Pattern Recognition: The Exploration of Machine Learning Algorithms in Archaeological Site Prediction, Fraser River Valley, British Columbia

Golder Associates Ltd., teaming with the Seyem’ Qwantlen Business Group (Kwantlen First Nation), was retained by the Township of Langley to develop a model to predict the location of unrecorded archaeological sites on a 10,000 year-old landscape located in the Fraser River Valley, British Columbia. Conventional predictive modelling techniques are common practice however with the increased availability of more powerful computers and software there is a growing potential for using machine learning algorithms to predict a wider variety of archaeological site types with greater accuracy. For this Pattern Recognition Project (PRP) the intern will complete a machine learning literature review and an examination of the local archaeology to identify potential machine learning methodologies and algorithms to predict site locations as well as the best environmental, physiographic and cultural variables to input into the model. This research will be used to create a report which describes the PRP, its results, and recommendations. The results generated by the PRP will be used to pilot a new approach for archaeological predictive modelling using machine learning algorithms and will ultimately be used to assist the Township in responsibly managing local archaeological sites.

Faculty Supervisor:

Andrew Martindale

Student:

Raini Johnson

Partner:

Golder Associates

Discipline:

Anthropology

Sector:

Construction and infrastructure

University:

University of British Columbia