https://github.com/google-deepmind/forest_typology
Datasets to protect Earth's forests and biodiversity
https://github.com/google-deepmind/forest_typology
benchmark-datasets biodiversity deep-learning earth-observation forest habitat-mapping machine-learning remote-sensing sustainability
Last synced: 5 months ago
JSON representation
Datasets to protect Earth's forests and biodiversity
- Host: GitHub
- URL: https://github.com/google-deepmind/forest_typology
- Owner: google-deepmind
- License: apache-2.0
- Created: 2025-05-02T07:31:50.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-06T14:03:24.000Z (about 1 year ago)
- Last Synced: 2025-08-22T06:53:54.896Z (10 months ago)
- Topics: benchmark-datasets, biodiversity, deep-learning, earth-observation, forest, habitat-mapping, machine-learning, remote-sensing, sustainability
- Language: Jupyter Notebook
- Homepage:
- Size: 2.95 MB
- Stars: 88
- Watchers: 15
- Forks: 12
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# Forest Typology
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](https://deepmind.google/) (GDM) in collaboration with external
([World Resources Institute](https://www.wri.org/) (WRI)), and internal partners
([Google Research](https://research.google/),
[Google Geo Sustainability](https://earthoutreachonair.withgoogle.com/)) 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.
## Forest and habitat layers
* [Natural forests of the world (v1)](./natural_forests/README.md) - global
map of natural forests for 2020.
* Global drivers of forest loss (Upcoming).
## Benchmark datasets
* [ForTy (v1)](./forty_v1/README.md) - global multi-temporal multi-source
segmentation benchmark dataset for forest types.
* [Planted](./planted/README.md) - large-scale benchmark dataset for planted
forest recognition (with subtasks for monoculture plantation tree species
and genera recognition).
## License and disclaimer
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.