.XXXXXXX},
#>   }

License

CC BY 4.0 — see LICENSE.md for details.