Applications of artificial intelligence has permeated in almost every scientific field, including archaeology.
Most of us have grown up watching archaeology themed movies like ‘The Mummy’ series or ‘Indiana Jones’. While today’s digital technologies like artificial intelligence cannot crack a whip like Harrison Ford in Indiana Jones, it is surely bringing a huge momentum in the technological aspect of this science.
For instance, deep learning is already catering to problems in computer vision and with practical applications in several fields. Today, it is also helping in analysis of airborne data to detect archaeological traces.
ArchAI, a startup company is de-risking the construction industry by using artificial intelligence to automatically detect archaeology on earth observation data. Founded by Iris Kramer, an archaeologist-turned-computer scientist, ArchAI aims to lower the cost of construction and ensure that vital historical sites are preserved. It achieves this by employing deep learning to discover where archaeology is located during the earliest planning stages. This allows accurate estimates of time and cost involved with acquiring planning permission and significantly reduce the risk of discovering unexpected archaeology during construction.
Archaeologists, Gabriele Gattiglia and Francesca Anichini, from the University of Pisa in Italy, have developed ArchAIDE project, a digital tool that allows archaeologists to photograph a piece of pottery in the field and have it identified by convolutional neural networks.
Even by leveraging computer vision algorithms, archaeologists are analyzing satellite imagery and data from drones, planes. It also helps in automating the process of detecting possible archeological sites in them. Last year, a team of researchers from Binghamton University had developed an automated algorithm for identifying large earthen and shell mounds built by native populations of Southeast America.
As per the published research paper, many extant, yet unidentified, archaeological mound features continue to evade detection due to the heavily forested canopies that occupy large areas of the region, making pedestrian surveys difficult and preventing aerial observation. This challenge inspired the team to use object-based image analysis (OBIA) for analyzing light and radar and LiDAR (a 3D laser scanning technology) data. Using publicly available lidar data from Beaufort County, South Carolina, and an OBIA approach incorporating morphometric classification and statistical template matching, the team could systematically identify over 160 previously undetected mound features.
Apart from finding ruins during the excavation process, artificial intelligence is also used by linguistic anthropologists to trace the evolution of different languages. For instance, Google’s DeepMind used a deep neural network called PYTHIA to recreate missing inscriptions in ancient Greek from damaged surfaces of objects made of stone or ceramics.
Last year, two Israeli universities, Ariel University, the Israeli Heritage Department and Bar Ilan University, employed artificial intelligence to restore broken-up words penned in the Akkadian language. Akkadian is deemed as an extinct language spoken in the ancient Mesopotamian empires of Babylon and Assyria some 2,500 years before the birth of Christ, up until about 600 BC. It is the oldest known Semitic language and predates Aramaic, Hebrew, and Arabic. The researcher team from these two universities digitized the clay tablets inscribed in cuneiform (a writing system made of wedge-shaped impressions), using a tool dubbed as Babylonian Engine. Then the digitized texts were analyzed and studied by machine learning algorithms to uncover the secrets of the ancient Persian empire – sixth to fourth centuries BC. This method helped in restoring damaged texts by figuring out the appropriate words to use in the missing sections.
Artificial intelligence technologies also help archeologists and paleontologists uncover and study the behavior of early human beings. A study team from Centro Nacional de Investigación Sobre la Evolución Humana (CENIEH), used artificial intelligence at the Navalmaíllo Rock Shelter site in Madrid, which shows the activity by Neanderthal groups of breaking the bones of medium-sized animals for subsequent consumption of the marrow. The Navalmaíllo Rock Shelter, which is about 76,000 years old, offers one of the few large windows into Neanderthal behavior within the Iberian Meseta.
AI also proves a vital tool in mapping old civilizations. Machine learning algorithms enabled researchers at the Institut Català d’Arqueologia Clàssica (ICAC) to reconstruct more than 20,000 kilometers of paleo-rivers along the Indus Valley civilization.
Also, though in traditional research settings, information retrieved from many archaeological sites may not be sufficient to arrive at a substantive conclusion. Hence, researchers are leveraging machine learning to determine the accuracy and relevancy, of their archaeological findings. E.g. a team of Mexican archaeologists and the University of Marburg are leveraging machine learning models to identify whether the source material required for making Obsidian artifacts, discovered in Xalasco came from local sources or were obtained from other remote areas.
While, artificial intelligence helps in extracting archaic information about past ruins and human civilization, it is not a blanket solution! Nor will it replace humans as it lacks the subjective expertise of a human archeologist. So, it is obvious that while it helps in addressing numerous challenges faced by human experts, it is far from becoming Indiana Jones yet!