According to a Google DeepMind blog post dated October 22, 2026, Google DeepMind and Google Research, together with the World Resources Institute (WRI) and the International Institute for Applied Systems Analysis (IIASA), have released Forest Typology (ForTy) 2020, a global map that categorizes every 10-by-10-meter patch of land on Earth into six distinct forest and land-use types. The authors, Maxim Neumann and Charlotte Stanton, describe the map as a baseline for the European Union's regulation on deforestation-free products (EUDR). Alongside the map, the teams are sharing an early time series tracking how forests changed each year from 2017 to 2025, including where natural forests were replaced by plantations or farms. According to the post, the map allows users to see at 10-meter detail worldwide, year by year, not only where forest was lost but what replaced it, such as a timber plantation, a tree-crop farm, or other land. The post states that most existing global maps only indicate whether trees are present, which the authors describe as a challenge for distinguishing an old-growth rainforest from a eucalyptus plantation or an oil palm estate, which can look the same from space but hold different amounts of carbon and biodiversity.
What it means for you
This is a scientific data release about mapping forests, not a business tool. For most organizations it changes nothing about how work gets done. The narrow exception is organizations that must prove their products or supply chains are deforestation-free under EU rules — this map could become part of how that evidence is built.
Who should care
Compliance and sourcing teams at companies that sell commodities (timber, palm oil, cocoa, coffee) into the EU and need to document deforestation-free supply chains; environmental and GIS analysts.
Skip this if
Your organization doesn't deal with agricultural or forestry supply chains or EU deforestation reporting — then this is interesting science with no bearing on your work.
Sources: Google DeepMind — read the original