User Tools

Site Tools


L09: Land-cover model training

Things we cover in this session

Once the image segmentation has been finished, it can be used for selecting training areas and subsequently one can prepare the final training data set and train the land-cover classification model.

Things you need for this session

Things to take home from this session

At the end of this session you should be able to

  • compile a training dataset based on polygon training areas and a comprehensive set of raster layers
  • discuss the principal logic and required steps of training a machine learning model
  • train a machine learning model using the R gpm packages


For slide notes, export or printing, please use the options interface of the embedded frame.

courses/msc/msc-phygeo-remote-sensing/lecture-notes/rs-ln-09.txt · Last modified: 2017/01/18 22:13 by tnauss