User Tools

Site Tools


W10-1: Model improvement

Once the new land-cover prediction has been finished, it is time again for a qualitative and quantitative evaluation and eventually for some improvement steps.

After completing this worksheet you should be able to design and perform a workflow for enhancing the quality of a land-cover prediction.

Things you need for this worksheet

  • R — the interpreter can be installed on any operation system. For Linux, you should use the r-cran packages supplied for your Linux distribution. If you use Ubuntu, this is one of many starting points. If you use Windows, you could install R from the official CRAN web page.

  • R Studio — we recommend to use R Studio for (interactive) programming with R. You can download R Studio from the official web page.

  • Git environment for your operating system. For Windows users with little experience on the command line we recommend GitHub Windows.

  • your deliveries from W09-3: Model training

Learning log assignments

8-) As always, please add these entries to your today's learning log in the beginning of your Rmd file you will use to push to your GitHub classroom.

  • Favorite aspect of the session (if any)
  • Superfluous aspect of the session (if any)
  • Eureka effect (if any)
  • Links to what I've learned so far (if any)
  • Questions (if any)

As today's special, please complete the following assignment:

:-\ Please evaluate the quality of the land-cover prediction and - depending on potentially identified deficits - come up with a workflow which might lead to a improvement of the classification map.

:-\ Please implement the improvement in an R script or use any kind of GIS software for this

:-\ Please include one sentence summarizing the initial and final classification quality, a bullet point list describing your intended workflow and a screenshot of (a detail of) the modified classification into an Rmd script, update (i.e. commit) it and publish (i.e. push) it to the GitHub classroom.

courses/msc/msc-phygeo-remote-sensing/worksheets/rs-ws-10-1.txt · Last modified: 2017/01/26 15:51 by tnauss