Logo des Repositoriums

Auflistung nach Schlagwort "digital horticulture"

1 - 2 von 2
  • Konferenzbeitrag
    CherryGraph: Encoding digital twins of cherry trees into a knowledge graph based on topology
    (44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft, 2024) Andreas Gilson, Mareike Weule
    CherryGraph is a structural framework for mapping trees into an ontology-based knowledge graph that can be used as database backend for digital twins. Based on the reconstructed 3D topology of scanned trees, information is encoded in a knowledge graph that resembles the real canopy structure of trees. Thus, CherryGraph enables consistent navigation within the branching system of a tree over different time points regardless of natural fluctuations. The resulting knowledge graph can then be queried for arbitrary use cases or aggregated on different hierarchy levels. We demonstrate the potential of CherryGraph by using data of real cherry trees from the 2023 cherry season with exemplary queries that can be extended to include spatial and temporal dimensions for comparing indicators like elongation growth of shoots or tracking the development of other various tree traits over time.
  • Konferenzbeitrag
    For5G: Systematic approach for creating digital twins of cherry orchards
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Meyer, Lukas; Gilson, Andreas; Uhrmann, Franz; Weule, Mareike; Keil, Fabian; Haunschild, Bernhard; Oschek, Joachim; Steglich, Marco; Hansen, Jonathan; Stamminger, Marc; Scholz, Oliver
    We present a systematic approach for creating digital twins of cherry trees in orchards as part of the project “For5G: Digital Twin”. We aim to develop a basic concept for 5G applications in orchards using a mobile campus network. Digital twins monitor the status of individual trees in every aspect and are a crucial step for the digitalization of processes in horticulture. Our framework incorporates a transformation of photometric data to a 3D reconstruction, which is subsequently segmented and modeled using learning-based approaches. Collecting objective phenotypic features from individual trees over time and storing them in a knowledge graph offers a convenient foundation for gaining new insights. Our approach shows promising results at this point for creating a detailed digital twin of a cherry tree and ultimately the entire orchard.