Machine learning algorithms and their use for detection of objects in satellite images




  • Why is field boundaries detection important for agriculture?
  • What are current emphasis on AI in relation to satellite data?
  • What  ML algorithms can be used for land cover classification?
  • Learn more about Using ML for detection of Land Use Objects 
  • Introduction to datacubes, OGC coverages, coverage services, rasdaman, python API,
  • Services available for both Dubrovnik INSPIRE hackathon and Kampala INSPIRE hackathon challenges.

What: In this webinar we will explore possible machine learning algorithms and artificial neural networks that can be used for field boundaries detection from Sentinel 2 or Landsat images. Relevance to several of the Dubrovnik INSPIRE hackathon challenges as well as challenges of the Kampala INSPIRE hackathon will be highlighted.

Why: Accurate information on field boundaries is very important input for many reasons: eg. having accurate information on crop types and boundary defining a given soil block, we can for example determine the yield potential or the amount of fertilizer needed for given type of crop very precisely.

One of the possible ways is to exploit the potential of satellite imagery (Sentinel 2 or Landsat images), which provide a wealth of information about Earth’s surface and are available as open data. In conjunction with machine learning algorithms, we can get very interesting inputs for precision agriculture.

Who (is the webinar for): Academia & Research Researchers and Innovators who are engaged with solution of challenges related to AI and satellite images. Farmers’ associations and agricultural companies. Any possible participant of the Kampala Hackathon, who is considering his/her participation in this challenge

About Your Presenters

Peter Baumann is professor of Computer Science at Jacobs University Bremen and CEO & founder of rasdaman GmbH, Bremen. He has contributed to pioneering Array Databases (data models and query languages, storage and query optimization, architectures, applications such as in the earth, space, and life sciences) and advancing standardization of spatio-temporal geo services (OGC, INSPIRE, ISO) and Array SQL (ISO). Peter has been working close to the borderline between scientific innovation and industrial application. When at Technical University Munich, his work emerged into what now is his core topic: flexible, efficient services on large, multi-dimensional raster data sets. Peter architected rasdaman ("raster data manager"), the world's first Array Database System which is fully implemented and in operational use. The underlying concepts have been patented in Europe, USA, and Canada. Doing applications in Earth and life sciences brought Peter into geo service standardization. In OGC he is leading several working groups, and he is editor of OGC's Big Data standards suite, WCS, and the OGC Web Coverage Processing Service (WCPS) datacube query language. In ISO, Peter initiated Array SQL now being co-editor of the specification.

Peter Baumann

Peter Baumann

Professor Jacobs University Bremen, and CEO Rasdaman GmbH

Hana Kubickova graduated in Geomatics at Faculty of Applied Sciences, the University of West Bohemia in Pilsen in 2019 with an Ing. degree (eq. to MSc).. She is employed as a project and management support at Plan4all. Currently she is also involved in the STARGATE project and conducts research related to artificial intelligence and its use in precision agriculture.

Hana Kubickova

Hana Kubickova

Project Manager, Plan4all

Jan Chytrý is a student of Geoinformatics at Masaryk University, Brno, Czech Republic. He has recently focused on remote sensing and image classification and has experience with programming and data analysis. He is currently working on his thesis about enhancing land use/land cover from earth observation data.

Jan Chytry

Jan Chytry

Student of geoinformatics, Masaryk University Brno

Bente Lilja Bye has been a member of the GEO community since 2004, engaged both as representative in the GEO plenary, in committees and contributing to the GEO Work Programme, and currently represents Norway on the GEO Programme Board. Bente runs a small research and consultancy company, BLB, focusing on transforming Earth observation data to information and knowledge for societal benefit. She is responsible for Communication, Dissemination and Assessment as partner in NextGEOSS.

Bente Lilja Bye 150

Bente Lilja Bye CEO, BLB & webinar host on behalf of Plan4all