Extracting the U.S. building types from OpenStreetMap data

TL;DR

This paper presents a comprehensive U.S. building type dataset derived from OpenStreetMap data, using an unsupervised classification method validated against authoritative sources, aiding urban planning and related fields.

Contribution

It introduces a novel large-scale classification of U.S. buildings into residential and non-residential types using unsupervised learning on OSM data, covering over 67 million buildings.

Findings

High precision for non-residential building classification

High recall for residential buildings

Identified data quality issues due to missing metadata

Abstract

Building type information is crucial for population estimation, traffic planning, urban planning, and emergency response applications. Although essential, such data is often not readily available. To alleviate this problem, this work creates a comprehensive dataset by providing residential/non-residential building classification covering the entire United States. We propose and utilize an unsupervised machine learning method to classify building types based on building footprints and available OpenStreetMap information. The classification result is validated using authoritative ground truth data for select counties in the U.S. The validation shows a high precision for non-residential building classification and a high recall for residential buildings. We identified various approaches to improving the quality of the classification, such as removing sheds and garages from the dataset. Furthermore, analyzing the misclassifications revealed that they are mainly due to missing and scarce metadata in OSM. A major result of this work is the resulting dataset of classifying 67,705,475 buildings. We hope that this data is of value to the scientific community, including urban and transportation planners.