Fossil hunters can now use artificial intelligence to look for rich sites with a new method that saves time and helps take luck out of the equation.
U.S. paleontologists have created a computer model that can recognize fossil-rich locations in satellite imagery using information from known sites.
This neural network approach has provided a map of potential hidden treasures in the Great Divide Basin of Wyoming.
Robert Anemone from Western Michigan University and colleagues taught the computer system to analyze hundreds of images by tagging fossil-rich and fossil-poor pixels, and separating them into different categories, such as barren land, forest, wetland, and promising fossil bed.
In the summer of 2009, while digging in the Great Divide Basin, Anemone accidentally discovered a new site that proved to be the most productive location his research group had found in 13 years.
“That was kind of a seminal moment for me. That’s when I realized just how much of this is based purely on luck,” Anemone said in a press release.
He was inspired to improve traditional fossil hunting methods using technology, because most paleontologists rely on chance, struggling to complete diggings in the short summer season before snow or rain arrives.
“This approach saves the time and hassle of staging a 10- to 15-person crew in the field, where you have to carry your food and shelter and where you are making good time if you’re driving 10 miles per hour,” Anemone said.
“This new approach won’t guarantee results, but it sure helps you prioritize your time in the field, instead of just relying on a hunch.”
The Epoch Times publishes in 35 countries and in 19 languages. Subscribe to our e-newsletter.