AI Helps Decode Mysterious Prehistoric Cave Markings Known as Finger Flutings

Every mark left on a cave wall is a conversation in time. Thousands of years ago, someone pressed their fingers into a soft mineral film and drew sinuous lines – what archaeologists call flutes on the fingers. These gestures are preserved, but the people behind them remain unknown.

This anonymity may begin to disappear. In a new article published in Scientific reportsResearchers have unveiled an artificial intelligence system that analyzes modern finger grooves to test whether the gender of their ancient creators could one day be determined, offering a rare way to trace identity back into the deep past.

“Whether the marks were left by men or women, there could be real-world consequences,” said Dr. Andrea Jalandoni, lead researcher, in the recent study. press release.

What are finger flutings?

Finger flutes are prehistoric marks made by fingertips through clay or mineral deposits on the walls, ceilings and floors of limestone caves. They appear at archaeological sites throughout Western Europe and Australia, dating back to approximately 60,000–12,000 years ago, during the late Middle and Upper Paleolithic period.

Archaeologists consider them to be among the earliest known examples of symbolic expression and one of the few art forms created by both Homo sapiens and Neanderthals.

“Finger grooves can reveal information about age, gender, height, hand, and mark selection patterns,” the authors write in the study, describing how their machine learning system combines physical reproduction with digital modeling.

Previous attempts To determine who made the flutes on the fingers, it was necessary to measure the width of the fingers, a method that has been criticized in recent reviews as unreliable due to differences in cave surfaces and measurement errors. A new approach based on artificial intelligence offers a more objective way to test these ideas.

---

Read more: AI can translate a 5,000-year-old language, saving time and historical knowledge

---

Using artificial intelligence and virtual reality to decode finger grooves

The researchers conducted two controlled experiments with 96 adult participants. Each person created nine flutes twice: once in a moonmilk clay surrogate simulating cave walls, and once in virtual reality (VR) using Meta Quest 3. The images were used to train two image recognition models designed to detect geometric differences in signs.

VR waves did not reliably determine gender, but tactile waves performed much better.

“Under one training condition, the models achieved an accuracy of about 84 percent, and one model achieved a relatively high discrimination rate,” Dr. Gervase Tuxworth of Murdoch University said in a press release.

However, the models captured installation artifacts rather than features that could be generalized to caves. However, the study shows a reproducible pipeline linking archaeological methods and artificial intelligence, an important step towards a more rigorous digital archaeology.

Make analysis of ancient art open and reproducible

The researchers stress that their work is a proof of concept, not a definitive method. While the models performed best on physical clay samples, they also revealed the limitations of existing AI approaches, with training models tied to the experimental setup rather than characteristics that could be applied to ancient caves.

“We have published the code and materials so that others can replicate the experiment, critique it and scale it up,” said Dr Robert Haubt, co-author and computer scientist at the Australian Research Center for Human Evolution. “That’s how a proof of concept becomes a reliable tool.”

The open dataset and command code are available at GitHub. They suggest that the framework could also be adapted to analyze other forms of ancient markings, from petroglyphs to tool wear, expanding its use.

---

Read more: Artificial intelligence revives a 2,000-year-old Roman scroll that burned during the eruption of Vesuvius

---

Article Sources

Our authors in discovermagazine.com use peer-reviewed research and high-quality sources for our articles, and our editors review scientific accuracy and editorial standards. Review the sources used below for this article: