Our research combines Machine Learning, Remote Sensing and Geography to discover unprecedented knowledge at the level of individual trees.
We use PlanetScope, Skysat, Maxar and Gaofen-2 satellite images to produce maps on tree locations, count, cover, density, biomass, and canopy height, from local to continental scale.
Our work has been published in Nature, Nature Climate Change, Nature Sustainability, PNAS Nexus, Science Advances, Nature Plants, Nature Food, Nature Geoscience, Nature Ecology, Nature Communications, etc.
Research
During the past two decades, a variety of commercial satellites have begun to collect data at a higher spatial resolution, capable of capturing ground objects measuring one square metre or less. This resolution improvement places the field of terrestrial remote sensing on the threshold of a fundamental leap forward: from focusing on aggregate landscape-scale measurements to having the potential to map the location and canopy size of every tree over large regional or global scales. This revolution in observational capabilities will undoubtedly drive fundamental changes in how we think about, monitor, model and manage global terrestrial ecosystems (Hanan & Anchang, 2020).
Trees outside forests in global drylands (TOFDRY)
ERC starting grant
TOFDRY aims to quantify the worlds non-forest trees by using PlanetScope satellite imagery and a deep learning technique which is able to identify objects within imagery at unprecedented accuracy. See example.
Country-scale assessment of individual trees in Africa
DFF Sapere Aude Danish Research Leader Grant in collaboration with NASA
We have a special focus on Africa to produce large scale maps at tree-level at national and continental scale. See example.
Tree biomass in European Forests
In collaboration with INRAE, Kayrros, LSCE, and others
We use deep learning, NFI data, aerial and PlanetScope images to map tree biomass in European forests. See example.
The Carbon Sink of Southern China
In collaboration with the Chinese Academy of Sciences
We investigate the impact of afforestation projects on the karst landscapes of Southern China. See example.
Global carbon stock and vegetation monitoring
Together with INRAE, LSCE, and others
We use passive microwaves (L-VOD) at coarse scale for monitoring global carbon sinks and vegetation dynamics, and what biotic and abiotic factors drive them. See example.