Smart Forestry: AI in the Service of Nature
summary
Combines optical and Sentinel SAR satellite imagery with field inventory and a machine-learning model to produce 20 m-resolution maps of forest biomass and CO2 uptake, reporting roughly 20% estimation error on open-source imagery. Produces land-use/land-cover change maps and semi-automatic supply-chain due-diligence reports for EUDR compliance, and describes an asset called Selva that quantifies credits sold while routing most revenue to Guatemalan communities via reforestation and forest management projects.
AI-written summary · about
chapters (9)
- 0:00Smart Forestry intro
- 3:57Why forests matter
- 10:02Satellite imagery and AI
- 13:39Carbon monitoring with AI
- 16:30Carbon credits in Guatemala
- 19:01LULC maps vs deforestation
- 21:54EU compliance with AI
- 22:36Q&A
- 24:24Community involvement
related talks
48mTaking the planet’s pulse: AI to empower adaptation to global change
36mWatching Millions of Trees with Python: For Impact and Profit
41mAbby Seneor | AI Track | Compass AI & Data Summit 2025
28mGeoAI: Evolution of AI-Based Tree/Vegetation Detection Models Using Imagery
13mOpen Source Technologies for Forest Biodiversity Monitoring
32mMeasuring Vegetation Health to Predict Natural Hazards
42mUsing Generative AI and Foundation Models to Predict Above Ground Biomass
25mApply responsible AI principles when building remote sensing datasets