How can we monitor forest structure, mortality, and disturbance at scale from satellite time series? We build methods for tree mortality mapping, deforestation detection, and forest typing from Sentinel-2, LiDAR, and related earth observation. Recent work includes sub-pixel mapping of disturbance and tree mortality from global Sentinel-2 time series (deadtrees.earth), conifer/deciduous classification from airborne LiDAR, and spatio-temporal deep learning for rainforest deforestation mapping. Forestry applications extend our ecology and remote sensing portfolio toward operational forest health and carbon-relevant monitoring.
Spotlight publications tagged for this research area.