Thousands of years ago, a Mount Vesuvius eruption covered more than 1,800 scrolls in ash, destroying the precious information on them. Or so we thought!
Today, thanks to AI, we have a chance to know what was in the scrolls that were lost alongside Pompeii.
Yes, we can read scrolls burned as badly as this!
One student managed to actually decipher one of the Herculaneum scrolls using AI and a humble Nvidia GeForce GTX 1070 graphics card, something which got him an award in the so-called Vesuvius challenge (picture above).
His story makes for an exciting look into what will be possible next in the field of archaeology.
From a Tom’s Hardware report:
In 2019, Dr. Brent Seales and other researchers made a breakthrough by augmenting their X-rays with a particle accelerator to scan two scrolls. Earlier this year, those X-rays were run through a machine-learning model to make the ink more legible. The Vesuvius Challenge offers prizes to anyone who can clearly decipher words from the two scrolls.
Luke Farritor, an undergrad at the University of Nebraska-Lincoln and Space-X intern, used his old GTX 1070 to train an AI model to detect “crackle patterns,” which indicate where an ink character used to be. Eventually, his GTX 1070-trained AI was able to identify the Greek word πορφυρας (or porphyras), which is either the adjective for purple or the noun for purple dye or purple clothes. Deciphering this single word earned Farritor a $40,000 prize.
Indeed, imagine what could come next! Nvidia’s blog post about the achievement included some more details about the Vesuvius challenge.
Scientists have already confirmed some mythical lost cities in the Amazon using Lidar, ancient locations are brought back to life using AR and, if people only used machine learning to try to crack codes not replace jobs, imagine how much more we could learn about ourselves and our past.