Skip to Content

Third Party Services Catalog

CREODIAS is the work of partners listed below. For more information on each partner, we invite you to visit their websites.

Filter

Clear All
Partner Type

Filter

Clear All
Partner Type

Add to the Catalog

If you are interested in becoming a partner, and have your information visible in this section, please click the button below

Third Party Services Catalog

CREODIAS is the work of partners listed below. For more information on each partner, we invite you to visit their websites.

Back

S2GLC

Member Since 2019

logo

S2GLC (Sentinel-2 Global Land Cover) is a project funded by the European Space Agency and carried out by a consortium composed of CBK PAN (Space Research Centre of Polish Academy of Sciences) – a project leader and IABG mbH, EOXPLORE UG and the University of Jena.

The goal of the project was to develop a classification methodology with a high degree of automation, ready to be used for global land cover mapping based on Sentinel-2 imagery. According to the developed methodology each Sentinel-2 tile is classified separately using a set of multi-temporal images. To maintain the 10 m resolution of Sentinel-2 imagery a pixel-based approach has been chosen. Multi-temporal images are classified separately with random forest (RF) classifier applying training samples selected randomly from existing low resolution databases. The final result is calculated using a dedicated aggregation procedure. This aggregation analyses, for each individual pixel, all multi-temporal results together with their probability scores returned by RF classifier. The last step of the classification workflow is the post-processing applied mostly to the pixels classified with low probability.

The developed methodology was used for classification of the major area of the European continent in the CREODIAS infrastructure. Adaptation of the S2GLC classification method, including modification of the classification legend, was based on tests conducted within selected Sentile-2 tiles representing various bio-geographical regions of Europe. According to the rules established in the initial part of the S2GLC project, training samples were derived from existing land cover databases, namely CORINE LC and High Resolution Layers.  Sentinel-2 satellite images and auxiliary data were processed without any visual interpretation work using dedicated software developed by CBK PAN.

Over fifteen thousand of Sentinel-2 images, for the year 2017, representing 815 Sentinel-2 tiles have been processed to map the selected area of Europe. Validation of the final map was performed based on a large set of 52 000 randomly distributed samples representing 55 Sentile-2 tiles spread across Europe. Distribution of these tiles allowed to perform validation on both European and country level. The overall accuracy (OA) of the complete map with 13 land cover classes was estimated to be over 86%. The accuracy assessment on a country level revealed very good quality of the land cover map with majority of countries exceeding 80% of OA.

More information can be found at the S2GLC project website: http://s2glc.cbk.waw.pl

We invite users to visit our Finder.CREODIAS.eu to search and download data from the S2GLC collection.

--

Space Research Centre of the Polish Academy of Sciences (CBK PAN) was established in 1977. CBK PAN is one of the main Polish research institutes in the field of space science and space engineering. Its research activities include space physics, astronomy, planetary geodesy, remote sensing, and hardware development. CBK PAN participated in numerous international space science missions and is involved in various research and application projects. The Earth Observation Department conducts research in the field of satellite and aerial  image processing and GIS applications. The research staff of the Department is experienced in remote sensing including  processing of optical, SAR  and LiDAR data. The Department specialises in land cover / land use classification using both pixel and object-oriented techniques, change detection, agricultural applications, satellite climatology, advanced environmental GIS analysis and programming (development of algorithms for image processing).