Project 2: A Map is Worth a Thousand Pictures

Design a second project aiming in the computation of a tree species map for the Marburg Open Forest area.

Learning objectives

At the end of your project you should be able to

  • compute land-cover classifications using R packages like caret to build a model for the prediction of the selected tree species classes,
  • discuss the principal logic and required steps of training a machine learning model,
  • understand the importance of appropriate training site selection strategies,
  • discuss strategies on which predictor variables to include in a classification model,
  • assess the overall quality using eyeball and a numerical accuracy assessment method,
  • work efficiently in teams on short-term projects and use collaborative project and software development tools,
  • efficiently document your code and analysis workflow for re-usability and scientific review,
  • communicate your work in a poster presentation and discussion potential next steps for improvement.

Standing on the shoulders of giants and your own feet

You already have collected experience in scientific knowledge generation, team work, and the transparent presentation of results. And do not follow the documentation example below. Build upon it when working on your next project assignment.

Updated: