GlobalBuildingAtlas: An Open Global and Complete Dataset of Building Polygons, Heights, and LoD1 3D Models

Paper

1. Overview

GlobalBuildingAtlas is a dataset providing global and complete coverage of building polygons (GBA.Polygon), heights (GBA.Height), and Level of Detail 1 (LoD1) 3D building models (GBA.LoD1).

It is the first open dataset to offer high-quality, consistent, and complete building data in 2D and 3D at the individual building level on a global scale.

⚠️ Note:

• This repository corresponds to Part II of the GlobalBuildingAtlas dataset, including PART II of the GBA.Polygon dataset containing building polygons from sources other than ODbL-licensed ones, and GBA.LoD1 provided in JSON format and links all building polygon features in GBA.Polygon.
• These building polygons are from Google Open Buildings, CLSM or our own derivation.
• This repository (GBA.LoD1) is distributed under the CC BY-NC 4.0 license.
• For the Part I of the dataset, please refer to HuggingFace.
• For GBA.Height, please refer to mediaTUM.

More details: https://github.com/zhu-xlab/GlobalBuildingAtlas

---

2. Format and Structure

File names reflect the geographic extent in EPSG:4326 (WGS84):

• 5° × 5° tiles:
  {e/w}{lon_min}_{n/s}{lat_max}_{e/w}{lon_max}_{n/s}{lat_min}

---

3. How to Use the Data

1. Access the representative dataset
   • Either in the representative/ folder of this repository, or via mediaTUM.
2. Identify tiles overlapping your region of interest (RoI)
   • For polygons and LoD1 models: use lod1.geojson to find the intersecting tiles in GBA.Polygon or GBA.LoD1.
   • For heights: use height_zip.geojson and height_tif.geojson to find intersecting tiles in GBA.Height.
3. Download required tiles

   • ODbL polygons: download from HuggingFace and save under:

     ./ODbLPolygon
     

   • LoD1 polygons and other data: download from this repository, and save under:

     ./Polygon
     ./LoD1
     

4. Run the enrichment script

   python produce_lod1.py
   

   • You may also specify folder paths at your choice.

   python produce_lod1.py \
       --odbl_root /path/to/odbl \
       --polygon_root /path/to/polygon \
       --json_root /path/to/json \
       --output_root /path/to/output
   

   • The script will read the two GeoJSON folders and the JSON folder, merge the properties, and add height and var fields.
5. Output
   • LoD1 GeoJSON files will be written under

   ./LoD1_GeoJSON
   

   or the folder you specified.
   • If you are only interested in GBA.Polygon, you can ignore the height and var fields.

• ⚠️Users may combine these datasets for analysis or downstream applications, but doing so may create license implications.
• ⚠️It is the responsibility of each user to ensure that their use complies with the respective licenses.
• ⚠️This repository does not provide legal advice; users should review the original licenses and, if necessary, consult legal counsel.

---

4. License

The building polygon and LoD1 data in this repository (GBA.LoD1) are licensed under the
CC BY-NC 4.0 license — https://creativecommons.org/licenses/by-nc/4.0/

---

5. Citation

If you find this dataset useful for your work, please cite the following publication.

@Article{globalbuildingatlas,
        AUTHOR = {Zhu, X. X. and Chen, S. and Zhang, F. and Shi, Y. and Wang, Y.},
        TITLE = {GlobalBuildingAtlas: an open global and complete dataset of building polygons, heights and LoD1 3D models},
        JOURNAL = {Earth System Science Data},
        VOLUME = {17},
        YEAR = {2025},
        NUMBER = {12},
        PAGES = {6647--6668},
        URL = {https://essd.copernicus.org/articles/17/6647/2025/},
        DOI = {10.5194/essd-17-6647-2025}
}

---