Global building maps compared for accuracy in different cities
A comparative assessment of global building and settlement datasets across geographic and settlement contexts
Computer Vision and Pattern Recognition
Summary
Maps of buildings and settlements around the world are important for many uses, like tracking population or city growth. The authors compared seven popular global building maps to see how well they match real city shapes and sizes. They found some maps work better in certain conditions, like different map resolutions or city sizes. This study helps users pick the right map and understand the strengths and limits of each dataset.
What this means in practice
- •For urban planners: Choose the most accurate building dataset for urban growth and infrastructure planning depending on resolution and city size.
- •For disaster risk managers: Use benchmarks of building map accuracy to improve exposure assessments and emergency response planning in different regions.
- •For insurance analysts: Integrate the most reliable global building datasets into models estimating property risk and insured asset values worldwide.$Commercial implications: Enables sale of risk assessment products using superior building data aligned with the latest accuracy benchmarks.
Authors
Rufai Omowunmi Balogun, Caroline Margaux Gevaert, Capucine Riom, Derrick Mirindi, Aaron Opdyke, Hamed Alemohammad, Pierre Chrzanowski, Edward Charles Anderson
Abstract
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.