GeoVectors: A Linked Open Corpus of OpenStreetMap Embeddings on World Scale
This addresses the problem of heterogeneous and large-scale geographic data for researchers and developers in machine learning and semantic web domains, offering a comprehensive resource, though it is incremental as it builds on existing OSM data.
The paper tackles the challenge of using OpenStreetMap entities in machine learning by creating GeoVectors, a linked open corpus of embeddings that provides latent representations for over 980 million geographic entities across 180 countries, making them accessible for algorithms and semantic applications.
OpenStreetMap (OSM) is currently the richest publicly available information source on geographic entities (e.g., buildings and roads) worldwide. However, using OSM entities in machine learning models and other applications is challenging due to the large scale of OSM, the extreme heterogeneity of entity annotations, and a lack of a well-defined ontology to describe entity semantics and properties. This paper presents GeoVectors - a unique, comprehensive world-scale linked open corpus of OSM entity embeddings covering the entire OSM dataset and providing latent representations of over 980 million geographic entities in 180 countries. The GeoVectors corpus captures semantic and geographic dimensions of OSM entities and makes these entities directly accessible to machine learning algorithms and semantic applications. We create a semantic description of the GeoVectors corpus, including identity links to the Wikidata and DBpedia knowledge graphs to supply context information. Furthermore, we provide a SPARQL endpoint - a semantic interface that offers direct access to the semantic and latent representations of geographic entities in OSM.