Especially in areas that are unsuitable for human exploration, archaeologists are increasingly coming up with inventive ways to use satellite imagery and artificial intelligence in their hunt for secrets that lay hidden.
Researchers at Khalifa University in Abu Dhabi have developed a high-tech solution to searching huge, arid areas for potential archaeological sites — a desert spanning 250,000 square miles on the Arabian Peninsula.
Archaeologists from Khalifa University are using AI in combination with satellite imagery and synthetic aperture radar (SAR) to detect new archaeological sites beneath the ever-shifting sands of the Empty Quarter desert.
The conventional method used by archaeologists to identify possible sites of interest is ground surveys, but in arid environments like the desert, this can be a laborious and challenging process. Sand and dust storms in the desert can make it difficult to identify potential sites, and dune patterns can further complicate matters. Nevertheless, in recent years, remote sensing—which uses optical satellite images from websites like Google Earth—has become more and more popular as a means of scouring large areas for unusual features.
In order to get beyond these obstacles, the group developed a machine learning algorithm to examine pictures obtained through the use of synthetic aperture radar (SAR), a satellite imaging method that employs radio waves to find objects hidden beneath surfaces like ice, sand, and vegetation. Data from Saruq Al-Hadid, a settlement in the desert outside of Dubai with signs of 5,000 years of activity, which is already well-known to archaeologists, was used to train the algorithm.
Once the algorithm was trained, it gave the team an indication of other potential areas nearby that are still not excavated. The technology is precise to within 50 centimeters and can create 3D models of the expected structure that will give archaeologists a better idea of what’s buried below. This innovative approach could revolutionize archaeological research in remote and hard-to-explore areas.
In collaboration with Dubai Culture, the government organization that manages the site, the team conducted a ground survey using a ground-penetrating radar, which “replicated what the satellite measured from space,” says Diana Francis, an atmospheric scientist and one of the lead researchers on the project.
Now, Dubai Culture plans to excavate the newly identified areas — and Francis hopes the technique can uncover more buried archaeological treasures in the future.
SAR imagery has been in use since the 1980s, and machine learning has been gaining traction in archaeology. But the use of the two together is a novel application, says Francis, and to her knowledge, is a first in archaeology.
If successful, the project will broaden the applications of AI in the field of archaeology. Some experts have urged caution against “over-reliance” on the technology, however.
Hugh Thomas, an archaeology lecturer at the University of Sydney, told CNN that there remains nothing better than a “trained archaeological eye” to detect sites. “The way that I would like to use this kind of technology is on areas that perhaps have either no or a very low probability of archaeological sites, therefore allowing researchers to focus more on other areas where we expect there to be more found,” he said.
The technology’s real test, and hopefully its validation, will take place when excavations at the Saruq Al Hadid complex start next month. According to Dubai Culture, only about 10% of the complex’s 2.3 square mile area has been fully excavated. By using the technology, Dubai Culture hopes to uncover more sites if archaeologists discover the structures that the algorithm has predicted.
The team plans to continue training the machine learning algorithm to improve its precision, before expanding its use to other areas, including Saudi Arabia, Egypt, and the deserts of Africa.
Recently A.I. was instrumental in discovering over 300 new Nazca petroglyphs in Peru, showcasing its global potential in archaeological exploration. Arkeonews reported on the findings by researchers at Japan’s Yamagata University last week.
DOI:10.3390/geosciences13060179
Cover Image: Sahara dunes at sunset.
