Home https://server7.kproxy.com/servlet/redirect.srv/sruj/smyrwpoii/p2/ Science https://server7.kproxy.com/servlet/redirect.srv/sruj/smyrwpoii/p2/ NASA uses supercomputers and artificial intelligence to count trees from space for the first time

NASA uses supercomputers and artificial intelligence to count trees from space for the first time

To understand how much carbon the Earth can store and how it changes over time, scientists will need to count a confusing number of trees and track their growth over time. It’s amazing that NASA people are already using supercomputers to do just that – through top-down images from space.


Scientists at the Goddard Space Flight Center in Maryland recently partnered with an international team of researchers to map trees using high-resolution satellite imagery – more than 1.8 billion trees outside the forest, more than half the size of million square meters miles.

The team used one of the fastest supercomputers in the world (Blue Waters at the University of Illinois) to analyze “in-depth training” on images of terrain from large parts of West Africa. They found that they could not only count trees that satellites had not been able to see before, but could begin to assess the carbon storage potential of those trees at the same time.

Much of the world’s efforts to assess a large number of trees are focused on well-forested regions. That’s why the NASA team is looking to focus on isolated trees in arid and semi-arid regions of West Africa for a more complete picture.

CONNECTED: For the first time, scientists are determining how many trees to plant and where to plant them to stop the climate crisis

“These dry areas are white on the maps – they are mostly masked because normal satellites just can’t see the trees,” lead author Martin Brand said in a statement. “They see a forest, but if the tree is isolated, they can’t see it. Now we are about to fill these white spots on the cards. And that’s quite exciting. “

To train machine learning algorithms, Brand, an assistant professor of geography at the University of Copenhagen, marked nearly 90,000 trees spanning different terrains personally – giving the software different shapes and shadows to learn the difference. The team also trained its algorithms to recognize both individual trees and small clusters in different types of terrain, ranging from savannas to deserts, and published its new study in Nature.

With proper on-site training, a job that can take a trained eye several years to take only a few weeks for artificial intelligence.

TAKE A LOOK: Scientists use recycled sewage to grow 500 acres of forest in the middle of the Egyptian desert

The team was able to map the crown diameter (width of a tree seen from above) of 1.8 billion trees on an area of ​​more than 500,000 square miles (1.3 square kilometers). They also compare the variability in tree cover and density in different rainfall patterns – information that the team plans to compare with upcoming tree height and biomass data to identify carbon storage potential.

In the future, assessments of this kind will monitor deforestation around the world more effectively for conservationists. Overhead data for one year will also be compared with later years so that scientists can judge whether conservation efforts are working or not.

POPULAR: The search engine that plants trees in every search has just planted its 100 millionth tree

Accurate, automated tree counting should also improve the ability of landowners to generate revenue from the unused space they may have to plant new trees – to quantify how much carbon they store for carbon credits.

Ultimately, improving researchers’ ability to find trees where they previously could not with satellite imagery – and to measure the carbon stocks of those trees – will eventually enable climate scientists to make global conservation measurements. of carbon on land. This will be a vital tool in a world where storing our excess carbon is becoming increasingly important.

I’M WATCHING NASA video for the breakthrough …

PLANT A little positivity for your friends and family on social media …

Source link