Forestry & remote sensing researcher —
reading the forest through lidar point clouds
I study how forests respond to disturbance at scale — fusing airborne lidar with decades of satellite imagery — and build fast geospatial tools in Rust & Python.
I am passionate about lidar and satellite remote sensing for forest disturbance characterization and monitoring. I love coding in Python and Rust to develop fast processing tools that simplify the manipulation of remote-sensing data, and I am deeply interested in deep learning and model explainability & uncertainty.
Fusing the vertical detail of lidar with the temporal depth of multi-decadal satellite records.
Forest structure in 3D
Millions of laser returns resolve a single tree in 3D. From the raw point cloud I extract structural attributes — height, crown size and cover — that drive fine-scale disturbance characterization.
30+ years from space
Three decades of surface-reflectance composites reveal how forests change — capturing the impact of insect outbreaks and the slow recovery that follows, pixel by pixel across the landscape.
From point clouds to production code — filter by what you're curious about.
High-Quality Personnel conducting scientific research on the effect of forest disturbances on forest structure at scale, combining lidar and Landsat data with machine learning.
Forestry & remote sensing studies across Canada, Italy and beyond.
Tools I author and research software I contribute to.
Characterizing forest disturbance, structure and resilience with lidar and Landsat time series.
Open to research collaborations, talks, and conversations about remote sensing, forest ecology, and fast geospatial tooling.