Google researcher discovers unmapped Maya site in Mexico using 48 AI agents

요약

AI tech is quickly transforming many different fields of research, including archaeology, as this discovery shows.

본문

A mockup of how a Mayan site may have looked next to a laptop screen showing LiDAR scans of a terrain — A mock-up made by Google Gemini (left) showing how the Mayan site may have looked in AD 700, next to a LiDAR scan of the hilltop (right). (Image credit: Pietro Miotti)

Share this article 0 Join the conversation Add us as a preferred source on Google Subscribe to our newsletter

AI agents have found what looks like an undiscovered Maya site
The discovery came from a scan of LiDAR data collected by Mexico
Experts are now investigating the site that the AI has flagged up

While some of AI's 'talents' — like putting together decent-looking restaurant menus — could legitimately be called into question, there's no doubt that these bots and agents excel at spotting patterns in vast troves of data, and the latest evidence comes from the potential discovery of a hidden Maya archaeological site in Mexico.

Google researcher Pietro Miotti described having a "random thought on vacation" about how AI agents might be used to sift through LiDAR datasets — topographical maps of Earth's terrain, captured from space satellites.

LiDAR (Light Detection and Ranging) lasers can cut through cloud cover and forest canopies, enabling researchers to find shapes in the landscape that aren't visible to the naked eye (or in landscapes that aren't even accessible to archaeologists).

Latest Videos FromTechRadarWatch full video here:

Miotti tasked 48 agents from different AI apps with scouring through a NASA database of LiDAR information collected across Peru, and the AI came back with multiple hits on structures that could be buildings. A second scan by the agents identified one particular site that hasn't yet been mentioned in scientific literature.

'LiDAR the entire planet'

My AI agents found an unmapped Maya site in Mexico, using LiDAR data from a NASA dataset. 72 hours from a random thought on vacation to a reply from Mexico's national archaeology institute. What a time to be alive… https://t.co/3bOMEdUFdFNovember 10, 2026

The AI assistance didn't stop there: Miotti's bot helpers told him who he should get in touch with about the discovery (Mexico's National Institute of Anthropology and History or INAH), and then composed an email (in Spanish) to the relevant agency, including details of the find and where on the map it's located.

Representatives from INAH got in touch, and the experts there are investigating further: a real result, in 72 hours. The site's status as an ancient Maya site hasn't been confirmed yet, but it looks like a promising lead, and one that was made possible by AI.

"I think we're on the brink of a revolution across every science, not just coding, physics and math," says Miotti. "And at this point we should LiDAR the entire planet and let agents help us find the rest."

Get daily insight, inspiration and deals in your inbox

Miotti still wasn't finished there, and got Gemini to generate an image of how the site may have looked in 700 CE — when the Maya people were actually living there. In the modern era, some serious exploring can be done from a computer through a team of AI bots, as well as out in the field.

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.

An Apple MacBook Air against a white background

The best laptops for all budgets

➡️ Read our full guide to the best laptops
1. Best overall:
Apple MacBook Air 13-inch M5
2. Best budget:
Apple MacBook Neo
3. Best Windows 11 laptop
Microsoft Surface Laptop 13-inch
4. Best thin and light:
Lenovo Yoga Slim 9i
5. Best Ultrabook
Asus Zenbook S 16

TOPICS

David Nield Freelance Contributor

Dave is a freelance tech journalist who has been writing about gadgets, apps and the web for more than two decades. Based out of Stockport, England, on TechRadar you'll find him covering news, features and reviews, particularly for phones, tablets and wearables. Working to ensure our breaking news coverage is the best in the business over weekends, David also has bylines at Gizmodo, T3, PopSci and a few other places besides, as well as being many years editing the likes of PC Explorer and The Hardware Handbook.

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.