F de Arruda Henrique, Reia Sandro M, Ruan Shiyang, Atwal Kuldip S, Kavak Hamdi, Anderson Taylor, Pfoser Dieter
Geography and Geoinformation Science, College of Science, George Mason University, 4400 University Dr., Fairfax, 22030, VA, USA.
Center for Social Complexity, College of Science, George Mason University, 4400 University Dr., Fairfax, 22030, VA, USA.
Sci Data. 2024 Nov 9;11(1):1210. doi: 10.1038/s41597-024-04046-w.
Building classification 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 presents a comprehensive dataset by providing residential/non-residential building classification covering the entire United States. We developed a dataset of building types based on building footprints and the available OpenStreetMap information. The dataset is validated using authoritative ground truth data for select counties in the U.S., which shows a high precision for non-residential building classification and a high recall for residential buildings. In addition to the building classifications, this dataset includes detailed information on the OpenStreetMap data used in the classification process. 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.
建筑分类对于人口估计、交通规划、城市规划和应急响应应用至关重要。尽管此类数据至关重要，但往往难以获取。为缓解这一问题，本研究通过提供覆盖美国全境的住宅/非住宅建筑分类，呈现了一个综合数据集。我们基于建筑占地面积和可用的OpenStreetMap信息开发了一个建筑类型数据集。该数据集使用美国部分县的权威地面真值数据进行了验证，结果表明非住宅建筑分类具有高精度，住宅建筑具有高召回率。除了建筑分类外，该数据集还包括分类过程中使用的OpenStreetMap数据的详细信息。这项工作的一个主要成果是得到了一个对67,705,475栋建筑进行分类的数据集。我们希望这些数据对科学界，包括城市和交通规划者有价值。
