A UWindsor computer scientist is using artificial intelligence to help archaeologists explain the disappearance of a large group of native North Americans more than 700 years ago.
Computer science professor Ziad Kobti is part of a four-member team that received almost $1.5 million from the U.S. National Science Foundation to determine the fate of Pueblo Indians, known as the Anasazi.
Dr. Kobti’s share of funding for the Village Ecodynamics Project, led by researchers at Washington State University, is about $186,000. He is the project’s primary programmer and uses a computer simulation technique called agent-based modelling to predict where prehistoric people might have situated their homes based on their natural and social environments.
Native populations grew rapidly between AD 600 and 1200 in the Mesa Verde and Rio Grande regions of the U.S. southwest, though the area was depopulated by AD 1280. Archaeologists theorize that conditions such as drought, disease, the emergence of new social influences, and raiding groups that created competition for resources, may have been responsible.
Using archaeological data, Kobti can create a model of the 1,500-square-kilometre area as it may have existed in AD 600. Each household, called an agent, represents an average of six family members. Agents function as a unit and interact with one another, while the programmer can introduce influences, such as drought or new animals to hunt.
“The agent has autonomy,” Kobti says. “It can think for itself without being told what to do. It can hunt, plant crops, trade food and goods with other agents and make decisions about where to live. It follows a strategy for survival and you can test these strategies.”
By mimicking such processes as population growth and resource usage, the computer tracks migration of agents and can predict where the Anasazi population may have moved. These predictions can be compared with existing archaeological data to help researchers try to solve the mystery of the Anasazi.