Comparison of Urban Mapping Methods using SAR - Second Edition

Due to the high level of interest, we are offering again the "Comparison of Urban Mapping Methods using SAR" remote F2F training session.

In response to the current situation and restrictions due to the COVID-19 pandemic, this hands-on training will be held remotely. The session will consist of a live demonstration, followed by a time to repeat the exercise on your pre-configured RUS Virtual Machines with live support from the RUS EO expert team. The session will close with live Q&A.

Please note that the RUS Copernicus Virtual Machines used for this training course can only be provided to citizens/residents of the Copernicus programme member countries (EU plus Iceland and Norway).

Background

As the world is facing a large increase in population, reliable information on urban areas is required to assist and help in the decision-making process. Different methods can be used to gather this information, but satellite earth observation offers a suitable approach based on the coverage and type of data that are provided.

A few years ago, the European Union (EU) started an ambitious program, Copernicus, which includes the launch of a new family of earth observation satellites known as the Sentinels. Amongst other applications, this new generation of remote sensing satellites will improve the observation, identification, mapping, assessment, and monitoring of urban areas and their dynamics at a range of spatial and temporal resolutions.

In this exercise we will employ RUS Copernicus Virtual Machines to process a multi-temporal dataset of Sentinel-1 SLC products and derive coherence (in SNAP), which will be used later to map urban areas over a region of interest in Germany. For that, we will use different methods using Python scripts provided in JupyterLab (basic thresholding, unsupervised classification - clustering, supervised classification - Support Vector Machine) and compare their results. Finally, we will assess accuracy by comparing our results with the Global Urban Footprint - DLR dataset.

Schedule

29 October 2020 - 9:00 AM - 15:30 PM CET

09:00 - 09:15 - RUS Copernicus introduction

09:15 - 11:45 - Demo Comparison of Urban Mapping Methods using SAR

11:45 - 15:00 - Time to repeat the exercise on your own RUS VM (with Live Chat support) and have lunch! (Keep in mind the time required to repeat the exercise is 2 to 3 hours)

15:00 - 15:30 - Live Q&A session

Equipment

Attendees will need a laptop (not possible from mobile) and will be provided with access to the RUS platform Virtual Machine (information on how to request and access the VM will be provided by e-mail).

Cost & Participation

Attendance to the training course is free of charge.

Audience & Selection

Space is limited to 20 Participants. Confirmation e-mails will be sent to selected attendees on 22 October 2020.

Please note that the RUS Copernicus Virtual Machines used for this training course can only be provided to citizens/residents of the Copernicus programme member countries (EU plus Iceland and Norway).

Venue & Room

Online training – GoToWebinar platform

Training date

Thursday 29th of October 2020