Artificial intelligence has helped archaeologists uncover an ancient lost work of art.

The Nazca Lines in Peru are ancient geoglyphs, images carved into the landscape. First formally studied in 1926, they depict people, animals, plants, and geometric shapes. The formations vary in size, with some of the biggest running up to 30 miles long. Their exact purpose is unknown, although some archaeologists think they may have had religious or spiritual significance. Local guides believe the lines relate to sources of water.

Some Nazca lines span miles of Peruvian countryside. Flickr/Christian Haugen

New geoglyphs are still being discovered and can be hard to spot due to changes in the landscape, with natural erosion and urbanization breaking them up.

A research team from Yamagata University recently announced it had discovered 142 new Nazca formations, including images of birds, monkeys, fish, snakes, and foxes.

The team partnered with IBM to try and train its deep-learning platform Watson to look for hard-to-find geoglyphs.

They fed the AI with aerial images to see if it could spot any more Nazca outlines. Watson threw up a few candidates, from which the researchers picked the most promising. Sure enough, their field work confirmed the AI had found an ancient Nazca artwork.

The find was a relatively small depiction of a humanoid figure spanning just 16 feet. The researchers estimate the figure dates from roughly 100 BC to AD 100, making it at roughly 2,000 years old.

The project's success has prompted Yamagata University to announce a more prolonged partnership with IBM, and will create a full location map of the geoglyphs to help future archaeologists.

Read more from the original source:

Scientists used IBM Watson to discover an ancient humanoid stick figure - Business Insider