CHM Live | AI Decodes Ancient History: The Herculaneum Scrolls
Computer History Museum
The Vesuvius Challenge employs advanced X-ray tomography and machine learning to decipher ancient, carbonized scrolls from Herculaneum, which were buried by the 79 CE eruption of Mount Vesuvius. Because these artifacts are too fragile for physical unrolling, researchers use analytical AI to enhance the contrast of ink that remains invisible in standard scans. This open-source project, involving papyrologist Federica Nicolardi, computer scientist Brent Seales, and entrepreneur Nat Friedman, has successfully recovered multiple columns of Epicurean philosophical text. By crowdsourcing solutions through a competitive, open-source model, the team has overcome significant hurdles in segmenting distorted papyrus layers. This work represents a major breakthrough in heritage science, enabling the recovery of lost classical literature and providing a scalable methodology for analyzing thousands of still-buried scrolls without risking their destruction.
Sign in to continue reading, translating and more.
Open full episode in Podwise
