Advertisement

AI Has Discovered Nearly 2 Billion Trees in the Sahara Desert

Researchers found more than 1.8 billion trees in and around the Sahara Desert with deep-learning AI.

There are many more trees in the West African Sahara Desert than we thought, according to a recent study based on AI and satellite imagery and published in the journal Nature — which found more than 1.8 billion trees in the Sahara Desert.

RELATED: ANCIENT DATE PALM AND ARCTIC FLOWER BROUGHT BACK FROM THE DEAD

AI found nearly 2 billion trees in the Sahara Desert

Researchers have counted more than 1.8 billion trees and shrubs in the 501,933 square-mile (1.3 million square-kilometer) area — in an area encompassing the western-most region of the Sahara Desert — called the Sahel — along with sub-humid zones of West Africa, reports The World Economic Forum.

"We were very surprised to see that quite a few trees actually grow in the Sahara Desert, because up until now, most people thought that virtually none existed," said Professor Martin Brandt from the geosciences and natural resource management department of the University of Copenhagen and lead author of the recent study.

"We counted hundreds of millions of trees in the desert alone. Doing so wouldn't have been possible without this technology," explained Brandt, according to a blog post on the University of Copenhagen's website. "Indeed, I think it marks the beginning of a new scientific era."

West Africa Study Area
The study area in West Africa is outlined in red. Source: University of Copenhagen

AI tree detection could suggest new carbon budget factors

The researchers used uncommonly detailed satellite imagery from NASA, along with deep learning — an advanced mode of AI. Typical satellite imagery can't identify single trees, which makes them invisible to ordinary means.

Additionally, limited interest in counting the number of trees outside of forests has led many to think this desert region has almost no trees whatsoever. But now we have proof showing how wrong they were.

Extra knowledge about trees in dry areas like the Sahara Desert is significant for multiple reasons, said Brandt. For one, they hint at the existence of an unknown factor for nations and companies considering their global carbon budget.

"Trees outside of forested areas are usually not included in climate models, and we know very little about their carbon stocks. They are basically a white spot on maps and an unknown component in the global carbon cycle," added Brandt.

AI will help us better grasp the Earth's ecosystem

Moreover, the recent study improves our comprehension of how crucial trees are for biodiverse ecosystems — not to mention the people living in these environments. A firmer grasp of the science of trees is critical for programs developing agroforestry — a force of major socioeconomic and environmental gravity amid arid regions, reports The World Economic Forum.

"Thus, we are also interested in using satellites to determine tree species, as tree types are significant in relation to their value to local populations who use wood resources as part of their livelihoods," said Professor Rasmus Fensholt of the geosciences and natural resource management department at the University of Copenhagen.

"Trees and their fruit are consumed by both livestock and humans, and when preserved in the fields, trees have a positive effect on crop yields because they improve the balance of water and nutrients," added Fensholt.

As the ecosystem of the planet shifts into phases less friendly to human biology, other species of life may also suffer. For humans to become better custodians of the Earth's biosphere, systems like the researchers' deep-learning AI will scale up our ability to grasp the global ecosystem — to take more precise measures against the climate crisis, but also to estimate the damage.

Advertisement
Follow Us on

Stay on top of the latest engineering news

Just enter your email and we’ll take care of the rest:

By subscribing, you agree to our Terms of Use and Privacy Policy. You may unsubscribe at any time.

Advertisement