Building Heights for Cities

Building height is recognized as a critical variable for accurately modeling the relationship between urban density and carbon emissions.This data repository contains pre-processed building height for cities obtained from Che., et al (2024). We re-aggregate the shapefiles to match Global Human Settlement Layers global tiles. The predicted building heights achieve robust predictive performance with reported R^2 values between 0.66 and 0.96 and root-mean-square errors (RMSE) ranging from 1.9 to 14.6 meters across 33 subregionsAdditionally, the selected dataset closely aligns with manually validated reference datasets provided by established entities such as ONEGEO Map, Baidu Maps, the United States Geological Survey (USGS), Microsoft Building Heights, and EMU Analytics (England).Citation:Che, Y., Li, X., Liu, X., Wang, Y., Liao, W., Zheng, X., Zhang, X., Xu, X., Shi, Q., Zhu, J., Zhang, H., Yuan, H., and Dai, Y.: 3D-GloBFP: the first global three-dimensional building footprint dataset, Earth Syst. Sci. Data, 16, 5357–5374, https://doi.org/10.5194/essd-16-5357-2024, 2024.

建筑高度被公认为是精准建模城市密度与碳排放之间关系的关键变量。本数据仓库包含从Che等人（2024）获取的城市预处理建筑高度数据。我们对shapefile文件进行重新聚合，以匹配全球人类住区层（Global Human Settlement Layers）的全球瓦片。预测的建筑高度表现出稳健的预测性能，在33个亚区域中，报告的决定系数（R²）值介于0.66至0.96之间，均方根误差（RMSE）范围为1.9至14.6米。此外，所选数据集与ONEGEO Map、百度地图、美国地质调查局（USGS）、Microsoft Building Heights以及EMU Analytics（英国）等知名机构提供的人工验证参考数据集高度一致。引用：Che, Y., Li, X., Liu, X., Wang, Y., Liao, W., Zheng, X., Zhang, X., Xu, X., Shi, Q., Zhu, J., Zhang, H., Yuan, H., and Dai, Y.：3D-GloBFP：首个全球三维建筑足迹数据集，《地球系统科学数据》（Earth Syst. Sci. Data），第16卷，5357–5374页，https://doi.org/10.5194/essd-16-5357-2024，2024年。