AI found nearly 2 billion trees – in the Sahara Desert?
There are more trees in the West African Sahara Desert than we thought – many more. Last year, a study based on AI and satellite imagery was published in the journal Nature. In it, the researchers say they found nearly two billion living trees in the Sahara Desert.
In total, the researchers counted about 1.8 billion trees and shrubs in the 501,933 square mile (1.3 million square kilometers) area. The area encompasses the westernmost region of the Sahara Desert, called the Sahel, as well as the sub-humid areas of West Africa.
“We were very surprised to see that a number of trees actually grow in the Sahara Desert, because until now most people thought there were hardly any,” said the Professor Martin Brandt of the University of Copenhagen and lead author of the recent study. .
“We have counted hundreds of millions of trees in the desert alone. It would not have been possible without this technology,” Brandt explained, according to a blog post on the University of Copenhagen website. “Indeed, I think this marks the start of a new scientific era.”
AI detection of trees could suggest new carbon footprint factors
The researchers used unusually detailed satellite imagery from NASA, along with deep learning, an advanced mode of AI. Typical satellite imagery cannot identify single trees, making them invisible to ordinary means.
Moreover, the limited interest in counting the number of trees outside forests has led many to believe that this desert region has almost no trees. But now we have evidence showing just how wrong they were.
Additional knowledge about trees in dry areas like the Sahara Desert is important for several reasons, Brandt said. On the one hand, they suggest the existence of an unknown factor for nations and companies given their global carbon budget.
“Trees outside forest areas are generally not included in climate models and we know very little about their carbon stocks. They are essentially a white spot on the maps and an unknown component of the global carbon cycle,” he said. added Brandt.
AI will help us better understand the Earth’s ecosystem
Additionally, the recent study improves our understanding of the importance of trees to biodiversity ecosystems, not to mention the people living in those environments. A better understanding of tree science is essential for agroforestry development programs – a major socio-economic and environmental force of gravity in arid regions, reports the World Economic Forum.
“So we are also interested in the use of satellites to determine tree species, as tree types are important in relation to their value to local people who use wood resources as part of their livelihood. livelihood, “said Professor Rasmus Fensholt of geosciences and natural resource management. department of the University of Copenhagen.
“Trees and their fruits are consumed by both livestock and humans, and when kept in fields, trees have a positive effect on crop yields as they improve the balance between water and nutrients, âadded Fensholt.
As the planet’s ecosystem shifts to phases less favorable to human biology, other species of life may also suffer. In order for humans to become better stewards of the Earth’s biosphere, systems like the deep learning AI of researchers will increase our ability to grasp the global ecosystem – to take more precise action against the climate crisis, but also to estimate the damage.