An official website of the European Union How do you know?      
European Commission logo
JRC Publications Repository Menu

Next Generation Mapping of Human Settlements from Copernicus Sentinel-2 data

cover
leveraging cloud computing, machine learning and earth observation data
Since the advent of the openly accessible Sentinel satellite data as part of the Copernicus programme of the European Commission and ESA, massive amounts of satellite data have brought disruptive changes in Earth observation data management and analysis. In the context of the Global Human Settlement Layer activities, the Copernicus Sentinel-2 mission offers new opportunities for mapping human settlements over large areas and for the update and improvement of the Global Human Settlement Layer datasets and information layers. Concurrently, state-of-the-art machine learning algorithms and cloud computing infrastructures have become available with a great potential to revolutionize the image processing of satellite remote sensing. Within this context, this study explores the feasibility of refactoring the existing GHSL workflows and applications into the cloud computing paradigm by leveraging the functionalities offered by the Distributed Web Platform WASDI combined with advanced machine learning methods for image processing and classification. In this report, we summarize the lessons learnt using WASDI for mapping of built-up areas from Sentinel data. We present the advantages of both convenient and powerful workflow management and cloud scalability and the experiences gained and challenges using the WASDI platform. The experiments showed that porting of the GHSL workflows to DIAS can be facilitated by the WASDI interface. When testing two different cloud providers, large differences in the time for accessing the Sentinel-2 data and downloading it were observed and had the largest impact on the performances of the workflows.
2020-09-02
Publications Office of the European Union
JRC121560
978-92-76-21441-0 (online),   
1831-9424 (online),   
EUR 30344 EN,    OP KJ-NA-30344-EN-N (online),   
https://publications.jrc.ec.europa.eu/repository/handle/JRC121560,   
10.2760/54360 (online),   
Language Citation
NameCountryCityType
Datasets
IDTitlePublic URL
Dataset collections
IDAcronymTitlePublic URL
Scripts / source codes
DescriptionPublic URL
Additional supporting files
File nameDescriptionFile type 
Show metadata record  Copy citation url to clipboard  Download BibTeX
Items published in the JRC Publications Repository are protected by copyright, with all rights reserved, unless otherwise indicated. Additional information: https://ec.europa.eu/info/legal-notice_en#copyright-notice