First high-resolution 3D map covering all of Earth’s 2.75 billion buildings unveiled

Scientists in Germany have, for the first time, created the most comprehensive digital representation of the world s man-made environment by compiling a massive 3D, high-resolution dataset containing 2.75 billion buildings. The GlobalBuildingAtlas, developed by a research team at the Technical University of Munich (TUM), sets the stage for advanced climate research and the implementation of the UN Sustainable Development Goals.

Funded by the ERC Starting Grand, the dataset builds on satellite imagery from 2019. It also achieves a 30 times finer resolution than previous global maps, which topped out at about 1.7 billion buildings. Xiaoxiang Zhu, PhD, a professor and holder of the Chair of Data Science in Earth Observation at TUM, who led the project, said that the map is expected to support more accurate urbanization, disaster management, and infrastructure models, and help cities become more inclusive and resilient.

Earth s buildings in 3D Each building in the atlas is modeled at a 9.8-by-9.8 feet (three-by-three meters) resolution. This, according to the team, provides sufficient precision to estimate height, volume, and structural density. Moreover, 97 percent of all the structures mapped are classified as Level of Detail 1 (LoD1) models.

These are simplified three-dimensional representations that capture each building s basic geometry. Although not as detailed as higher LoD levels, these can still be incorporated at scale into computational models. Zhu noted that they offer a solid foundation for urban structure analysis, volume calculations, and infrastructure planning. Xiaoxiang Zhu, PhD, uses satellite data to analyze developments on Earth.Credit: Juli Eberle / TUM / ediundsepp Gestaltungsgesellschaft Unlike earlier datasets that focused on cities in wealthy regions, the new map provides broad coverage of areas historically missing from digital maps, including Africa, South America, Southeast Asia, and rural areas around the globe.

Zhu explained that 3D building data reveals urbanization and poverty far more accurately than 2D maps. With 3D models, we see not only the footprint but also the volume of each building, enabling far more precise insights into living conditions, she said.

A digital snapshot Zhu also noted that the map introduces a new metric called building volume per capita. This global indicator measures total building mass per capita. In addition, it reveals social and economic disparities.

This indicator supports sustainable urban development and helps cities become more inclusive and resilient, she concluded in a press release. The 3D building data should provide a precise basis for planning and monitoring urban development. It is also aimed at helping cities take targeted steps to create more inclusive and equitable living conditions. These include adding housing or public facilities in densely populated, underserved areas.

Meanwhile, the map is also crucial for climate adaptation, as it improves models of energy demand, CO2 emissions, and green infrastructure planning. In addition, it improves disaster prevention through quicker assessment of natural event risks.

The team noted that the data is already drawing significant interest. The German Aerospace Center (DLR) is already exploring its use for the International Charter: Space and Major Disasters, which coordinates satellite data for emergency response worldwide.