[ad_1]
To get an idea of how much carbon the Earth can store and how it changes over time, scientists would need to count a staggering number of trees and monitor their growth over time. Incredibly, the NASA guys are now using supercomputers to do just that, via top-down images from space.
Scientists from NASA’s Goddard Space Flight Center in Maryland recently collaborated with an international team of researchers to map trees using high-resolution satellite imagery: more than 1.8 billion trees found outside forests on a area of over half a million square. miles.
The team used one of the fastest supercomputers in the world (Blue Waters at the University of Illinois) to perform a “deep learning” analysis on terrain images from large sections of West Africa. They found that not only could they count the trees that the satellites hadn’t been able to see before, but they could also start evaluating the carbon storage potential of those trees at the same time.
Much of the world’s efforts to evaluate large numbers of trees have focused on well-wooded regions. This is why the NASA team sought to focus on isolated trees in the drylands and semi-arid regions of West Africa, for a more complete picture.
RELATED: For the first time ever, scientists identify how many trees to plant and where to plant them to stop the climate crisis
“These arid areas are white on maps – they are basically masked because ordinary satellites just don’t see trees,” lead author Martin Brandt said in a statement. “They see a forest, but if the tree is isolated, they cannot see it. We are now well on our way to filling in these white spots on the maps. And this is pretty exciting. “
To train the machine learning algorithms, Brandt, an assistant professor of geography at the University of Copenhagen, personally marked nearly 90,000 trees spanning different terrains, providing the software with different shapes and shadows to learn the difference. The team also trained their algorithms to recognize both single trees and small clusters in different types of terrain, ranging from savannas to deserts, and published their new study in Nature.
With the right training in place, a job that may have required trained eyes over several years to complete took only a few weeks for the AI.
CHECK-OUT: Scientists use recycled wastewater to cultivate a 500-acre forest in the middle of the Egyptian desert
The team was able to map the canopy diameter (the width of a tree seen from above) of 1.8 billion trees spanning an area of more than 500,000 square miles (1.3 square km). They also compared the variability of tree cover and density based on different rainfall patterns – information the team plans to compare with upcoming tree height and biomass data to identify carbon storage potential.
In the future, such assessments will more effectively track deforestation around the world for environmentalists. General data from one year will also be compared with subsequent years to allow scientists to assess whether conservation efforts are working or not.
POPULAR: The search engine that plants trees with every search has just planted its 100 millionth tree
Accurate and automated tree counting should also increase landowners’ ability to monetize the unused space they may have to plant new trees, to quantify the amount of carbon they are storing for carbon credits.
Ultimately, improving researchers’ ability to locate trees where they previously couldn’t with satellite imagery and to measure the carbon storage of those trees will ultimately enable climate scientists to make global measurements of carbon storage on earth. This will be a vital tool in a world where storing our excess carbon is becoming increasingly crucial.
CLOCK a video from NASA about the turning point …
PLANT some positivity for your friends and family on social media …
[ad_2]
Source link
