A. Berquand, D. Dold

Launched in a New Space era, the space economy is experiencing rapid growth with an ever-increasing number of new commercial entrants. In this context, we present an approach based on Natural Language Processing (NLP) and Knowledge Graph Embedding (KGE) to model and analyse the socio-economic landscape of the European space sector. In this prototype study, we present the initial results obtained by extracting information from 3 databases containing information on R&D studies led at the European Space Agency (ESA), and on European companies. This information is merged in a semantically compatible way as a Knowledge Graph (KG). Combining NLP and KGE, we predict new links to complete and clean this KG, enabling novel insights into the integrated databases. The presented results demonstrate the potential of our approach for enhancing ecosystem monitoring, mapping existing capabilities, and identifying technology gaps. Although we obtain encouraging results, we also identify several challenges for adapting such an approach in production, to be solved in future studies.

Deutscher Luft- und Raumfahrtkongress 2023, Stuttgart

Deutsche Gesellschaft für Luft- und Raumfahrt - Lilienthal-Oberth e.V., Bonn, 2023

Conference Paper

englisch

21,0 x 29,7 cm, 7 Seiten

urn:nbn:de:101:1-2023111011564392229564

10.25967/610139

Knowledge graphs, Representation learning

Download - Bitte beachten Sie die Nutzungsbedingungen dieses Dokuments: CC BY 4.0OPEN ACCESS

Berquand, A.; Dold, D. (2023): Modelling the European Space Sector with Knowledge Graphs. Deutsche Gesellschaft für Luft- und Raumfahrt - Lilienthal-Oberth e.V.. (Text). https://doi.org/10.25967/610139. urn:nbn:de:101:1-2023111011564392229564.

10.11.2023