AI hunting for hidden secrets in the sand in world’s most barren desert dubbed The Empty Quarter left unexplored by man
SECRETS buried deep in the sands of the Arabian Peninsular will soon be uncovered thanks to AI.
Archaeologists have turned to artificial intelligence to help detect potential sites in the Rub al-Khali desert, Abu Dhabi.
The vast stretch of desert, better known as the “The Empty Quarter”, is 250,000 square miles of ochre-coloured dunes.
The desert is the largest area of continuous sand in the world.
It occupies more than one-fourth of Saudi Arabia’s total area and features varied topography.
One of the driest regions in the world, the Rubʿ al-Khali is virtually uninhabited and largely unexplored.
The harsh conditions of the desert can often hide potential ancient sites.
However, researchers at Khalifa University in Abu Dhabi have developed a high-tech solution to make the search easier.
The team created a machine learning algorithm to analyse images collected by a synthetic aperture radar (SAR), a satellite imagery technique that uses radio waves to detect objects hidden beneath surfaces including, vegetation, sand, soil and ice.
Diana Francis, an atmospheric scientist and one of the lead researchers on the project, said: “We needed something to guide us and focus our research.”
Francis then trained the machine to use data from an already-known site, Saruq Al-Hadid in Dubai.
She said: “Once it was trained, it gave us an indication of other potential areas that are still not excavated.”
She added that the technology was precise to within 19 inches and could create 3D models of the expected structure to give archaeologists a better idea of what’s buried below.
Traditionally, archaeologists have used ground surveys to detect potential sites, while optical satellite images have gained popularity for searching large areas for unusual features.
However, the new AI technology will make the search easier.
Khalifa University isn’t alone in using artificial intelligence to detect potential sites.
Amina Jambajantsan, a PhD student at the Max Planck Institute, is using machine learning to speed up the “tedious job” of searching through high-resolution drone and satellite images for potential sites of interest.
Meanwhile, researchers from Yamagata University have been using AI technology to decipher Nazca civilisation geoglyphs in Peru.
Using the new tech, archaeologists found 303 geoglyphs, which they later confirmed by visiting the sites photographed in their search.
Archaeologist Masato Sakai, from Yamagata University, said: “The use of AI in research has allowed us to map the distribution of geoglyphs in a faster and more precise way.”
“The traditional method of study, which consisted of visually identifying the geoglyphs from high-resolution images of this vast area, was slow and carried the risk of overlooking some of them.”
In a paper published in the Proceedings of the National Academy of Sciences (PNAS), the authors explained the discovery process and discoveries themselves.
The AI model was particularly good at picking up smaller relief-type geoglyphs which are harder to spot with the naked eye.
The authors said: “Of the 303 newly discovered figurative geoglyphs, 178 were individually suggested by the AI, and 125 were not individually AI-suggested.”