This vector dataset contains information about individual building footprints covering all countries of the European Union (EU27). This is the result of conflating the building footprint polygons available in three datasets, and in the following order of priority: OpenStreetMap, Microsoft GlobalML Building Footprints and European Settlement Map.
Results indicate how DBSM R2023 compares robustly agains cadastral data from Estonia, used as reference area.
The comparison with GHS-BUILT-S, reveals a relative overestimation of the latter, factored by 0.68 at the EU scale for a sound match.
While this dataset only contains the polygon of the building footprint, the aim is to continue to add relevant attributes from the point of view of energy efficiency and energy consumption in building in future versions.
Ana Martinez; Pietro Florio; Cristiano Giovando; Katarzyna Goch (2026): DBSM R2023 - Individual building footprints for EU27 from the hierarchical conflation of OSM, Microsoft Buildings and ESM R2020. European Commission, Joint Research Centre [Dataset] doi: 10.2905/JRC.24QRN70 PID: http://data.europa.eu/89h/60c6b14d-3dda-4034-b461-390dc8ed8665
building footprintsbuilt-upenergy transitionopen dataopen mapsOpenStreetMappan-EU mapssatellite imagery
A free and open-source global
dataset of geographic features, including building footprints
and attributes (downloaded in PBF format)
A freely available dataset of building footprints developed by
Microsoft using machine learning algorithm on very high-resolution satellite imagery.
A raster dataset of built-up areas at 2-meter spatial resolution,
classified using Convolutional Neural Networks from imagery available through the Copernicus services (downloaded in GeoTIFF format).
.svg){kind=icon}
.svg){kind=icon}
.svg){kind=icon}
This paper presents a hierarchical conflation process applied to open datasets for the creation of a seamless pan-European map of building footprints in vector format, named Digital Building Stock Model – DBSM. The objective is the sequential addition of input components (which currently include OpenStreetMap, Microsoft GlobalML Building Footprints, European Settlement Map), taking into account their limitations, and aiming at the highest level of completeness possible, for planning and evaluating energy transition scenarios at the EU level. The results indicate how DBSM compares robustly against cadastral data from Estonia, used as reference area. The comparison of DBSM with GHS-BUILT-S, a 10 metres resolution grid with worldwide coverage that encodes the built-up surface in each pixel as derived from Sentinel-2 imagery for the year 2018, reveals a relative overestimation of the latter, factored by 0.68 at the EU scale for a sound match.
