It is not the eye of Shiva, it is much more powerful. It is able to detect on the ground a piece of ancient pottery, no matter how small. He is also able to see phytoliths on the ground, the skeletons that plants leave when they rot, the molds that the passage of time creates on the ground; he is able to see them, even if they are only a few millimeters. Not only does he see on the ground, he also sees on old maps. Discover in the lines of paths, walls, crops or hills where there could have been some type of human settlement, some construction, town, city, road or temple. They are the new tools of computational archaeology, well-trained algorithms that are able to see from satellites, drones or aircraft, but are also able to scan old digitized maps. They analyze the territory and point out: “There”.
This divine eye that is the archaeological algorithm has made it possible to discover about 6,000 potential places of interest in the Indus River valley, between Pakistan and India.
Both this discovery and the design and feeding of the algorithm are part of the doctoral thesis of Iban Berganzo, a telecommunications engineer with a doctorate in Computational Archeology and researcher at the Catalan Institute of Classical Archeology (ICAC), linked to the University Rovira and Virgili of Tarragona. It was directed by Héctor Orengo (ICAC) and Felipe Lumbreras, from the UAB Computer Vision Center.
“These are the lines of work today, those that combine specialisms”, explains Berganzo to La Vanguardia. “It is not unreasonable to think that we can have a worldwide archaeological cartography. And our teams are at the forefront of computational archeology in the world.”
The thesis describes how in a large area of ??475,000 km², along the Indus valley, he has been able to point out 6,000 possible archaeological properties. It is an unprecedented fact in terms of the reconstruction of the ancient landscape. Berganzo plans to extend the research to all of India.
This specialist has worked in that territory due to the links between Orengo, his tutor, and Cambridge. The Cambridge University Library and the British Library preserve the very detailed maps from the colonial era that have allowed digital tools to be trained thanks to the prior and subsequent comparison of verified archaeological information.
“We train the artificial intelligence by fixing in the algorithm the data of deposits of which you are certain: location, shapes… a hill, a pottery. You have to keep validating what you learn, until a moment comes when you detect in real time what each thing is”, says the engineer. “Until you get the positive detection to be statistically significant.” One of the technologies is the Lidar (, which allows scanning reliefs from the air.
One of the most valuable features is that these systems can enable effective real-time site monitoring tools to prevent looting and other threats. Excavations now begin from the air. With zenithal and wide-ranging visions with which you can discover remains in thousands of km² without having to step on the ground or sweat looking for three stones in a row that suggest an ancient wall. For Berganzo, however, this is a complement to the work on the ground: “We must never underestimate the work in the field. We free the archaeologist from routine operations so that he can focus on the analysis of the sites”.
