{"id":366,"date":"2018-05-03T14:34:50","date_gmt":"2018-05-03T12:34:50","guid":{"rendered":"https:\/\/blogs.fu-berlin.de\/reseda\/?page_id=366"},"modified":"2018-09-26T08:15:13","modified_gmt":"2018-09-26T06:15:13","slug":"analyse","status":"publish","type":"page","link":"https:\/\/blogs.fu-berlin.de\/reseda\/analyse\/","title":{"rendered":"Analyse"},"content":{"rendered":"

We will use two possible scenarios in order to show you the possibilities of R when it comes to remote sensing issues:<\/p>\n

    \n
  1. classification<\/strong>: a common land cover classification of one multispectral Landsat 8 scene<\/li>\n
  2. regression<\/strong>: generation of subpixel information based on Landsat 8 data and high resolution reference data<\/li>\n<\/ol>\n

    A complete workflow utilizing various R packages is given in the next sections. <\/p>\n

    \n

    Chapter in a Box<\/h1>\n

    In this chapter, the following content awaits you:<\/p>\n

    Machine Learning Basics<\/strong><\/a>
    \n– familiarize yourself with the basic terms of the ML, e.g., unsupervised vs. supervised, linear vs. nonlinear, parametric vs. non-parametric, overfitting vs. underfitting
    \n    Classification<\/strong><\/a>
    \n– learn how to sample polygons in QGIS
    \n– classify a multispectral Landsat 8 scene using a RF and a SVM into several land cover classes
    \n– test the performance of your classifier via a learning curve
    \n    Regression<\/strong><\/a>
    \n– learn how to prepare reference polygons for regressor training
    \n– perform a Support Vector Regression\n<\/div>\n

    <\/br><\/br><\/p>\n

    \n
    \n