Reducing Government Costs and Increasing Access to Greenspaces in the United Kingdom with DINO

UK's Forest Research agency is using Meta's open source DINOv2 computer vision model — trained on 18 million satellite images in collaboration with the World Resources Institute — to build high-resolution Canopy Height Maps for monitoring trees across England. The model enables individual tree detection at national scale, potentially replacing costly LiDAR surveys and manual field surveys. This could reduce data procurement costs, increase update frequency to a rolling three-year cycle, and improve monitoring of government tree canopy targets under the Environmental Improvement Plan. Meta has also introduced DINOv3 to further improve visual intelligence for similar reforestation monitoring use cases globally.