Algorithms used to analyze tree heights around the world

The Eco-Vision Lab at the Department of Civil, Environmental and Geomatic Engineering (D-BAUG) of the Swiss Federal Institute of Technology in Zurich (ETH) has created a global map that offers insights into the height of trees across our planet. The Global Canopy Height Map uses images of every location across the planet sent back to Earth every five days by two Copernicus Sentinel-​2 satellites operated by the European Space Agency (ESA). This could deliver key information in connection with fighting climate change and species extinction. After all, as Konrad Schindler, Professor of Photogrammetry and Remote Sensing, explains in a press release issued by ETH: “Around 95 percent of the biomass in forests is made up of wood, not leaves”. As such, he concludes that “biomass strongly correlates with height”.

“We simply do not know how tall trees are globally”, comments Ralph Dubayah, the Principal Investigator of NASA’s Global Ecosystem Dynamics Investigation (GEDI) mission, in the same press release. “We need good global maps of where trees are. Because whenever we cut down trees, we release carbon into the atmosphere, and we don’t know how much carbon we are releasing”, he adds.

In the lab, researchers are developing machine learning algorithms that make it possible to automatically analyze large-scale environmental data. The trick to this is to stack the image filters, Schindler explains. This gives the algorithm contextual information as every pixel already has information about its neighboring pixel.

It would take a single powerful computer three years to process this veritable mountain of data. “Fortunately, we have access to the ETH Zurich high-​performance computing cluster, so we didn’t have to wait three years for the map to be calculated”, comments Nico Lang, who developed the approach within the framework of his doctoral thesis.