Menu

Loading Events

« All Events

  • This event has passed.

Satellite data analysis & machine learning classification with QGIS – Part 2

May 11 2:00 pm 4:00 pm SAST

This ITU workshop, presented in collaboration with the UN Open GIS Initiative, is the second part of a two-part workshop, with part 1 taking place on 17 April at 14.00 – 16.00.

The workshop introduces participants to the classification of satellite imagery that can be done with QGIS open-source software. It will show participants how to retrieve, process and classify satellite imagery, as well as how to assess performance of machine learning algorithms through error matrix and accuracy indexes.

The workshop will use two QGIS plugins: Semi-automatic Classification Plugin (SCP) and dzetsaka.

  • SCP is used for majority of pre-processing operations such as retrieval of the Sentinel 2 imagery for an area of interest, DOS (Dark object subtraction) atmospheric correction, selection of specific bands for classification, creation of composite and computation of band algebra (i.e. NDVI).
  • dzetsaka is used to detect and classify built-up areas starting from pre-processed satellite imagery with Gaussian Mixture Model, Random Forest and K-Nearest Neighbours machine learning algorithms.

The workshop will also focus on other QGIS functionalities for clipping satellite imagery and creating vector file of training data. Lastly, outcomes of the machine learning algorithm are compared with the global map of human settlements – GHS-BUILT (Sentinel-1) produced by Joint Research Center (JRC) of European Commission to assess their performance.

There are two one-page guidelines for the software requirements, exercise datasets and software downloads required before the workshop.

More info here.

Free

Join the newsletter…

All the latest updates and insights delivered directly to your inbox!