发表机构
The World Bank, Global Facility for Disaster Reduction and Recovery; Center for Geospatial Analytics, Clark University; University of Twente; School of Engineering and Applied Science, University of Pennsylvania; School of Architecture and Planning, Morgan State University（世界银行，全球减灾与恢复基金; 克拉克大学地理空间分析中心; 特文特大学; 宾夕法尼亚大学工程与应用科学学院; 摩根州立大学建筑与规划学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究对七个全球建筑数据集在135个区域进行基准测试，发现Overture在矢量精度上最优，WSF Tracker在100米栅格上领先但高估建成区，并建立了可复现的比较基准。
AI 中文摘要
全球建筑和聚落数据集日益支持人口制图、暴露评估、城市监测以及对建成环境的其他分析，然而，跨产品、地理区域、参考数据集、空间尺度和评估方法的比较证据仍然零散。我们对七个全球或近全球产品进行了基准测试，包括Overture Maps、Global Building Atlas、3D-GloBFP、Google Open Buildings 2.5D Temporal (OBT)、Microsoft TEMPO、GHSL和WSF Tracker，并与135个研究区域的统一参考足迹进行了比较。评估结合了检测、几何一致性和总量精度的互补度量，以及对聚落特征的分层分析和关于误差大小和时间对齐的诊断实验。Overture在市级矢量F1中位数上表现最佳（0.786）。栅格排名依赖于分辨率：OBT在10米分辨率下达到最高中位数F1（0.642），而WSF Tracker在100米分辨率下领先（0.862）。然而，WSF Tracker大幅高估了建成区面积，强调在使用栅格产品时，用户必须了解栅格是仅识别建筑物还是包含额外的不透水面。栅格精度随建筑密度持续增加（Spearman ρ = 0.58-0.75），而小型候选建筑在矢量产品中与假阳性不成比例地相关。将WSF Tracker与参考影像进行时间对齐后，平均F1提高了0.060（中位数+0.037），表明在快速增长的地区，所报告的精度是保守的。该研究建立了一个可复现的基准，用于比较不同地理和聚落情境下的异构全球城市和聚落图层数据集。
英文摘要
Global building and settlement datasets increasingly support population mapping, exposure assessment, urban monitoring, and other analyses of the built environment, yet comparative evidence remains fragmented across products, geographic regions, reference datasets, spatial scales, and evaluation methods. We benchmark seven global or near-global products, including Overture Maps, Global Building Atlas, 3D-GloBFP, Google Open Buildings 2.5D Temporal (OBT), Microsoft TEMPO, GHSL, and WSF Tracker, against harmonized reference footprints across 135 study areas. The evaluation combines complementary measures of detection, geometric agreement, and aggregate quantity accuracy, together with stratified analyses of settlement characteristics and diagnostic experiments on error size and temporal alignment. Overture achieved the highest median city-level vector F1 (0.786). Raster rankings were resolution-dependent: OBT achieved the highest median F1 at 10m (0.642), whereas WSF Tracker led at 100m (0.862). However, WSF Tracker substantially overestimated built-up area, emphasizing that when using raster products, it is important for the user to understand whether the raster identifies only buildings or includes additional impervious surfaces. Raster accuracy increased consistently with building density (Spearman \r{ho} = 0.58-0.75), while small candidate buildings were disproportionately associated with false positives in the vector products. Temporally aligning WSF Tracker with reference imagery increased mean F1 by 0.060 (median +0.037), indicating that the reported accuracies are conservative in rapidly growing areas. The study establishes a reproducible benchmark for comparing heterogeneous global urban and settlement layer datasets across geographic and settlement contexts.
