Charles M. Russell National Wildlife Refuge Spot Landcover Classification in Relation to Greater Sage Grouse

Description

This landcover raster was generated through a Random Forest predictive model developed in R using a combination of image-derived and ancillary variables, and field-derived training points grouped into 18 classes. Overall accuracy, generated internally through bootstrapping, was 75.5%. A series of post-modeling steps brought the final number of land cover classes to 28.

Resources

Name Format Description Link
0 CSDGM IMPORT ERROR: No digtinfo/formcont https://www.sciencebase.gov/catalog/item/5755d2f1e4b023b96ec1eb7c

Tags

  • montana
  • charles-m-russell-national-wildlife-refuge
  • landcover
  • cmr
  • spot-imagery

Topics

Categories