\n<\/p>\n
The team \u2014 centered in Ghana but spread across Tel Aviv, Zurich and beyond \u2014 has explored ways to make the project even more useful ever since. \u201cWe operate in a constant hackathon mode: trying new ideas, looking at challenges and limitations and thinking, \u2018OK, how can we solve this?\u2019\u201d says Google Research program manager Abdoulaye Diack. \u201cOne thing we hadn\u2019t been able to capture with the original dataset was how an area evolves over time \u2014 the data was static. And it was information partners were seeking.\u201d<\/p>\n
Commercial satellite image providers tend to prioritize capturing imagery based on demand and profit, leaving large swaths of the Global South \u2014 about 40% of the globe \u2014 without any regular and high-resolution coverage, and some remote villages and informal settlements without any coverage at all. More readily available and frequently updated open-source imagery \u2014 like that taken by the European Space Agency\u2019s Sentinel-2 satellite, which has a global revisit time of every five days \u2014 was long considered too low-resolution to work for the task of building detection.<\/p>\n
Hopeful that this low resolution might be less of a hurdle than they thought, the team decided to try it.<\/p>\n
First, they put a single low-res frame of an area captured by Sentinel-2 into their model and asked it to produce polygons of the buildings on the ground. \u201cThat was a very difficult task, but there was potential,\u201d Abdoulaye says. \u201cSo we asked the model to produce just the building masks \u2014 or raster data made up of binary pixels linked to specific coordinates \u2014 from the image. It did a decent job and we thought: This is doable.\u201d<\/p>\n
About a year later, and after much painstaking iteration on the model, the team released the Open Buildings 2.5D Temporal Dataset last month. Covering 2016 to 2023, it offers an annual snapshot of building presence and counts across much of the Global South, as well as building heights, showing how development, catastrophe and other factors impact cities. Users simply select a region, toggle between years, and watch the world expand and contract in patterns of colorful shapes.<\/p>\n
\u201cAbout 2.5 billion more people could move to cities by 2050, most of them in the Global South \u2014 this could be a real step change for governments and organizations working through that growth,\u201d says Google Research product manager Olivia Graham. \u201cIf a city is planning where to put essential services like healthcare and education, or where to develop infrastructure like water and energy supplies, this dataset shows the areas that are actively growing.\u201d<\/p>\n<\/div>\n