We may not understand them, but that doesn’t stop us from finding them. We’re talking Nazca lines – those huge line drawings of humanoids, animals, geometric shapes and unidentifiable things etched primarily into Peru’s Nazca Desert and a few other places in South America. Hidden from non-indigenous people – ironically, because of their size – the Nazca lines were first “discovered” by airplanes. Now that the rest of us know what they look like, new techniques are being developed to find more that may be too faint to see. One such tool is artificial intelligence, which is how researchers recently found a giant humanoid figure. Does IBM’s Watson get credit for this “discovery” with an asterisk to denote “not the human Watson”?
“A research team led by Professor Masato Sakai (Cultural anthropology, Andean archeology) at Yamagata University discovered 142 new geoglyphs, which depict people, animals and other beings, on the Nasca Pampa and surrounding area in Peru, South America.
Situated mainly in the west of the Nasca Pampa, these new geoglyphs were identified through fieldwork and analyzing high-resolution 3D data, among other activities conducted up to 2018. The biomorphic geoglyphs are thought to date back to at least 100 BC to AD 300.”
The Nasca (or Nazca) Pampa is a relatively small area (12 by 9 miles or 20 by 15 km) where the giant geoglyphs that have become known as the Nazca lines were “discovered” – first by people standing on nearby hills and then in the 1940s by pilots. Formed by removing lines of reddish-brown stones to expose the lighter clay earth beneath them, the original purpose and creators of the Nazca lines are disputed to this day. Those disputes plus the sheer number is why the latest “discovery” is generating excitement, not to mention the potential for finding more using artificial intelligence.
“These geoglyphs depicted people and many different animals (including birds, monkeys, fish, snakes, foxes, felines, and camelids). All of these figures were created by removing the black stones that cover the land, thereby exposing the white sand beneath. They are categorized into two main types, depending on whether the geoglyphs were made by removing stones to form lines (type A) or to form solid-colored surfaces (type B). Type A geoglyphs are generally large in scale, and all of the figures thatspan more than 50 meters(165 feet) across belong to this type, while most type B geoglyphs are less than 50 meters(165 feet). Out of the newly identified geoglyphs, the longest stretched over 100 meters (330 feet) across and was categorized under type A, while the smallest was under 5 meters (16 feet) and belonged to type B.”
As explained in detail in the press release, Professor Sakai and his team analyzed high-resolution 3D aerial photos and other data collected from 2004 to 2019 in order to identify potential Nazca lines, which were then confirmed by on-site observations. That’s how 142 of the shapes were determined, including one depicting a two-headed snake eating humans. (You can see it, along with many more of the figures, here). However, the last shape identified was the result of a collaboration between the team and IBM Japan. Together, they developed an AI model on an IBM Power System AC922 server using the deep learning platform IBM Watson Machine Learning Community Edition. The humanoid it found “represented the first glyph at the site discovered by an AI.” Get ready for more.
“Building on the foundation of the first collaborative feasibility study with IBM Japan, Yamagata University has newly entered into an academic agreement to collaborate with the IBM Research, and tap into IBM’s extensive initiatives to analyze and leverage large, complex data sets, such as remote sensing and geographical data, with AI. Moving forward, researchers will enrich their understanding about the distribution of the geoglyphs by utilizing IBM PAIRS Geoscope (IBM PAIRS), an AI platform from the IBM Thomas J. Watson Research Center for analyzing 3D spatio-temporal data quickly and efficiently.”
In these days of controversy surrounding the usage of AI for nefarious purposes, it’s refreshing to learn of projects employing it for the “discovery” and analysis of the Nazca lines – without a profit motive driving it. The lines are in a protected World Heritage Site which guards them from most intrusions (except for the occasional wayward trucker). Let’s hope the sharing of the new and detailed images will satisfy the curious … and someday explain if the lines are the projects of aliens or an advanced human culture trying to send us a message – a message besides “Please don’t erase!”