<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/not-all-forests-are-equal-mapping-the-world-s-forests-58svtreun" -->

---
title: Not All Forests Are Equal: Mapping the World’s Forests
description: Google DeepMind, Google Research, WRI and IIASA released Forest Typology (ForTy) 2020, a global 10-meter map classifying land into six forest and land-use...
canonical: https://daily.dev/posts/not-all-forests-are-equal-mapping-the-world-s-forests-58svtreun
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Not All Forests Are Equal: Mapping the World’s Forests | daily.dev
og:description: Google DeepMind, Google Research, WRI and IIASA released Forest Typology (ForTy) 2020, a global 10-meter map classifying land into six forest and land-use...
og:url: https://daily.dev/posts/not-all-forests-are-equal-mapping-the-world-s-forests-58svtreun
og:image: https://api.daily.dev/og/posts/58svTrEuN.png
og:image:alt: Not All Forests Are Equal: Mapping the World’s Forests
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Not All Forests Are Equal: Mapping the World’s Forests

**[DeepMind](https://daily.dev/sources/dm)** · 7 min read · 0 upvotes · 0 comments

## Summary

Google DeepMind, Google Research, WRI and IIASA released Forest Typology (ForTy) 2020, a global 10-meter map classifying land into six forest and land-use types, from primary forest to plantations and tree crops. It uses AlphaEarth Foundations satellite embeddings and was trained on about 1.7 million labeled locations. Validated against over 9,000 sites, it picked the correct forest type 90% of the time and distinguished forest from non-forest 95% of the time, beating other global forest maps. An accompanying early time series tracks yearly changes from 2017 to 2025, including what replaces lost forest. Both are freely available on Google Earth Engine under an open license.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://deepmind.google/blog/beyond-tree-cover-mapping-the-worlds-forest-types>

## Questions this post answers

### What is Forest Typology (ForTy) 2020 and how accurate is it?

ForTy 2020 is a global 10-meter resolution map from Google DeepMind, Google Research, WRI and IIASA that classifies land into six forest and land-use categories, including primary forest, naturally regenerating forest, planted forest, plantation forest, tree crops, and other land. Validated against over 9,000 sites, it correctly identified forest type 90% of the time and distinguished forest from non-forest land 95% of the time.

_Teams building deforestation-free supply chain tools can track geospatial AI datasets like this on daily.dev._

### What data does the ForTy forest classification model use as input?

The model takes AlphaEarth Foundations embeddings as a key input, which are data-compact summaries of years of satellite observations for each 10-meter pixel. It was trained on roughly 1.7 million labeled locations drawn from expert surveys, national and regional datasets, and targeted reviews of places where the model struggled, using a custom architecture built for remote sensing challenges.

_Developers evaluating satellite embedding approaches for geospatial models can follow this kind of research on daily.dev._

### Where can I access the ForTy forest type map and time series data?

The Forest Typology 2020 map and its accompanying year-by-year time series from 2017 to 2025 are freely available on Google Earth Engine under an open license. The time series shows not just where forest was lost or gained but what replaced it, such as a timber plantation or tree-crop farm.

_Anyone building on open geospatial datasets can keep tabs on new Earth Engine releases via daily.dev._

## Similar posts on daily.dev

- [Mapping the World's Forests with Greater Precision: Introducing Canopy Height Maps v2](https://daily.dev/posts/mapping-the-world-s-forests-with-greater-precision-introducing-canopy-height-maps-v2-k2ggmevzm) · AI at Meta · 0 upvotes · 0 comments
- [Fire and Forest Loss in Kalimantan: A Strong Signal, With an Important Caveat](https://daily.dev/posts/fire-and-forest-loss-in-kalimantan-a-strong-signal-with-an-important-caveat-fycbejjn6) · Medium · 1 upvotes · 0 comments
- [OpenTrees.org](https://daily.dev/posts/opentrees-org-csy7wkqcc) · Hacker News · 2 upvotes · 0 comments
- [OlmoEarth v1.3: State-of-the-art embeddings for the whole planet](https://daily.dev/posts/olmoearth-v1-3-state-of-the-art-embeddings-for-the-whole-planet-nzbungfid) · Hugging Face · 0 upvotes · 0 comments
- [Three ways Google scientists use AI to better understand nature](https://daily.dev/posts/three-ways-google-scientists-use-ai-to-better-understand-nature-hs8ysqhav) · DeepMind · 0 upvotes · 0 comments

---

[View this post on daily.dev](https://daily.dev/posts/not-all-forests-are-equal-mapping-the-world-s-forests-58svtreun)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Not All Forests Are Equal: Mapping the World’s Forests","url":"https://daily.dev/posts/not-all-forests-are-equal-mapping-the-world-s-forests-58svtreun","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/not-all-forests-are-equal-mapping-the-world-s-forests-58svtreun"},"datePublished":"2026-10-27T16:31:29.284Z","dateModified":"2026-10-27T17:06:29.569Z","description":"Google DeepMind, Google Research, WRI and IIASA released Forest Typology (ForTy) 2020, a global 10-meter map classifying land into six forest and land-use...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ceab6d37c0fd7f1ea1662a9adea28c9a?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ceab6d37c0fd7f1ea1662a9adea28c9a?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"DeepMind","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"DeepMind","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/dm","url":"https://daily.dev/sources/dm"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/not-all-forests-are-equal-mapping-the-world-s-forests-58svtreun","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"","timeRequired":"PT7M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"DeepMind","item":"https://daily.dev/sources/dm"},{"@type":"ListItem","position":3,"name":"Not All Forests Are Equal: Mapping the World’s Forests"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/not-all-forests-are-equal-mapping-the-world-s-forests-58svtreun#faq","mainEntity":[{"@type":"Question","name":"What is Forest Typology (ForTy) 2020 and how accurate is it?","acceptedAnswer":{"@type":"Answer","text":"ForTy 2020 is a global 10-meter resolution map from Google DeepMind, Google Research, WRI and IIASA that classifies land into six forest and land-use categories, including primary forest, naturally regenerating forest, planted forest, plantation forest, tree crops, and other land. Validated against over 9,000 sites, it correctly identified forest type 90% of the time and distinguished forest from non-forest land 95% of the time. Teams building deforestation-free supply chain tools can track geospatial AI datasets like this on daily.dev."}},{"@type":"Question","name":"What data does the ForTy forest classification model use as input?","acceptedAnswer":{"@type":"Answer","text":"The model takes AlphaEarth Foundations embeddings as a key input, which are data-compact summaries of years of satellite observations for each 10-meter pixel. It was trained on roughly 1.7 million labeled locations drawn from expert surveys, national and regional datasets, and targeted reviews of places where the model struggled, using a custom architecture built for remote sensing challenges. Developers evaluating satellite embedding approaches for geospatial models can follow this kind of research on daily.dev."}},{"@type":"Question","name":"Where can I access the ForTy forest type map and time series data?","acceptedAnswer":{"@type":"Answer","text":"The Forest Typology 2020 map and its accompanying year-by-year time series from 2017 to 2025 are freely available on Google Earth Engine under an open license. The time series shows not just where forest was lost or gained but what replaced it, such as a timber plantation or tree-crop farm. Anyone building on open geospatial datasets can keep tabs on new Earth Engine releases via daily.dev."}}]}
```