Juli Schilliger, an expert in ancient scroll research, and Youssef Nader, a specialist in restoring Herculaneum's carbonized scrolls, share their insights on the groundbreaking Vesuvius Challenge. They discuss the remarkable technology, like X-ray tomography, used to virtually unwrap these fragile artifacts. The duo also highlights the complexities of deciphering two-thousand-year-old text, the role of machine learning in their success, and the incredible potential for future applications of their techniques in various fields.
Read more
AI Summary
AI Chapters
Episode notes
auto_awesome
Podcast summary created with Snipd AI
Quick takeaways
The Vesuvius Challenge harnesses crowdsourcing to reconstruct texts from carbonized scrolls, making ancient knowledge accessible through modern technology.
Innovative algorithms used by Schiliger and Nader improved the identification of ink on fragile scrolls, paving the way for future discoveries.
Deep dives
The Preservation of Ancient Knowledge
In 79 AD, the eruption of Mount Vesuvius buried the Roman town of Herculaneum under a thick layer of ash and mud, effectively preserving the ancient villa of Lucas Calponius Piso. This villa contained a vast library of papyrus scrolls that were carbonized but remained intact due to the unique conditions created by the volcanic debris. It wasn't until the mid-1700s that these scrolls were discovered, but their fragile state made them challenging to open without damaging them further. A modern breakthrough came in 2015 with the advent of x-ray tomography and computer vision techniques, which allowed researchers to virtually unwrap these scrolls without physical manipulation, showing that ancient knowledge can still be accessed today.
The Vesuvius Challenge: A Crowdsourced Approach
The Vesuvius Challenge was initiated to harness the power of crowdsourcing in deciphering the texts of the carbonized scrolls, aiming to reconstruct their contents through collaborative efforts. Participants, including Julie Schiliger and Yusef Nader from the winning team, utilized various computational methods to analyze and interpret the data derived from the scrolls. Their objective involved reading passages of 140 characters each with a high degree of accuracy, requiring innovative techniques in image processing and machine learning. The challenge not only engaged a global community of researchers but also revitalized the quest to reveal lost historical texts from antiquity.
Utilizing Advanced Technology for Ink Detection
Both Schiliger and Nader implemented unique algorithms for detecting ink on the scrolls, with specific approaches tailored to address the challenge of carbon-based inks that were difficult to visualize in x-ray scans. Schiliger utilized a segmentation algorithm based on optical flow techniques which improved the accuracy and speed of isolating scroll surfaces in the three-dimensional imaging data. Meanwhile, Nader focused on employing self-supervised learning strategies that allowed models to iteratively improve their accuracy in distinguishing ink from the background. These technological innovations significantly contributed to the successful identification of characters within the scrolls, thus revealing parts of ancient texts that were previously unreadable.
Looking Ahead: Future of Scroll Deciphering
The ongoing efforts in the Vesuvius Challenge and related projects indicate a promising future for the exploration of ancient texts and scrolls. Researchers like Schiliger and Nader have transitioned from competition to collaboration, now contributing to organized efforts to further the unrolling and reading of remaining scrolls. There exists potential for applying these developed technologies beyond Herculaneum, as researchers explore similar techniques on other significant historical materials, including Egyptian papyrus. The successful unveiling of ancient writings not only benefits historical understanding but may also inspire advancements in fields such as medical imaging and data analysis in modern contexts.
In 79 AD, in the ancient Roman town of Herculaneum, twenty meters of hot mud and ash buried an enormous villa once owned by the father-in-law of Julius Caesar. Inside, there was a vast library of papyrus scrolls.
The scrolls were carbonized by the heat of the volcanic debris, but they were trapped underground where they remained preserved.
It wasn’t until the 1750s that the scrolls were discovered, but they were fragile and resistant to being opened and read.
Then, in 2015, researchers used X-ray tomography and computer vision to virtually unwrap the scrolls.
Last year, the Vesuvius Challenge was launched by Nat Friedman, Daniel Gross, and Brent Seales to crowdsource the process of reconstructing the text from the scrolls.
Juli Schilliger and Youssef Nader are two members from the winning team. They join the show to talk about the computational approaches they used to reconstruct the scroll text.
For interested listeners, the 2024 Vesuvius Challenge is now live, with new challenges and prizes. Check out ScrollPrize.org to learn more.
Jordi Mon Companys is a product manager and marketer that specializes in software delivery, developer experience, cloud native and open source. He has developed his career at companies like GitLab, Weaveworks, Harness and other platform and devtool providers. His interests range from software supply chain security to open source innovation. You can reach out to him on Twitter at @jordimonpmm