news photo
  • by LandSense team
  • 25.09.2017
  • Conference, Presentation

How Crowdsourcing EO datasets improves cloud detection algorithms and land cover change – LandSense at EO Open Science 2017

Matej Aleksandrov from SINERGISE gave a Lightning Talk explaining the collaborative and innovative research, undertaken with IIASA, that engages the public in an initiative involving ESA’s Sentinel-2 satellite imagery.

The initiative tries to tackle cloud cover, one of the major issues with automatic or semi-automatic land change algorithms. While high resolution Sentinel-2 data is available at a high revisit time, clouds are affecting the performance of current land change detection algorithms. Using a number of tools developed at IIASA, and the Sentinel Hub services provided by SINERGISE, which allow for fast access to the entire global archive of Sentinel-2 data, the aim of this research is to obtain a large data resource of curated cloud classifications. The resulting dataset will be published as open data and made available through the Geopedia platform.

In his talk, Matej introduced the interested audience to this topic and explained how the crowdsourcing-based approach will allow improving EO datasets in a rapid and efficient manner. For those who missed this talk, abstract and video are available on the EO Open Science channel.