![\"\"](\"https:\/\/static.euronews.com\/website\/images\/logos\/logo-euronews-stacked-outlined-72x72-grey-9.svg\"){kind=logo}
\n ADVERTISEMENT<\/p>\n
\n ADVERTISEMENT<\/p>\n
Satellites orbiting Earth to gather images and measurements of land, forests, cities, and coastal waters have helped scientists understand our planet.<\/p>\n
However, since these images come from many different sources, it can be difficult to combine them into a single picture.<\/p>\n
Google\u2019s artificial intelligence (AI) unit, DeepMind, recently announced an AI model called AlphaEarth Foundations that can create highly detailed maps of our world in nearly real time.<\/p>\n
AlphaEarth Foundations functions like a \u201cvirtual satellite\u201d that maps the world \u201cat any place and time,\u201d Christopher Brown, a research engineer at Google DeepMind, said at a press briefing<\/a> in July.<\/p>\n \u201cWhether they are monitoring crop health, tracking deforestation, or observing new construction, [researchers] no longer have to rely on a single satellite passing overhead. They now have a new kind of foundation for geospatial data,\u201d Google DeepMind wrote in a statement<\/a> last month.<\/p>\n The system combines trillions of images from dozens of public sources, including satellite images, radar scans, laser-based 3D mapping, and climate simulations. It maps the entire planet\u2019s terrestrial land and coastal waters.<\/p>\n Google said the model can generate accurate enough data about an ecosystem down to an area of 10 square metres. Data from AlphaEarth Foundations takes up far less storage space than similar AI systems, which makes large-scale analysis more practical, the company said.<\/p>\n During AlphaEarth Foundations\u2019s initial testing of data from 2017 to 2024, it beat similar AI models in identifying land use and estimating surface properties, with an average error rate that was 24 per cent lower, according to a paper<\/a> published by DeepMind.<\/p>\n Google hopes it will help researchers study changes across the planet for food security, deforestation, urban expansion, and water resources.<\/p>\n Why scientists want this level of detail and how AI can help<\/p>\n AlphaEarth Foundations is part of a growing trend in environmental science where AI turns the constant stream of satellite observations into practical tools for studying the Earth.\u00a0<\/p>\n High-resolution, regularly updated data help researchers measure environmental changes precisely and understand what is driving them.<\/p>\n They can be used to track the effects of climate change, plan conservation, and manage resources like water and farmland.<\/p>\n For example, in 2020, scientists at NASA and the University of Copenhagen mapped 1.8 billion individual tree canopies<\/a> in the Sahel and Sahara regions of west Africa, using AI trained to recognise trees in satellite images.<\/p>\n Without AI, this would have taken millions of people years to complete, according to the study<\/a> authors.\u00a0<\/p>\n