Across millions of kilometres of the Sahel and Sahara regions of West Africa, scientists have mapped 1.8 billion individual tree canopies. This is the first time that mapping of trees has ever been done in such detail over such a diverse area.
How is this possible?
A huge database of satellite images using artificial intelligence has been analysed by researchers. These researchers have employed neural networks which can recognise specific objects, like trees, based on shapes and colours
In order to train the AI system, the system was shown satellite images where trees were manually traced. This was an arduous process of identifying and labelling approximately 90,000 trees.
These images allowed the computer to learn what a tree looked like and could pick out individual canopies from the thousands of images in the database. The AI system can now identify quickly what would have taken millions of people years to identify without the AI system.
Scientists at New Mexico State University believe it will soon be possible, with certain limitations, to map the location and size of every tree worldwide.
This information has allowed the team to understand more about trees growing in dry desert conditions because understanding how much vegetation can be found in deserts is important for ecology.
The data gathered will be used as a baseline for studies in preservation, restoration, and climate change.
There is now also the opportunity to measure deforestation. These satellites would also allow scientists to determine how much carbon is stored in deserts (which is a figure that is not currently included when modelling climate change).
Overall, the survey is promising, but it is too early to determine whether the new information will have a significant impact on our understanding of the climate crisis.