Google Deepmind creates global forest map with satellite data and AI
Google DeepMind and the World Resources Institute released ForTy, a global satellite map of 2020 land cover that classifies areas at 10‑meter resolution into six categories, including primary forest, plantations, and tree crops. The system uses AlphaEarth Foundations and multiple image‑recognition stages to distinguish forest types by growth and harvest cycles, not appearance alone.
Key points
- ForTy maps 2020 land cover at 10‑meter resolution into six classes, achieving 90.2% overall accuracy.
- The map outperforms European Commission maps, scoring 95.5% vs 93.6% for forest vs non‑forest and 90.9% vs 87.8% for forest types.
- ForTy identifies only about half of tree crops and planted forests and 60% of plantations, limiting its usefulness for EUDR compliance.
ForTy achieved 90.2% overall accuracy and outperformed European Commission maps on the same test data, scoring 95.5% versus 93.6% for forest versus non‑forest classification and 90.9% versus 87.8% for forest types. Experts reviewed 8,190 randomly selected sites, finding the map correct in 90.2% of cases, but it identified only about half of tree crops and planted forests and 60% of plantations.
The map provides a 2020 reference point needed for the EU Regulation on Deforestation‑free Products, helping companies assess supply‑chain risks and support global conservation targets, though gaps in tree crop and plantation detection limit its usefulness for policy enforcement.
Google Deepmind creates a global map of forests with satellite data and AI
The Decoder · 31 October 2026
Loading the full article…
This text was published by The Decoder and written by Jonathan Kemper. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Opera proposes WebAI standard to run local AI models in browsers · 1 src
- Microsoft releases Mage-VL-Cowork 4B hybrid computer-use model · 1 src
- NVIDIA releases MotionBricks AI for Real-Time game and robot movement · 1 src
- Anthropic removes Opus 4.8 fast mode on November 30 · 2 src
- Mistral releases Mistral Large 4 (Le Chonk) 1-trillion-parameter multimodal model on Hugging Face · 12 src
Comments
via GitHub Discussions