# Google Research — Separating natural forests from other tree cover with AI for deforestation-free supply chains

- Company: Google Research (research.google)
- Announced: 2025-11-13T19:04:00+00:00
- Category: research-paper
- Subject: Research
- Models affected: MTSViT
- Source: https://research.google/blog/separating-natural-forests-from-other-tree-cover-with-ai-for-deforestation-free-supply-chains/
- Record: https://forck.live/items/1390-separating-natural-forests-from-other-tree-cover-with-ai-for-deforestation

Google Research and Google DeepMind release Natural Forests of the World 2020, a globally consistent 10-meter resolution map distinguishing natural forests from other tree cover, published in Nature Scientific Data. The map uses a multi-modal temporal-spatial vision transformer (MTSViT) model and achieves 92.2% accuracy. It aims to support deforestation-free regulations like the EUDR.

## Evidence

Verbatim from https://research.google/blog/separating-natural-forests-from-other-tree-cover-with-ai-for-deforestation-free-supply-chains/:

> we’re releasing Natural Forests of the World 2020, a new map and dataset, published in Nature Scientific Data. This project ... provides a critical baseline for deforestation and degradation monitoring. It's the first globally consistent, 10-meter resolution map that differentiates natural forests from other tree cover and achieves a best-in-class accuracy of 92.2% when validated against a global independent dataset.

---

Record: https://forck.live/items/1390-separating-natural-forests-from-other-tree-cover-with-ai-for-deforestation
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md