Artificial intelligence is pushing the world into the future with platforms that can mimic the way humans speak and even process information — but the technology could also help solve some of history’s great mysteries.
Researchers at the Yamagata University Institute of Nasca and IBM Japan used a deep learning AI model to discover Peruvian geographic symbols etched in the Nazca Desert dating back to between 500 BC and 500 AD.
Geoglyphs are depressions made in the earth to create various shapes and lines, Peru has the Nazca lines which are considered the most famous geoglyphs in the world.
Geoglyphs are often large, with previously discovered Nazca Lines measuring up to 1,200 feet long, making them virtually impossible to spot on the ground. Archaeologists first discovered Peruvian geoglyphs after the advent of airplanes nearly 100 years ago, when pilots spotted the shapes from the air.
Using an artificial intelligence system, the researchers were able to discover four new geoglyphs depicting a “humanoid” figure holding what looked like a stick, one depicting a fish, another a bird, and One depicts a pair of legs.
Mysterious Nazca Lines Reveal Their Secrets
There is debate in academic circles as to why people make these geoglyphs, with some speculating that they honor deities who they believe can see the shapes from above, while others believe aliens played a role and the lines are extraterrestrial The remains of the spaceship airport.
Mysterious ‘humanoid’ figure found in Peru
The Yamagata researchers said that until recently, archaeologists and researchers would only examine aerial photos of the area with the naked eye in an attempt to find new geographic symbols, which “requires a lot of time and poses challenges for efficiency and scalability.”
The scientists turned to artificial intelligence in their quest, training a deep-learning system to identify potential Nazca Lines based on previously discovered geoglyphs in the region.
“Due to the need to detect unconfirmed candidate geoglyphs, careful consideration and ingenuity are required in order to train a deep learning object detection model using training data of very limited quality and quantity,” the researchers said.
Ancient Nazca lines damaged after truck drives into archaeological site
Using artificial intelligence paid off for the Yamagata team, as the technology worked 21 times faster than when only humans were analyzing such photos.
“We identified new landmark candidates approximately 21 times faster than with the naked eye alone,” the researchers said in their study published in the Journal of Archaeological Science. “In a new paradigm combining fieldwork and artificial intelligence, this method will benefit the future of archaeology.”
Russia’s Mysterious ‘Nazca Lines’ Are Thousands of Years Old
After successfully integrating AI into archaeological research, the Yamagata researchers will now work with the New York-based IBM TJ Watson Research Center to expand their research to the entire region where the line was discovered.
“Furthermore, we plan to collaborate with the Peruvian Ministry of Culture on a campaign aimed at preserving geoglyphs discovered using AI,” the researchers said.
Archaeologists have used artificial intelligence before to unravel other mysteries of the world, with computers taking on what is often the hardest job for scientists and explorers: scouring the land for artifacts, lost cities and cemeteries.
AI systems trained to detect patterns on land using satellite and sonar imagery have proven fruitful for other archaeologists, with AI detecting Mesopotamian burial sites based on satellite imagery in 2021 , another AI system detected sunken ships with 92 percent accuracy.
700,000-year-old archaeological site found in Greek coal mine believed to be the oldest in the country
AI techniques are also helping scientists translate ancient texts. Researchers at the University of Chicago’s Oriental Institute and Department of Computer Science recently trained a system that can translate ancient inscriptions with 80 percent accuracy using thousands of images and ancient characters.
Scientists at Yamagata University emphasized that archaeologists are likely to see a surge in the use of artificial intelligence in the future.
Click here for the Fox News app
“The proliferation of drones, robotics, and light detection and ranging (LiDAR), big data, and artificial intelligence has fueled recent advances in automated sensing that may drive the next wave of archaeological discoveries,” they said.