In the good old days of paleontology, scientists had to get dirty in the field. These days, robots do it for them. Okay, not quite, but a new high tech approach to digging in the dirt is helping paleontologists dig smarter: artificial intelligence.
Normally, discovering fossils depends largely on luck. Paleontologists can take educated guesses as to where to search—trekking down dry stream beds to look for bones that might have eroded off slopes, for instance—but they mostly depend on walking around to see what catches the eye. If they are lucky, they can cover ground in bucking and bouncing jeeps down dirt roads set up by oil and gas companies. In any case, traditional approaches can be challenging, lengthy—and fruitless.
Increasingly, paleontologists are relying on technology to narrow their search for fossils. For instance, Google Earth has helped identify sites in South Africa containing fossils of the ancient hominid Australopithecus sediba.
And it goes further than that. Computer models built of a vast array of artificial neurons make up networks that can search fossil sites for anomalies. Rather than a scientist walking for hundreds of miles, squinting into the sun, the computer scans and analyzes the landscape, looking for prime fossil sites. One model looked at 100 known fossil sites. Scientists told the model about the first 75, to train it. The computer then spotted 20 of the remaining 25 all by itself.
The scientists then unleashed their computer on unknown sites. It showed them places to look, and at first they were disappointed. Scientific American writes:
Anemone’s neural network pointed out several places to search. Initially, these proved fruitless—the scientists unearthed many fossils at the first recommended sites, but not the kind they wanted. The researchers had the neural network search for fossils in areas that past geologic surveys declared were in the Wasatch Formation—former lakeshore and riverside areas where they expected to unearth primate fossils. But on arrival at the first dozen or so sites, it was clear the original surveys were in error. Instead, those locations were actually in the Green River Formation—former lakebed areas with many aquatic fossils but few mammal bones.
As these models learn more, they’ll be able to spot better sites and lead to better fossils. It could make for better, faster digs, but the work will still require experts to get down in the dirt and dig up the fossils.
More from Smithsonian.com: