Preparing training points for remote sensing algorithm

Usage

get_lu_points(
  df,
  year,
  lookup,
  lu_constant = c(),
  nb_pts = 100,
  col_name = "type"
)

Arguments

df: sf data.frame with land use. "type" column should be present.
year: numeric value, year of land use.
lookup: dataframe with "lc1" column for numeric codes and "type" column for text.
lu_constant: vector of strings with land uses to be kept constant in land use (i.e. water, urban areas, etc.)
nb_pts: numeric, number of points per land use/crop class. Optional, default 100.
col_name: string with name of column to be used representing type of crops/land use. Optional, default "type".

Value

sf data.frame with point input for remote sensing training algorithm.

Examples

if (FALSE) {
library(sf)
##Loading land use/crop layer
lu_path <- system.file("extdata", "GIS/lu_layer.shp", package = "svatools")
lu <- st_read(lu_path,  quiet = TRUE)
##Preparing lookup table
lookup <- data.frame(lc1 = seq(1:length(unique(c(lu$type)))), 
type = unique(c(lu$type)))
lu_constant <- c("fesc", "orch", "frst", "frse", "frsd", "urld", "urhd", 
"wetl", "past", "watr", "agrl")
##Getting training points
pts <- get_lu_points(lu, 2021, lookup, lu_constant)
}