Scientists are offering $250,000 (£205,000) in prizes for anybody who can read a series of 2,000-year-old manuscripts that were charred during the eruption of Mount Vesuvius. When the volcano blast wiped out Pompeii in 79AD, hundreds of texts from the Herculaneum library were buried and carbonised by the smoking ash and gases. They resurfaced in 1752 in a villa near the Bay of Naples which is once believed to belong to the father-in-law Julius Caesar, but their contents have remained a mystery as scientists judged them too fragile to unfurl. Now a team of researchers has launched a contest after showing that an artificial intelligence system can extract letters and symbols from high-resolution X-ray images of the documents. This machine-learning algorithm was trained to read the ink on both the surface and hidden layers of the unopened scrolls.

The eruption of Mount Vesuvius in AD79 laid waste to Pompeii and nearby Herculaneum where the intense blast of hot gas carbonised hundreds of ancient scrolls in the library of an enormous luxury villa. Now, researchers are launching a global contest to read the charred papyri after demonstrating that an artificial intelligence programme can extract letters and symbols from high-resolution X-ray images of the fragile, unrolled documents. Scientists led by Prof Brent Seales, a computer scientist at the University of Kentucky, were able to read the ink on surface and hidden layers of scrolls by training a machine-learning algorithm to spot subtle differences in the papyrus structure captured by the X-ray images. "We've shown how to read the ink of Herculaneum. That gives us the opportunity to reveal 50, 70, maybe 80% of the entire collection," said Seales.

A supercomputer programmed to think like the notorious Zodiac killer could help solve one of the most difficult cases in US law enforcement history. A new artificial intelligence software designed to understand human language may be able to decipher secret messages left by the notorious serial killer who has evaded justice for decades. The computer was commanded to think like the Zodiac and produced some creepy poetry when fed all the known writings of the elusive criminal, it was learned Thursday. A University of Southern California professor created an artificial intelligence software that was designed to help crack the code of the Z340, the Zodiac killer's famous cipher. The ciphers, which were sent with letters to the police and newspapers in Northern California during the 1960s and 70s, contain letters and symbols that may hide clues as to the killer's identity.