2026-09-10T09:44:59Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:27564 2026-09-10T05:38:43Z ddc:004 open_access

GeoKG for GeoFM: Neuro-Symbolic Integration of Semantically-Enriched Geospatial-Temporal Data (Short Paper) Moltzen, Kai Banerjee, Debayan Burmester, Julian Ehrenberg, Anna Kohler, Martin Möller, Cedric Pfeifer, Jann Taffa, Tilahun Abedissa Schulz, Hanna Marlene Usmanova, Aida Westphal, Patrick Usbeck, Ricardo GeoKG Foundation Models GeoFM neuro-symbolic Data Integration Solving complex real‑world problems requires integrating heterogeneous data. Although recent Geospatial Foundation Models (GeoFMs) excel at pixel‑level analysis, they make only limited use of the geographic information contained in natural language texts and therefore often lack the semantic context needed for complex geospatial reasoning. This vision paper argues for reconceiving unstructured texts as a core component of a neuro‑symbolic framework that populates a geospatial‑temporal knowledge graph (GeoKG). We outline an architecture in which modality‑specific extractors produce multi‑granular footprints that are fused into a GeoKG, synchronizing symbolic representations with embeddings, geometries, and grid cells. This GeoKG supports geospatial reasoning and provides enriched training data for truly multimodal GeoFMs, for which we pose a set of research challenges. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Kai Moltzen and Debayan Banerjee and Julian Burmester and Anna Ehrenberg and Martin Kohler and Cedric Möller and Jann Pfeifer and Tilahun Abedissa Taffa and Hanna Marlene Schulz and Aida Usmanova and Patrick Westphal and Ricardo Usbeck 2026 Is Part Of LIPIcs, Volume 393, 17th International Conference on Spatial Information Theory (COSIT 2026) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.COSIT.2026.20 urn:nbn:de:0030-drops-275645 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.COSIT.2026.20 eng https://creativecommons.org/licenses/by/4.0/legalcode