Google DeepMind تطلق خريطة لغابات العالم تفرّق بين الغابة الطبيعية والمزرعة، بدقة 10 أمتارGoogle DeepMind releases a world forest map that tells natural forest from plantations, at 10-metre detail

Google DeepMind and Google Research, with the World Resources Institute (WRI) and the International Institute for Applied Systems Analysis (IIASA), have released Forest Typology (ForTy) 2020, a map that sorts every 10-by-10-metre patch of land on Earth into six types: primary forest, naturally regenerating forest, planted forest, plantation forest, tree crops and agroforestry such as oil palm and cocoa, and other land.

Why it matters: from space, an old-growth forest and a tree plantation can look like the same green patch, even though they hold very different amounts of carbon and biodiversity. The EU's deforestation regulation requires that products like coffee, cocoa and palm oil don't come from land that was forest in 2020 and has since been converted to farming, and the map gives companies and regulators a baseline for that.

Alongside it comes an early time series tracking change year by year from 2017 to 2025, showing what replaced lost forest: a timber plantation, a tree-crop farm or other land. The model was trained on about 1.7 million labelled locations.

To test it, the team checked the map against more than 9,000 randomly chosen sites, each examined by two trained experts. It picked the right forest type 90% of the time and told forest from non-forest 95% of the time. The map is freely available on Google Earth Engine under an open licence.