# Google DeepMind releases detailed global forest type map

> The new Forest Typology 2020 map shows every 10‑meter patch of land as natural, planted or farmed forest, with yearly changes from 2017‑2025.

Oossa · 2026-10-22 · https://oossa.com/en/google-deepmind-releases-detailed-global-forest-type-map

Google DeepMind and Google Research have published Forest Typology (ForTy) 2020, a global map that classifies every 10‑by‑10‑meter area on Earth into six forest or land‑use types. The map is available now on Google Earth Engine under an open license. An early time series also shows how those patches changed each year from 2017 to 2025.

## How the map works

ForTy divides land into primary forest, naturally regenerating forest, planted forest, plantation forest, tree crops/agroforestry, and other land. The model was trained on about 1.7 million labeled locations and uses AlphaEarth Foundations embeddings – compact summaries of satellite data – to detect subtle patterns like planting cycles. Validation against more than 9,000 expert‑checked sites found a 90 % correct classification rate for forest types and 95 % accuracy for forest versus non‑forest.

## Why it matters

The map lets regulators, companies and NGOs see not just where trees exist but what kind they are, which is required by the EU’s deforestation‑free products rule. It also reveals hidden conversions, such as natural forest turned into a timber plantation, that standard tree‑cover maps miss.

## The facts

- The Forest Typology 2020 map classifies land into six categories defined by the UN Food and Agriculture Organization.
- The model was trained with about 1.7 million labeled locations from expert surveys and national datasets.
- Validation on over 9,000 random sites gave a 90 % accuracy for forest‑type classification and 95 % for forest versus non‑forest.
- The time series covers yearly changes for every 10‑meter pixel from 2017 to 2025.
- The map and time series are freely available on Google Earth Engine under an open license.

## Why it matters

For a consumer, the map helps ensure that products like coffee or chocolate are not linked to recent forest conversion, because regulators can trace the exact forest type behind supply chains. For a forest manager, it provides a clear picture of where natural forests are being replaced, supporting more targeted protection and restoration efforts.

## Sources & references

1. [Beyond tree cover: mapping the world’s forest types](https://deepmind.google/blog/beyond-tree-cover-mapping-the-worlds-forest-types/) – Google DeepMind, 2026-10-22

Last updated: 2026-10-22