| optim.spatial {BAT} | R Documentation |
Optimization of spatial sampling.
Description
Optimization of sampling site distribution in space based on environmental (or other) variables.
Usage
optim.spatial(layers, n, latlong = TRUE, clusterMap = TRUE)
Arguments
layers |
A SpatRaster object from package terra. |
n |
The number of intended sampling sites (clusters). |
latlong |
Boolean indicating whether latitude and longitude should be taken into account when clustering. |
clusterMap |
Boolean indicating whether to build a new raster with clusters. |
Details
Optimizing the selection of sampling sites often requires maximizing the environmental diversity covered by them. One possible solution to this problem, here adopted, is performing a k-means clustering using environmental data and choosing the sites closest to the multidimensional environmental centroid of each cluster for sampling (Jimenez-Valverde & Lobo 2004)
Value
Either a matrix of cells x clusters (also indicating distance to centroid, longitude and latitude of each cell) or a list with such matrix plus the clusterMap.
References
Jimenez-Valverde, A., & Lobo, J. M. (2004) Un metodo sencillo para seleccionar puntos de muestreo con el objetivo de inventariar taxones hiperdiversos: el caso practico de las familias Araneidae y Thomisidae (Araneae) en la comunidad de Madrid, Espana. Ecologia, 18: 297-305.