A 21-year-old computer science student, Luke Farritor, from the University of Nebraska–Lincoln, has reportedly made a groundbreaking discovery with the help of artificial intelligence that allowed him to read the first text inside a carbonized scroll from the ancient Roman city of Herculaneum.
What Happened: This scroll had been unreadable since the eruption of Mount Vesuvius in AD 79, which also buried Pompeii, according to an article in the Nature journal.
Farritor developed a machine-learning algorithm that successfully detected Greek letters on several lines of the rolled-up papyrus. To achieve this, he utilized subtle differences in surface texture to train his neural network and highlight the ink, such as the word ‘purple’ (πορϕυρας).
The Vesuvius Challenge, an initiative offering awards for reading the ancient scrolls, announced Farritor as the winner of the ‘first letters’ prize, valued at $40,000.
See Also: Elon Musk Brings TikTok’s Obsession With Fall Of Roman Empire On X
This contest allowed contestants to unlock the mysteries of the scrolls by studying flat images produced by an X-ray computed tomography (CT) scan, showcasing areas of papyrus coated with ink. Farritor and other participants used the images to identify letters and characters. With this pioneering achievement, the academic community is excited about the potential to uncover more texts from Herculaneum’s library.
Why It Matters: Farritor’s breakthrough marks a significant step in reading previously undecipherable texts from ancient history and literature. It may revolutionize our understanding of the past, offering access to works directly from their original authors, rather than copies made by scribes over centuries.
Machine learning’s application in revealing ancient texts is part of a broader shift, where AI is increasingly aiding scholars in the study of historical documents. This technological progress holds the potential to unveil a wealth of previously unseen texts, including those present in parchment book bindings, palimpsests, and cartonnage, ultimately expanding our knowledge of history and literature.
Photo via Shutterstock
Engineered by Benzinga Neuro, Edited by Ramakrishnan M
The GPT-4-based Benzinga Neuro content generation system exploits the extensive Benzinga Ecosystem, including native data, APIs, and more to create comprehensive and timely stories for you. Learn more.
© 2024 Benzinga.com. Benzinga does not provide investment advice. All rights reserved.
Trade confidently with insights and alerts from analyst ratings, free reports and breaking news that affects the stocks you care about.