The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B4-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2022, 53–59, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B4-2022-53-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2022, 53–59, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B4-2022-53-2022
 
01 Jun 2022
01 Jun 2022

INTEGRATING CONCEPTS OF ARTIFICIAL INTELLIGENCE IN THE EO4GEO BODY OF KNOWLEDGE

R. Lemmens1, S. Lang2, F. Albrecht2, E. Augustijn1, C. Granell3, M. Olijslagers4, C. Pathe5, C. Dubois5, and M. Stelmaszczuk-Górska5 R. Lemmens et al.
  • 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, Artificial Intelligence, Machine Learning, Geocomputation, Concept model, Ontology

Abstract. The EO4GEO Body of Knowledge (BoK) forms a structure of concepts and relationships between them, describing the domain of Earth Observation and Geo-Information (EO/GI). Each concept carries a short description, a list of key literature references and a set of associated skills which are used for job profiling and curriculum building. As the EO/GI domain is evolving continuously, the BoK needs regular updates with new concepts embodying new trends, and deprecating concepts which are not relevant anymore. This paper presents the inclusion of BoK concepts related to Artificial Intelligence. This broad field of knowledge has links to several applications in EO/GI. Its connection to concepts, already existing in the BoK, needs special attention. To perform a clean and structural integration of the cross-cutting domain of AI, first a separate cluster of AI concepts was created, which was then merged with the existing BoK. The paper provides examples of this integration with specific concepts and examples of training resources in which AI-related concepts are used. Although the presented structure already provides a good starting point, the positioning of AI within the EO/GI-focussed BoK needs to be further enhanced with the help of expert calls as part of the BoK update cycle.