basin 2 hi_res_1

Artificial ‘brain’ network hunts for fossils

WASHINGTON U.-ST. LOUIS (US) — Artificial intelligence is giving paleontologists a leg up in locating fossils—usually a task akin to finding the proverbial needle in a haystack.

Traditionally, fossil-hunters have only been able to make educated guesses about fossil locations.

“I don’t want to say it’s total luck,” says Glenn Conroy, professor of physical anthropology at Washington University in St. Louis, “but it’s a combination of hard work, meticulous planning and, well, a good dose of luck.”

The Great Divide Basin, a 4,000-square-mile stretch of rocky desert in Wyoming. (Credit: Robert Anemone)

In 1991, Conroy discovered the fossils of the first—and still the only—known pre-human ape ever found south of the equator in Africa after only 30 minutes of searching a limestone cave in Namibia. He and researchers at Western Michigan University have now developed a software model that may make luck unnecessary.

Using artificial neural networks (ANNs)—computer networks that imitate the workings of the human brain—Conroy and colleagues Robert Anemone, and Charles Emerson, developed a computer model that can pinpoint productive fossil sites in the Great Divide Basin, a 4,000-square-mile stretch of rocky desert in Wyoming that has been a productive area for fossil hunters, yielding 50 million- to 70 million-year-old early mammal fossils.

The software builds on satellite imagery and maps fossil-hunters have used for years to locate the best fossil sites. It just takes the process a step further, Conroy says.

With information gathered from maps and satellite imagery—such as elevation, slope, terrain, and many other landscape features—the networks were “trained” to use details of existing fossiliferous areas to accurately predict the locations of other fossil sites elsewhere in the Great Divide Basin.

Because few sites are 100 percent identical, researchers had to “teach” the ANNs to recognize sites that shared key features in common that then used pattern recognition to identify sites that share similar features.

“The beauty and power of neural networks lie in the fact that they are capable of learning,” says Conroy, also a professor of anatomy and neurobiology. “You just need to give them a rule to deal with things they don’t know.”

When Conroy and colleagues tested the software at the Great Divide Basin last summer, it correctly identified 79 percent of the area’s known fossil sites, and 99 percent of the sites it tagged contained fossils.

The scientists also tested the software on the nearby Bison Basin, also in Wyoming. Despite having been taught to recognize fossil sites at a neighboring location (the Great Divide Basin), the ANNs correctly identified four fossil sites in the Bison Basin.

“That gave us encouragement that a blind test based on a neural network for a different basin still gave us pretty good predictive results,” says Conroy, who will next use the software to search for early hominid fossil sites in South Africa.

“In the old days, we’d all bring different maps, and start walking,” Conroy says. “Now, we’re talking about ways to improve one’s chances.”

More news from Washington University in St. Louis: