DeepMind and WRI publish ForTy, a global 2020 forest-type map
Original title: Google Deepmind creates a global map of forests with satellite data and AI
ForTy labels six land classes at 10-meter resolution and was judged correct on 90.2 percent of 8,190 sites.
Google DeepMind and the World Resources Institute released ForTy, a 2020 global map separating primary forest, regenerating forest, planted forest, plantations, tree crops and other land. It is intended as a reference for the EU deforestation regulation, which restricts goods tied to forest cleared or degraded after December 31, 2020. The system uses AlphaEarth Foundations and staged models, with Gemini helping adapt older labels. Accuracy is weaker for plantations and tree crops than for primary forest.
Unconfirmed: Overall accuracy is boosted by easy non-forest land, and some regional area estimates are biased.
- Experts confirmed 89 percent of primary forests but only about half of tree crops.
- About a quarter to a third of mapped plantations or tree crops were wrong.
- Authors estimate about 2 billion hectares of primary forest worldwide.
- The map overestimates Asian primary forest by about 200 million hectares.
- Vendors
- Products
- ForTy
- Organizations
- Google DeepMindWorld Resources Institute
- AI models
- AlphaEarth FoundationsGemini
From the original article
5 min read at the-decoder.com
Google Deepmind and the World Resources Institute have released ForTy, a global map that classifies forests and other land into six categories, including primary forest, plantations, and tree crops. The map could help track deforestation under EU rules, but it identifies only about half of planted forests and tree-crop areas, and 60% of plantations.
By Jonathan Kemper · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.