Google DeepMind 用卫星数据和 AI 绘制全球森林类型地图
原标题：Google Deepmind creates a global map of forests with satellite data and AI
AI 摘要
Google DeepMind 与世界资源研究所合作开发了 ForTy，利用卫星数据和 AI 生成 2020 年全球森林类型地图，以 10 米分辨率将地表分为六类，整体准确率 90.2%，并在同一测试数据上优于欧盟委员会的地图。该地图主要为欧盟无毁林产品法规（EUDR）提供 2020 年基准参考，但研究团队承认其在人工林和树作物识别上仍存在明显短板。
正文节选
Google Deepmind creates a global map of forests with satellite data and AI Key Points - Google Deepmind and the World Resources Institute created a global satellite map of 2020 land cover, classifying areas at 10-meter resolution into six categories, including primary forest, plantations, and tree crops. - The system uses AlphaEarth Foundations and multiple image-recognition stages to distinguish forest types by growth and harvest cycles, not appearance alone. - The map achieved 90.2% overall ac