{
  "id": 16057709,
  "title": "Beyond tree cover: mapping the world’s forest types",
  "url": "https://urgent.news/2026/10/22/beyond-tree-cover-mapping-the-worlds-forest-types",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-22T14:30:24.000Z",
  "source": {
    "name": "Google DeepMind",
    "slug": "google-deepmind",
    "url": "https://deepmind.google/blog/beyond-tree-cover-mapping-the-worlds-forest-types/"
  },
  "original_language": "en",
  "account": "A new 10-meter resolution map has been released, categorizing the world's forest types and tracking changes in them over time. This information is crucial for understanding the ecological value of forests and informing conservation efforts. The map distinguishes between various types of forests and land use, such as primary forests, plantations, and tree-crop farms. By doing so, it helps identify where natural forests are being converted into agricultural land and provides insights into forest degradation.\n\nThe map was developed by Google DeepMind and Google Research, in collaboration with the World Resources Institute (WRI) and the International Institute for Applied Systems Analysis (IIASA). It builds upon the previous Natural Forests of the World 2020 map, which identified natural forests from other tree cover. ForTy goes beyond this by categorizing each 10-by-10-meter patch of land into six distinct forest and land-use types, based on definitions from the UN Food and Agriculture Organization (FAO).\n\nTo create this detailed map, the researchers built a large-scale collection of forest-type examples, which was used to train a custom model. This model uses satellite observations to identify subtle clues like planting patterns, growth cycles, and harvest rhythms. The map has been validated against over 9,000 sites, achieving a 90% accuracy rate in correctly identifying forest types and a 95% accuracy rate in distinguishing between forests and non-forests.\n\nThe new time series, which tracks changes in forest types from 2017 to 2025, provides additional valuable information. It shows the year-by-year transformations that occur within forests, including the conversion of natural forests into plantations, tree-crop farms, or abandoned land regenerating into forests. This level of detail is essential for understanding the full impact of human activities on the world's forests.\n\nThe Forest Typology 2020 map and the new time series are now available on Google Earth Engine under an open license, making them accessible to governments, companies, and conservation organizations worldwide. These tools will enable stakeholders to make more informed decisions about forest protection and sustainable land management, ultimately contributing to the preservation of the planet's vital forest ecosystems.",
  "summary": "A global map categorizing every 10-meter patch of land on Earth into distinct forest types.",
  "key_points": [
    "New 10-meter resolution map categorizes world's forest types",
    "Developed by Google DeepMind, Google Research, WRI, IIASA",
    "Tracks changes in forest types from 2017 to 2025"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}