By Rob Wu, Dailymail.Com’s technical correspondent
23:57 10 December 2023, updated 23:57 10 December 2023
The uncanny ability of artificial intelligence to detect patterns in large amounts of data could finally unravel some of the thorniest mysteries of the ancient world.
Researchers working with companies like IBM and Google’s Deepmind are on the cusp of deciphering ancient texts once thought unreadable — and even “deciphering” a language unknown from nearly two millennia before the birth of Christ.
Artificial intelligence allows researchers to sift through images much faster than humans, and these technologies could answer fundamental questions about the history of language and perhaps uncover lost works of Greek and Roman writers.
Cracking unknown language
A mysterious and little-known language, “Linear A” discovered on tablets on the island of Crete in 1900, has yet to be deciphered, but artificial intelligence may be able to crack the code.
Among the most famous examples of unknown languages in the world, stones and tablets written in the strange language “LInear A” are the main script used by the Minoan civilization, a Bronze Age kingdom led by King Minos.
The 1,400 Linear A tablets date back to 1800 BC, and despite numerous efforts, they have never been deciphered – another, more recent script found on tablets on the island, Linear B, was discovered in 1953.
This breakthrough came about thanks to the researchers’ realization that recurring words in the language may be place names on the island and that the Linear B script may be similar to ancient Greek.
But Linear A poses a much tougher challenge, as the “original language” is completely unknown – no text in the language has ever been translated.
Arthur Evans, the researcher who found the tablets, said that Linear A is one of the oldest writings ever discovered, and that its similarity to images indicates that it has an essential place in the development of human language.
Researchers from MIT and Google’s Deepmind AI lab used AI to automatically translate texts in Linear B — the first time this has been done, raising hopes that AI could one day be able to unravel texts in Linear A.
Many researchers use techniques such as data mining and natural language processing to uncover patterns within linear AI.
A team from MIT and DeepMind are working on a new system that can decipher lost languages by exploring the relationships between different languages.
Reading in an old library
Discovered in ruins near Pompeii, the Herculaneum Scrolls are surprisingly fragile charred manuscripts that were preserved following the volcanic eruption in 76 AD.
Herculaneum was buried under scorching mud during the volcanic eruption, and the manuscripts were found in 1750 inside a luxurious villa believed to have been owned by Julius Caesar’s father-in-law.
Unlike other libraries from the period, which decayed due to contact with air, the manuscripts were preserved, but were not yet readable.
Artificial intelligence could finally provide a way for researchers to read passages from manuscripts, which remained undeciphered for nearly two millennia after the volcanic eruption.
The research, led by Professor Brent Sales of the University of Kentucky and with a cash prize from Silicon Valley investors, uses artificial intelligence models to decipher the scrolls.
Computer science students used computer tomography (similar to X-ray scans) and artificial intelligence to “read” marks on a scroll of papyrus.
The Herculaneum manuscripts are the only library that has survived from classical times, and researchers hope that there may be undiscovered works by poets and playwrights in ancient Greece and Rome.
Described as a “potential treasure”, the computer science student managed to unlock the first word – ‘purple’ – from a single scroll, winning $40,000 in the Vesuvius Challenge.
“This word is our first excursion into an ancient, unopened book, evoking royalty, wealth and even sarcasm. What would the context show? Pliny the Elder explores the color purple in its natural history as the process of producing purple saury from oysters,” said Professor Sales.
“The Gospel of Mark describes how Jesus was mocked when he was dressed in purple before his crucifixion.
“What exactly this scroll discusses is still unknown, but I believe it will be revealed soon.”
The secret of the Nazca lines
The Nazca Lines, which feature strange animals and humanoids, including one described as an “astronaut,” were first found in 1927 – but no one has ever explained their purpose.
Conspiracy theorists suggest that the massive lines stretching across the Nazca Plateau may have been created by aliens.
Scholars suggest they were likely used as paths for processions, and their massive size makes them visible to the gods.
Now, artificial intelligence is revitalizing the discovery of the new Nazca Lines, which people carved into the Peruvian landscape between 500 BC and 500 AD.
Researchers from Yamagata University have now sped up the process of discovering the new Nazca Lines by 21 times using ‘deep learning’ in partnership with IBM – and are now using artificial intelligence to comb through ‘geographic figures’ missing in previous searches.
Researchers are racing against time as erosion and climate change put the geoglyphs at risk.
“It is essential to identify and protect as many Geoglyphs as possible,” the researchers write.
By being able to discover more mysterious geoglyphs, researchers hope to understand more about how and why they were created.
As technology continues to advance, the field of archaeology is also benefitting from the use of artificial intelligence. AI has the potential to uncover answers to longstanding archaeological mysteries that have baffled researchers for decades. From ancient civilizations to lost artifacts, the possibility of utilizing AI to solve these mysteries is both exciting and promising. In this article, we will explore three major archaeological puzzles that artificial intelligence could soon help unravel, shedding new light on our ancient past.