**OSM Building Classification**
This dataset provides a comprehensive dataset with the classification of 67,705,475 buildings across the United States into residential and non-residential categories. The classification uses an unsupervised approach based on OpenStreetMap (OSM) data. The dataset is divided into three main categories: Metropolitan Regions, Micropolitan Regions, and Other Regions. This dataset is intended to serve as a resource for the scientific community.
We changed the format of the files from shapefile to GPKG, contrary to the description in our arXiv preprint.
If you publish a scientific paper that uses this material, please cite the following:
F. de Arruda, H., Reia, S.M., Ruan, S. et al. An OpenStreetMap derived building classification dataset for the United States. Sci Data 11, 1210 (2024). https://doi.org/10.1038/s41597-024-04046-w