sp (version 1.2-3)

spsample: sample point locations in (or on) a spatial object


sample point locations within a square area, a grid, a polygon, or on a spatial line, using regular or random sampling methods; the methods used assume that the geometry used is not spherical, so objects should be in planar coordinates


spsample(x, n, type, ...) makegrid(x, n = 10000, nsig = 2, cellsize, offset = rep(0.5, nrow(bb)), pretty = TRUE)


Spatial object; spsample(x,...) is a generic method for the existing sample.Xxx fumctions
optional arguments, passed to the appropriate sample.Xxx functions; see NOTES for nclusters and iter
(approximate) sample size
character; "random" for completely spatial random; "regular" for regular (systematically aligned) sampling; "stratified" for stratified random (one single random location in each "cell"); "nonaligned" for nonaligned systematic sampling (nx random y coordinates, ny random x coordinates); "hexagonal" for sampling on a hexagonal lattice; "clustered" for clustered sampling; "Fibonacci" for Fibonacci sampling on the sphere (see references).
bounding box of the sampled domain; setting this to a smaller value leads to sub-region sampling
for square cell-based sampling types (regular, stratified, nonaligned): the offset (position) of the regular grid; the default for spsample methods is a random location in the unit cell [0,1] x [0,1], leading to a different grid after each call; if this is set to c(0.5,0.5), the returned grid is not random (but, in Ripley's wording, "centric systematic"). For line objects, a single offset value is taken, where the value varies within the [0, 1] interval, and 0 is the beginning of each Line object, and 1 its end
if missing, a cell size is derived from the sample size n; otherwise, this cell size is used for all sampling methods except "random"
for "pretty" cell size; spsample does not result in pretty grids
logical; if TRUE, choose pretty (rounded) coordinates


SpatialPoints-class. The number of points is only guaranteed to equal n when sampling is done in a square box, i.e. (sample.Spatial). Otherwise, the obtained number of points will have expected value n.When x is of a class deriving from Spatial-class for which no spsample-methods exists, sampling is done in the bounding box of the object, using spsample.Spatial. An overlay using over may be necessary to select the features inside the geometry afterwards.Sampling type "nonaligned" is not implemented for line objects.Some methods may return NULL if no points could be successfully placed.makegrid makes a regular grid that covers x; when cellsize is not given it derives one from the number of grid points requested (approximating the number of cells). It tries to choose pretty cell size and grid coordinates.


x = "Spatial"
sample in the bbox of x
x = "Line"
sample on a line
x = "Polygon"
sample in a Polygon
x = "Polygons"
sample in a Polygons object, consisting of possibly multiple Polygon objects (holes must be correctly defined, use checkPolygonsHoles if need be)
x = "SpatialPolygons"
sample in an SpatialPolygons object; sampling takes place over all Polygons objects present, use subsetting to vary sampling intensity (density); holes must be correctly defined, use checkPolygonsHoles if need be
x = "SpatialGrid"
sample in an SpatialGrid object
x = "SpatialPixels"
sample in an SpatialPixels object


Chapter 3 in B.D. Ripley, 1981. Spatial Statistics, Wiley

Fibonacci sampling: Alvaro Gonzalez, 2010. Measurement of Areas on a Sphere Using Fibonacci and Latitude-Longitude Lattices. Mathematical Geosciences 42(1), p. 49-64

See Also

over, point.in.polygon, sample


Run this code

meuse.sr = SpatialPolygons(list(Polygons(list(Polygon(meuse.riv)), "x")))

points(spsample(meuse.sr, n = 1000, "regular"), pch = 3)

points(spsample(meuse.sr, n = 1000, "random"), pch = 3)

points(spsample(meuse.sr, n = 1000, "stratified"), pch = 3)

points(spsample(meuse.sr, n = 1000, "nonaligned"), pch = 3)

points(spsample(meuse.sr@polygons[[1]], n = 100, "stratified"), pch = 3, cex=.5)

gridded(meuse.grid) = ~x+y
points(spsample(meuse.grid,n=1000,type="random"), pch=3, cex=.5)
points(spsample(meuse.grid,n=1000,type="stratified"), pch=3, cex=.5)
points(spsample(meuse.grid,n=1000,type="regular"), pch=3, cex=.5)
points(spsample(meuse.grid,n=1000,type="nonaligned"), pch=3, cex=.5)

fullgrid(meuse.grid) = TRUE
points(spsample(meuse.grid,n=1000,type="stratified"), pch=3,cex=.5)

Run the code above in your browser using DataCamp Workspace