Scribd
Upload
87 views

Workshop Satellite Data Analysis and Machine Learning Classification With QGIS

This document provides information about a workshop on satellite data analysis and machine learning classification using QGIS. The workshop will demonstrate how to retrieve, process, and classify satellite imagery from Sentinel-2 using QGIS plugins. It will also show how to assess machine learning algorithms' performance using error matrices and accuracy indexes. Participants will practice preprocessing imagery, classifying built-up areas using algorithms like random forest, and comparing results to the GHS-BUILT dataset to evaluate accuracy. The full-day workshop is divided into two sessions covering introduction/preprocessing and processing/assessment.

Uploaded by

hasto
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
87 views

Workshop Satellite Data Analysis and Machine Learning Classification With QGIS

This document provides information about a workshop on satellite data analysis and machine learning classification using QGIS. The workshop will demonstrate how to retrieve, process, and classify satellite imagery from Sentinel-2 using QGIS plugins. It will also show how to assess machine learning algorithms' performance using error matrices and accuracy indexes. Participants will practice preprocessing imagery, classifying built-up areas using algorithms like random forest, and comparing results to the GHS-BUILT dataset to evaluate accuracy. The full-day workshop is divided into two sessions covering introduction/preprocessing and processing/assessment.

Uploaded by

hasto
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Workshop: Satellite data analysis and Machine Learning classification with QGIS

Gorica Bratic and Maria Antonia Brovelli


Politecnico di Milano Department of Civil and Environmental Engineering - Milano (Italy)

The scope of the workshop is to introduce how classification of satellite imagery can be done with QGIS
(https://www.qgis.org/en/site/) by showing 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 involves two QGIS plugins: Semi-automatic Classification Plugin (SCP) and dzetsaka. SCP is
used for majority of preprocessing 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., Normalized Difference Vegetation Index
(NDVI). The dzetsaka plugin is used to detect and classify built-up areas starting from preprocessed satellite
imagery with Gaussian Mixture Model, Random Forest and K-Nearest Neighbors machine learning
algorithms.
Besides the two plugins, some core QGIS functionalities and are included in the workshop 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. Before being used for
assessing algorithms’ performances, GHS-BUILT (Sentinel-1) is adapted to coordinate reference system,
resolution, and classes of classification outcomes. Adaptation of GHS-BUILT (Sentinel-1) involves many
isolated operations (reprojection, tile merging, resampling, and reclassification). For this reason, the QGIS
Graphical Modeler is introduced in the exercise because it allows automation of chain of operations.
Besides the adaptation of GHS-BUILT (Sentinel-1), the computation of error matrix and accuracy indexes for
each classification outcome are integrated with the Graphical Modeler too.

Requirements for the exercise (guides for installation will be provided):

• QGIS Desktop 3.10.x with GRASS


• scikit-learn library for Python3 in QGIS
• Account on Copernicus Open Access Hub (for retrieving Sentinel-2 imagery)

Dataset for the exercise:


• Vector of bounding box of region of interest
• Training dataset
• GHS-BUILT (Sentinel-1) data in the region of interest
• Satellite imagery (Since download of imagery takes a lot of time, we will provide satellite imagery to the
participants, but however the procedure of download will be explained)

Schedule. The workshop is organized in two parts of about 2 hours each (the pace of the workshop is slow
in such a way to give time to “average” attendees the time of following and doing the exercise.
• introduction and pre-processing
• processing/assessment

You might also like