Extracts the values of cells in a raster (RasterLayer, RasterStack
RasterBrick, or SpatRaster) that are covered by polygons in a
simple feature collection (sf or sfc) or SpatialPolygonsDataFrame.
Returns either a summary of the extracted values or the extracted values
themselves.
# S4 method for Raster,sf
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for Raster,SpatialPolygonsDataFrame
exact_extract(x, y, ...)
# S4 method for Raster,SpatialPolygons
exact_extract(x, y, ...)
# S4 method for Raster,sfc_MULTIPOLYGON
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for Raster,sfc_POLYGON
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for Raster,sfc_GEOMETRY
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for Raster,sfc_GEOMETRYCOLLECTION
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for SpatRaster,sf
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for SpatRaster,SpatialPolygonsDataFrame
exact_extract(x, y, ...)
# S4 method for SpatRaster,SpatialPolygons
exact_extract(x, y, ...)
# S4 method for SpatRaster,sfc_MULTIPOLYGON
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for SpatRaster,sfc_POLYGON
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for SpatRaster,sfc_GEOMETRY
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)
# S4 method for SpatRaster,sfc_GEOMETRYCOLLECTION
exact_extract(
x,
y,
fun = NULL,
...,
weights = NULL,
append_cols = NULL,
coverage_area = FALSE,
default_value = NA_real_,
default_weight = NA_real_,
include_area = FALSE,
include_cell = FALSE,
include_cols = NULL,
include_xy = FALSE,
force_df = FALSE,
full_colnames = FALSE,
stack_apply = FALSE,
summarize_df = FALSE,
quantiles = NULL,
progress = TRUE,
max_cells_in_memory = 3e+07,
grid_compat_tol = 0.001,
colname_fun = NULL
)a RasterLayer, RasterStack, RasterBrick, or SpatRaster
a sf, sfc, SpatialPolygonsDataFrame, or SpatialPolygons
object with polygonal geometries
an optional function or character vector, as described below
additional arguments to pass to fun
a weighting raster to be used with the weighted_mean
and weighted_sum summary operations or a user-defined
summary function. When weights is set to 'area', the
cell areas of x will be calculated and used as weights.
when fun is not NULL, an optional character vector
of columns from y to be included in returned data frame.
if TRUE, output pixel coverage_area
instead of coverage_fraction
an optional value to use instead of NA in x
an optional value to use instead of NA in weights
if TRUE, and fun is NULL, augment
the data frame for each feature with a column
for the cell area. If the units of the raster CRS are
degrees, the area in square meters will be calculated
based on a spherical approximation of Earth. Otherwise,
a Cartesian area will be calculated (and will be the
same for all pixels.) If TRUE and fun is
not NULL, add area to the data frame passed
to fun for each feature.
if TRUE, and fun is NULL, augment
the data frame for each feature with a column
for the cell index (cell). If TRUE and
fun is not NULL, add cell to the
data frame passed to fun for each feature.
an optional character vector of column names in
y to be added to the data frame for each
feature that is either returned (when fun is
NULL) or passed to fun.
if TRUE, and fun is NULL, augment
the returned data frame for each feature with columns
for cell center coordinates (x and y). If
TRUE and fun is not NULL, add
x and y to the data frame passed to fun
for each feature.
always return a data frame instead of a vector, even if
x has only one layer and fun has length 1
include the names of x and weights in
the names of the data frame for each feature, even if
x or weights has only one layer.
This is useful when the results of multiple
calls to exact_extract are combined with
cbind.
if TRUE, apply fun independently to
each layer or x (and its corresponding layer
of weights, if provided.) The number of
layers in x and weights must equal
each other or 1, in which case the
single layer raster will be recycled.
If FALSE, apply fun to all layers of
x (and weights) simultaneously.
pass values, coverage fraction/area, and weights to
fun as a single data frame instead of
separate arguments.
quantiles to be computed when fun = 'quantile'
if TRUE, display a progress bar during processing
the maximum number of raster cells to load at
a given time when using a named summary operation
for fun (as opposed to a function defined using
R code). If a polygon covers more than max_cells_in_memory
raster cells, it will be processed in multiple chunks.
require value and weight grids to align within
grid_compat_tol times the smaller of the two
grid resolutions.
an optional function used to construct column names.
Should accept arguments values (name of value layer),
weights (name of weight layer), fun_name (value of
fun), fun_value (value associated with fun, for
fun %in% c('quantile', 'frac', 'weighted_frac)
nvalues (number of value layers), weights
(number of weight layers)
a vector, data frame, or list of data frames, depending on the type
of x and the value of fun (see Details)
exact_extract extracts the values of cells in a raster that are covered
by polygonal features in a simple feature collection (sf or sfc) or
SpatialPolygonDataFrame, as well as the fraction or area of each cell that
is covered by the feature. Pixels covered by all parts of the polygon are
considered. If an (invalid) multipart polygon covers the same pixels more
than once, the pixel may have a coverage fraction greater than one.
The function can either return pixel values directly to the caller, or can return the result of a predefined summary operation or user-defined R function applied to the values. These three approaches are described in the subsections below.
If fun is not specified, exact_extract will return a list with
one data frame for each feature in the input feature collection. The data
frame will contain a column with cell values from each layer in the input
raster (and optional weighting raster) and a column indicating
the fraction or area of the cell that is covered by the polygon.
If the input rasters have only one layer, the value and weight columns in the
data frame will be named values or weights. When the input rasters have
more than one layer, the columns will be named according to names(x) and
names(weights). The column containing pixel coverage will be called
coverage_fraction when coverage_area = FALSE, or coverage_area when
coverage_area = TRUE. Additional columns can be added to the returned data
frames with the include_area, include_cell, and include_xy arguments.
If the output data frames for multiple features are to be combined (e.g.,
with rbind), it may be useful to include identifying column(s) from the
input features in the returned data frames using include_cols.
Often the individual pixel values are not needed; only one or more summary
statistics (e.g., mean, sum) is required for each feature. Common summary
statistics can be calculated by exact_extract directly using a predefined
summary operation. Where possible, this approach is advantageous because it
allows the package to calculate the statistics incrementally, avoiding the
need to store all pixel values in memory at the same time. This allows the
package to process arbitrarily large data with a small amount of memory. (The
max_pixels_in_memory argument can be used to fine-tune the amount of memory
made available to exact_extract.)
To summarize pixel values using a predefined summary option, fun should be
set to a character vector of one or more operation names. If the input raster
has a single layer and a single summary operation is specified,
exact_extract will return a vector with the result of the summary operation
for each feature in the input. If the input raster has multiple layers, or if
multiple summary operations are specified, exact_extract will return a data
frame with a row for each feature and a column for each summary operation /
layer combination. (The force_df option can be used to always return a data
frame instead of a vector.)
The following summary operations are supported:
min - the minimum non-NA value in any raster cell wholly or
partially covered by the polygon
max - the maximum non-NA value in any raster cell wholly or
partially covered by the polygon
count - the sum of fractions of raster cells with non-NA
values covered by the polygon
sum - the sum of non-NA raster cell values, multiplied by
the fraction of the cell that is covered by the polygon
mean - the mean cell value, weighted by the fraction of each cell
that is covered by the polygon
median - the median cell value, weighted by the fraction of each cell
that is covered by the polygon
quantile - arbitrary quantile(s) of cell values, specified in
quantiles, weighted by the fraction of each cell that is
covered by the polygon
mode - the most common cell value, weighted by the fraction of
each cell that is covered by the polygon. Where multiple
values occupy the same maximum number of weighted cells,
the largest value will be returned.
majority - synonym for mode
minority - the least common cell value, weighted by the fraction
of each cell that is covered by the polygon. Where
multiple values occupy the same minimum number of
weighted cells, the smallest value will be returned.
variety - the number of distinct values in cells that are wholly or
partially covered by the polygon.
variance - the population variance of cell values, weighted by the
fraction of each cell that is covered by the polygon.
stdev - the population standard deviation of cell values, weighted by
the fraction of each cell that is covered by the polygon.
coefficient_of_variation - the population coefficient of variation of
cell values, weighted by the fraction of each
cell that is covered by the polygon.
weighted_mean - the mean cell value, weighted by the product of
the fraction of each cell covered by the polygon
and the value of a second weighting raster provided
as weights
weighted_sum - the sum of defined raster cell values, multiplied by
the fraction of each cell that is covered by the polygon
and the value of a second weighting raster provided
as weights
frac - returns one column for each possible value of x, with the
the fraction of defined raster cells that are equal to that
value.
weighted_frac - returns one column for each possible value of x,
with the fraction of defined cells that are equal
to that value, weighted by weights.
In all of the summary operations, NA values in the the primary raster (x)
raster are ignored (i.e., na.rm = TRUE.) If NA values occur in the
weighting raster, the result of the weighted operation will be NA. NA
values in both x and weights can be replaced on-the-fly using the
default_value and default_weight arguments.
If no predefined summary operation is suitable, a user-defined R function may
be provided as fun. The function will be called once for each feature and
must return either a single value or a data frame. The results of the
function for each feature will be combined and returned by exact_extract.
The simplest way to write a summary function is to set
argument summarize_df = TRUE. (For backwards compatibility, this is not the
default.) In this mode, the summary function takes the signature
function(df, ...) where df is the same data frame that would be returned
by exact_extract with fun = NULL.
With summarize_df = FALSE, the function must have the signature
function(values, coverage_fractions, ...) when weights are not used, and
function(values, coverage_fractions, weights, ...) when weights are used.
If the value and weight rasters each have a single layer, the function arguments
will be vectors; if either has multiple layers, the function arguments will
be data frames, with column names taken from the names of the value/weight
rasters. Values brought in through the include_xy, include_area,
include_cell, and include_cols arguments will be added to the values
data frame. For most applications, it is simpler to set summarize_df = TRUE
and work with all inputs in a single data frame.
rast <- raster::raster(matrix(1:100, ncol=10), xmn=0, ymn=0, xmx=10, ymx=10)
poly <- sf::st_as_sfc('POLYGON ((2 2, 7 6, 4 9, 2 2))')
# named summary operation on RasterLayer, returns vector
exact_extract(rast, poly, 'mean')
#> [1] 43.16667
# two named summary operations on RasterLayer, returns data frame
exact_extract(rast, poly, c('min', 'max'))
#> min max
#> 1 25 65
# named summary operation on RasterStack, returns data frame
stk <- raster::stack(list(a=rast, b=sqrt(rast)))
exact_extract(stk, poly, 'mean')
#> mean.a mean.b
#> 1 43.16667 6.525083
# named weighted summary operation, returns vector
weights <- raster::raster(matrix(runif(100), ncol=10), xmn=0, ymn=0, xmx=10, ymx=10)
exact_extract(rast, poly, 'weighted_mean', weights=weights)
#> [1] 43.133
# custom summary function, returns vector
exact_extract(rast, poly, function(value, cov_frac) length(value[cov_frac > 0.9]))
#> [1] 7