DeepMind Model Diagnoses Forest Death From Space at 90.5% Accuracy
alex_verem · x · 2026-07-04
@alexverem introduced a model trained by Google DeepMind in collaboration with the World Resources Institute and the University of Maryland for Global Forest Watch to diagnose the causes of forest death from space, achieving 90.5% accuracy and completely free to use. The system previously used weekly 10-meter resolution satellite imagery of the tropics to track 'where' forests were disappearing but couldn't determine 'why'. The new model trains a ResNet neural network on roughly 7,000 manually annotated satellite images, reading scar patterns to identify the causes of tree loss.
More from Multimodal
- TischEins, a large Midjourney SREF library, relaunches with new design after security outage — tisch_eins · 2026-10-26
- MOSS-Image-SFT 4-step distillation tops 16.5K downloads on Hugging Face — _akhaliq · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26
- One-sentence 3D worlds turn cinematic with CineMap and TapNow — gizakdag · 2026-10-26
- No Camera Needed: Creator Builds an Entire World in CineMap and Directs It Into Cinema — gizakdag · 2026-10-26
- Kling vs. Seedance: the Chinese AI video model rivalry — DavidmComfort · 2026-10-26