It’s not just for ChatGPT. Archaeologists have increasingly found new ways to use artificial intelligence in their search for hidden truths – especially in terrain inhospitable to human exploration.
Now a team of researchers at Khalifa University in Abu Dhabi has developed a machine-learning algorithm to help them explore large parts of the Rub al-Khali, or “Empty Quarter,” a 400,000-square-mile desert on the Arabian Peninsula. to search. The desert is home to the site of Saruq Al-Hadid, which contains evidence of 5,000 years of human activity. Using data from this site, the team trained their algorithm to detect other potential dig areas nearby.
Traditional ground surveys are difficult and expensive to conduct in the desert, while sandstorms and dune patterns have proven to be persistent obstacles to interpreting satellite images. The algorithm can analyze images acquired using synthetic aperture radar (SAR), a powerful radar system that can penetrate sand and vegetation, allowing researchers to see hidden structures beneath the surface.
Courtesy of Khalifa University/Benromdhane et al. 2023.
The archaeologists used satellite-based SAR, which can cover a larger area than is possible from the ground. With the financial support of Dubai Culture, the government body that manages Saruq Al-Hadid, the team was also able to conduct a ground survey using radar to replicate the satellite’s results. Using machine learning and deep learning techniques, the team has managed to create an algorithm capable of automated detection of features in the landscape, accurate up to 50 cm away, and able to create 3D models of the expected produce structure.
“A major problem in remote sensing studies of arid and semi-arid environments such as the United Arab Emirates (UAE) is the degradation of image content by dust particles or cloud cover,” the researchers wrote in an article published in Geosciences last June – a problem that SAR, which is rarely available to archaeologists due to its cost and complexity, has been able to avoid. “To the best of the authors’ knowledge,” they add, “the current study is the first to use advanced image processing and machine learning techniques for the detection, prediction and guidance of archeology within the area of interest and the Rub’ Al -study. -Khali Desert.”
Courtesy of Khalifa University/Benromdhane et al. 2023.
If successful, the project will broaden the applications of AI in the field of archaeology. The application of AI in archeology is not limited to the Arabian Peninsula. For example, AI played a key role in the discovery of four new Nazca petroglyphs in Peru, demonstrating the global potential of these petroglyphs in archaeological research. Artnet news reported on the findings of researchers from Japan’s Yamagata University in 2023. These researchers suggested that AI could identify new petroglyph candidates 21 times faster than the naked eye.
However, some experts have urged caution against “over-reliance” on the technology. Hugh Thomas, a lecturer in archeology at the University of Sydney, told CNN that there is nothing better than a “trained archaeological eye” to pinpoint sites. “The way I would like to use this kind of technology is in areas where there may be no or very low probability of archaeological sites, allowing researchers to focus more on other areas where we expect more to be found,” he says . said.
Dubai Culture plans to begin excavations of the areas of interest identified by the algorithm at Saruq Al-Hadid next month. Only about 10 percent of the site, covering an area of 2.3 square kilometers, has been exposed. If AI’s predictions are correct, Dubai Culture has explained that it will continue to use the technology. Diana Francis, one of the project’s lead researchers, told CNN: “The idea is to export (the technology) to other areas, especially Saudi Arabia, Egypt and perhaps also the deserts in Africa.”
