A forest map built for the deforestation rulebook

Facts are attributed and linked to their sources. The analysis and opinions are the author's own.

What it is

On 22 October Google DeepMind and Google Research, with the World Resources Institute and IIASA, released Forest Typology (ForTy) 2020. It is a global map that sorts every 10-by-10-metre patch of land into six types: primary forest, naturally regenerating forest, planted forest, plantation forest, tree crops and agroforestry, and other land. DeepMind calls it "a key baseline for the EU's deforestation regulation". An early time series tracks changes every year from 2017 to 2025, including where natural forest was replaced by plantations or farms.

The team validated it against more than 9,000 randomly chosen sites checked by two trained experts each. ForTy picked the right forest type 90% of the time and told forest from non-forest 95% of the time. Instead of a yes-or-no label, it gives a probability for each class. The map and time series are free on Google Earth Engine under an open licence, and the 2020 map is described in Scientific Data.

Why it matters

The EU regulation on deforestation-free products requires that goods such as coffee, cocoa and palm oil do not come from land that was forest in 2020 and was later converted to farming. Wood products must also avoid primary forest later turned into plantations. A tree-cover map cannot answer that, because a plantation looks green from space. A forest-type map with a yearly history can.

A map that gives you a probability, not a verdict, is a map built for people who carry the risk.

That is a finance question as much as an environmental one. Lenders and trade-finance desks financing commodity supply chains have to evidence where goods came from. DeepMind's own example is useful: a company assessing deforestation risk might accept only pixels the model is highly confident about. In my view, that choice of threshold should be documented and owned like any other risk appetite decision. A free, open baseline also lowers the cost of due diligence for smaller exporters, including in emerging markets, who could not afford commercial mapping.

What I'd watch

• Whether EU authorities or certification bodies accept ForTy as evidence in due-diligence statements.
• How the time series performs in regions with lots of smallholder agroforestry, where classes blur.
• Whether banks and insurers begin citing it in sustainability-linked lending and trade-finance checks.