TAGS

There are no tags associated with this article.

New features on CREODIAS Finder

We managed to implement new features for CREODIAS Finder with our recent update. 

Since launch, it has been always possible to search through the CREODIAS API for products based on the timeliness criteria widely used in collections like Sentinel-1 or Sentinel-3, and now this feature is available also in the UI. The user can now limit the results of the query to the NRT or STC products by simple selection from the drop-down menu.

Another new feature in the UI is the orbit number criteria enabled for the Sentinels. Now following selectors are available:

  • Sentinel-1 and Sentinel-2: Relative Orbit Number
  • Sentinel-3: Relative Orbit Start
  • Sentinel-5P: Absolute Orbit Number

Head over to the CREODIAS Finder to find out about the changes yourself.


CREODIAS at the 25th MARS Conference in Prague

The Joint Research Centre (JRC) of the European Commission, in collaboration with its Directorate-General for agriculture and the Czech Republic paying agency for agriculture (SZIF), organises the 25th MARS conference in Prague on 26-28 November 2019.

The annual conference provides a platform to present and discuss EU countries’ experiences and general observations regarding the integrated administration and control system (IACS), including developments in shared management of EU farmers’ dossiers.

This year it will be the 25th edition and therefore agenda will take into account this milestone.

The provisional topics of the 25th conference are:

    - the state of the technical guidance on IACS

    - the development of technologies and procedures for ‘checks by monitoring’

    - enhancing the CAP’s environmental and climate performance via the strategic plans

    - strengthening the pro-active role of the farmer

    - IACS data sharing solutions

CREODIAS delegation is represented by CloudFerro, and is on-site for 3 days with a booth. During this time, we shall present our platform, CloudFerro's cloudcomputing capabilities, showcase case studies and help in the demonstation of Sen4CAP.


CREODIAS to support Copernicus Hackathon DLR Berlin 2019

The observation of the Earth from space is an important task of space travel. It provides data for environmental protection, climate monitoring, assessment of natural disasters and other social tasks. Coding Copernicus is the hackathon for all space enthusiasts, developers, programmers, computer scientists, graphic artists and all those who have always wanted to work with satellite data.

The aim of hackathons is to develop new ideas for the use of satellite data. Based on Copernicus data, teams will work within within 24 hours on one of the 3 challenges on the topics of sustainability, efficiency or innovation. During the whole time, the participants will be mentored by experts from the field, and will have the fantastic opprotunity to use CREDIAS cloud environment to process their data.

Link to the event: https://coding-copernicus.de/


Oi-X Green Mobility hackathon powered by CREODIAS

The CREODIAS platform gladly supports hackathons and IT challenges that use Earth Observation data from Copernicus. We offer access to our data repositorium as well as our powerful cloud computing environment so that such hackathons can take place in a swift manner.

Last week, Oi-X Green Mobility took place Lyngby, Demmark. Among the key tasks were:

 - focus on personal transport from a-b on a day-to-day basis connected to a health perspective

 - use satellite data for research to analyze infrastructure related perspectives on green mobility.

The list of challenges are available here

Dates:

  • Oi-X Info Lunch & Webinar: 09. October 2019
  • Oi-X Developer Weekend: 25-27 October 2019   
  • Oi-X Finals: 06. November 2019

S2GLC operating on CREODIAS

Sentinel-2 Global Land Cover (S2GLC) project, founded by ESA was implemented in 2016 - 2019 by a consortium led by CBK PAN together with three partners: IABG, EOXPLORE and the University of Jena. The project was divided into two phases: Development of LC classification on a global scale and LC classification of Europe.

The goal of Phase 1 was to develop the classification methodology ready to use for the global LC mapping based on Sentinel-2 images. According to the developed methodology each Sentinel-2 tile has been 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 have been classified separately with Random Forest (RF) classifier applying training samples selected randomly from low resolution databases. The final result has been calculated using a dedicated aggregation procedure. This aggregation analyses, for each individual pixel, all multi-temporal results together with their prediction scores returned by RF classifier. The last step of the classification workflow was post-processing applied mostly to the pixels classified with low probability. The developed classification procedure was tested on five study areas: the whole territory of Germany and Italy and three other test sites in China, Columbia and Namibia.

The main objective of Phase 2 of the project was performing LC classification over a major area of the European continent in the CREODIAS  infrastructure. For this purpose, the developed methodology was adjusted to the European landscape and restructured to  full automation of all processes. The classification method and legend established in the initial part of S2GLC project has been also adapted to European conditions. Training samples have been derived from existing LC databases – CORINE LC and High Resolution Layers.  

All the classifications were carried out on the CREODIAS platform. Over fifteen thousands of Sentinel-2 images representing 815 Sentinel-2 tiles have been processed using a dedicated software developed by CBK PAN. Validation of the final map was performed based on a large set of 52 000 randomly distributed samples. The overall accuracy (OA) of the complete map with 13 LC classes was estimated to be over 86%  and 89% for the legend reduced to 10 classes.

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

 

--

Example of S2GLC, as seen in CREODIAS promotional materials