AI, the new Indiana Jones?

Archaeologists, most exemplified in popular culture by the character of Indiana Jones, are more often seen as people who do a lot of manual field work: exploring hitherto unknown areas of land to find objects or patterns that would give some clues to the ancient past. They are now catching up with the rest of the sciences in utilising the amazing technology of AI.

Uncovering long-abandoned ancient settlements in Madagascar, detecting nearly indiscernible bumps of earthen mounds left behind by prehistoric North American cultures, mapping Bronze Age river systems in the Indus Valley, and many more such activities are seeing the involvement of AI. Such activities called Landscape Archaeology are examples of areas where AI is helping scientists hunt for new archaeological digs as well as understand ancient cultures at large scale and great pace.

So what data is used by AI to help with Landscape Archaeology? The near-ubiquitous availability of satellite data and other kinds of aerial imagery has been a boon to the field. The large troves of complex data are parsed using Machine Learning techniques such as Computer Vision and Natural Language Processing.

For example, Computer Vision is being used to identify large earthen and shell mounds built by native populations in America long before Europeans arrived with far-off visions of skyscrapers and superhighways in their eyes. The sites, still hidden in places like the South Carolina wilderness, contain a wealth of information about how people lived, what they ate, and the ways they interacted with the local environment and other cultures. The imagery comes from LiDAR, which uses light pulses that can penetrate tree canopies to map forest floors. The shape, size, and texture characteristics of the mounds  are the features identified and used to train the algorithm so that the model thus developed can be used to identify potential sites for further exploration. 

Other archaeological approaches also benefit from AI. AI methods, for instance, are being used to understand the chemical makeup of artefacts like pottery and ceramics. This can help identify where these materials were made, how far they were transported and help us to understand the extent of past trading networks. Linguistic anthropologists have also used machine intelligence methods to trace the evolution of different languages. Using AI, we can learn when and where languages emerged around the world.

Here's a research paper on mound-detection using LiDAR.