Updating and using the EO4GEO Body of Knowledge for (AI) concept annotation

Lemmens, Rob; Albrecht, Florian; Lang, Stefan; Casteleyn, Sven; Stelmaszczuk-Górska, Martyna; Olijslagers, Marc; Belgiu, Mariana; Granell, Carlos; Augustijn, Ellen-Wien; Pathe, Carsten; Missoni-Steinbacher, Eva-Maria; Monfort Muriach, Aida

doi:https://doi.org/10.5194/agile-giss-3-44-2022

Articles | Volume 3

AGILE GIScience Ser., 3, 44, 2022

https://doi.org/10.5194/agile-giss-3-44-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

AGILE GIScience Ser., 3, 44, 2022

https://doi.org/10.5194/agile-giss-3-44-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 3

11 Jun 2022

Updating and using the EO4GEO Body of Knowledge for (AI) concept annotation

Rob Lemmens¹, Florian Albrecht², Stefan Lang², Sven Casteleyn³, Martyna Stelmaszczuk-Górska⁵, Marc Olijslagers⁴, Mariana Belgiu¹, Carlos Granell³, Ellen-Wien Augustijn¹, Carsten Pathe⁵, Eva-Maria Missoni-Steinbacher², and Aida Monfort Muriach³ Rob Lemmens et al.

Show author details

¹Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, The Netherlands
²Department of Geoinformatics, University of Salzburg, Salzburg, Austria
³Institute of New Imaging Technologies (INIT), Universitat Jaume I (UJI), Spain
⁴Spatial Applications Division Leuven, KU Leuven, Belgium
⁵Department of Earth Observation, Friedrich-Schiller-University, Jena, Germany

Keywords: Body of Knowledge, concept model, concept annotation, artificial intelligence

Abstract. The EO4GEO Body of Knowledge (BoK) serves as a vocabulary for the domain of geoinformation and earth observation, supporting the annotation of online resources. This paper presents how the BoK is designed, maintained and improved. We discuss how the BoK content can be extended, using the example of integrating artificial intelligence (AI) concepts and show how annotation is done by adding persistent concept identifiers in the metadata of training materials. This platform allows us to share online information with clarified semantics. A prolonged use necessitates the incentivisation of an active expert community and a further adoption of infrastructure standards.