Wie lässt sich aus offenen 🌐 Geodaten ein Mehrwert für Gesellschaft und Wissenschaft gewinnen (und das nicht nur durch Fachleute)? Dieser Frage geht die aktuelle Frühjahrsreihe des IÖR-Forums nach. Alle Veranstaltungen und Informationen 👉 https://www.ioer.de/veranstaltungen/ioer-forum/ioer-reihe-geodaten-nutzbar-und-erlebbar-machen
#IOER_FDZ #GeoData #NFDI
@BERD_NFDI @NFDI @nfdi4earth @konsortswd @saxfdm @a_tack
control #OpenLayers with your hands via webcam
"Map Gesture ControlsControl maps with your hands
Browser-native hand gesture controls for OpenLayers. Powered by MediaPipe. No backend required."
@wesense project is in early stage, but looks promising. A decentralized network of ever free global sense data from citizen networks? Yes please. Worth keeping an eye on.
Spanish startup Xoople is developing a satellite constellation to collect precise physical earth data aimed at feeding into deep learning models. Announced Series B Funding ($130M) and a deal with L3Harris Technologies to begin building sensors for its spacecraft.
Xoople claims it will deliver reliable ground-truth data about the physical world with precise, continuous context and deep time-series measurements with unparalleled quality and global coverage.
https://www.xoople.com/resources/xoople-announces-130m-series-b-to-build-earths-system-of-record-for-the-agentic-era/ #Space #Xoopie #Earth #Data #GeoData #Cloud #Software #Satellite #SpaceCraft #LLMs #AI
*Artigos científicos* 1/2
Estudo interessante @heigit sobre integração #geodados rodoviários assistida por #IA no #OpenStreetMap
Quanto mais correções são feitas com #HumanInLoop, menor #transparência e #rastreabilidade da #QualidadeDosDados
Pessoalmente, sempre me recusei a passar de artesão qualificado para controlador produtos padronizados, mas aqui novo argumento para não introduzir #IA #geodata no #OSM. Solução: #mashup #OSM + dados de IA para preencher lacunas.
https://www.tandfonline.com/doi/full/10.1080/24694452.2025.2589286
*Scientific papers* 2/2
A #lowcost #deeplearning methodology integrating #OpenStreetMap for #urban planning tasks across multiple domains. #OSM #vectors serve as reference masks for #satelliteimagery to enable predictions via #CNN and #GNN. Accuracy >90%.
New #remotesensing products require #vector #geodata. Hence the value of investing in the completeness and consistency of #OSM data
https://www.
nature.com/articles/s41598-026
*Scientific papers* 1/2
Interesting study by @heigit on #AI-assisted integration of road #data into #OpenStreetMap, which shows the more corrections made using #HumanInLoop, the less #transparency and #traceability regarding #DataQuality
Personally, always refused to switch from being a skilled craftsman to a controller of standardized products, but here’s another argument against introducing #AI #geodata into #OSM. Solution: #mashup #OSM + AI data to fill in the gaps.
https://www.tandfonline.com/doi/full/10.1080/24694452.2025.2589286
*Articles scientifiques* 2/2
Une méthodologie #lowcost d'apprentissage profond intégrant #OpenStreetMap pour tâches #urbanisme multidomaines. Vecteurs #OSM servent de masques de référence #imageriesatellite pour prédictions via #CNN et #GNN. Précision >90 %.
Les nouveaux produits #teledetection ont besoin de #geodata #vecteur. D’où intérêt investir dans complétude + homogénéité données #OSM
*Articles scientifiques* 1/2
Étude intéressante de @heigit sur intégration #geodata routière assistée #IA dans #OpenStreetMap qui montre que plus il y a de corrections avec #HumanInLoop, moins il y a de #transparence et #tracabilite de #DataQuality
Perso, toujours refusé de passer statut artisan qualifié à contrôleur produits standardisés, mais argument ici en plus pour ne pas introduire #IA #geodata dans #OSM. Solution : #mashup #OSM + data IA pour combler trous.
https://www.tandfonline.com/doi/full/10.1080/24694452.2025.2589286
Leibniz-IÖR Dresden
Jakob Miksch
Joris Meys
BGDon 🇨🇦 🇺🇸 👨💻
SeverinGeo
Thomas Weibel