Google DeepMind and World Resources Institute Release First Global 10‑Meter Forest‑Type Map
Current overview (not historical)
Google DeepMind and the World Resources Institute have unveiled ForTy, the first global forest‑type classification map based on 2020 satellite data. The 10‑meter resolution map distinguishes primary forest, naturally regenerating forest, planted forest, plantation forest, and tree crops such as oil palm, rubber, and cocoa. During training, the system employed a three‑stage model and an expert correction workflow, adding roughly 43,000 examples to correct misclassifications—such as European vineyards mislabeled as tree crops, North‑American natural pine forests misidentified as plantations, and missed oil palm in Africa and Indonesia. In a head‑to‑head test against a European EUDR‑specific map, ForTy achieved 95.5% accuracy for forest vs. non‑forest and 90.9% accuracy for forest‑type classification, outperforming the competitor’s 93.6% and 87.8% respectively.
Written with AI from the reporting · updated 10/31/2026
Expand the detailed fact route and sources
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Unclassified fact stationOct 31, 00:00recorded Oct 31, 19:13single sourcerevised
Google Deepmind and World Resources Institute发布全球森林分类地图ForTy
Read original source ↗ The DecoderReplay this moment in the explorerEvidence & revisions · 1 source records
- Subject：
- Action：
- 发布全球森林分类地图
- Object：
- ForTy
- Occurred (fact side)：
- Oct 31, 00:00
- Published (valid side)：
- Oct 31, 18:15
- First seen (known side)：
- Oct 31, 19:13
Fact stationSingle source · one-sided claimRevisedCopy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.
Uncertainty marks flag where to check the sources; they are not proven causation.
Report timeline
Explore every side through dated source reports.
- The DecoderRelated fact: single sourceSource report revisedDeepMind and WRI Release ForTy, a 10‑meter Global Map Classifying Forests and Tree Crops for 2020
Report first recorded Oct 31, 19:13
Google DeepMind and the World Resources Institute have produced ForTy, the first global map that classifies land into six categories—primary forest, naturally regenerating forest, planted forest, plantation forest, tree crops such as oil palm, rubber, or cocoa, and other land—at 10‑meter resolution using satellite data and AI. The map assigns each 1‑km square the most common land‑use class in 2020, providing a reference point for the EU Regulation on Deforestation‑free Products, which requires companies to prove that goods were not linked to forest loss after December 31 2020. ForTy’s multi‑stage model, built on DeepMind’s AlphaEarth Foundations, incorporates verified examples, external data on tree height, buildings, and forest loss, and iterative active‑learning rounds that added about 43,000 expert‑labeled examples to correct errors. The dataset can also support other initiatives such as the Tropical Forest Forever Facility and the UN’s 2030 land‑protection goal.
Read original source ↗
Event activity trend
- Latest comparable
- 3
- Comparable peak
- 10Oct 31, 20:00
- 24h change
- -50%
The chart compares consistently observed participants only. Hover or tap to inspect each hour; use arrow keys to move between observations.
Event discussion
Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.