Protecting biodiversity and curbing carbon emissions from deforestation demands a deeper understanding of global forest cover. Informed decision-making hinges not only on knowing where forests are, but on understanding their composition and distinguishing forest types that play critical roles as biodiversity hotspots and major carbon sinks.
Google DeepMind (GDM) in collaboration with external (World Resources Institute (WRI)), and internal partners (Google Research, Google Geo Sustainability) are developing AI models to estimate the forest types and to generate regional to global maps of forest land cover. In addition to releasing these layers we create benchmark datasets for AI researchers.
- Natural forests of the world (Upcoming).
- Global drivers of forest loss (Upcoming).
- ForTy (v1) - global multi-temporal multi-source segmentation benchmark dataset for forest types.
- Planted - large-scale benchmark dataset for planted forest recognition (with subtasks for monoculture plantation tree species and genera recognition).
Copyright 2025 DeepMind Technologies Limited
All non-software materials are licensed under the Creative Commons Attribution 4.0 International License (CC-BY). You may obtain a copy of the CC-BY license at: https://creativecommons.org/licenses/by/4.0/legalcode
Unless required by applicable law or agreed to in writing, all software and materials distributed here under the Apache 2.0 or CC-BY licenses are distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the licenses for the specific language governing permissions and limitations under those licenses.
This is not an official Google product.