Creating Machine Learning Models Using Historical Maps to Identify the Places In-Between

Summary

This is an abstract from the "*SE The State of Theory in Southeastern Archaeology" session, at the 89th annual meeting of the Society for American Archaeology.

Historical archaeology lies at the intersection of the written word, the spoken word, and material things. We extend and enhance that purview by incorporating machine learning algorithms to create more dynamic assessments of places documented on historical maps, thus engaging more deeply with sociocultural and environmental perspectives embedded in a multiscalar historical past. By creating hybridized data sources to create more dynamic collections of information, we are able to take advantage of inherent “unknowns” in traditionally utilized data sources to identify probable locations of past human activity. Embedding the in-between spaces in our model of historic coastal plantation spaces allows us to more fully engage with theory building of liminal, disenfranchised spaces and places using a broader synthesis of the processual culture history building inherent in southeastern archaeology while also engaging with the so-called “ontological turn.” Ultimately, we propose that by identifying the locations of places ignored or unknown by archaeologists, as well as highlighting the areas within which many community-building activities took place, we can create a system to identify and protect important cultural heritage resources that are at risk due to the climate emergency.

This Resource is Part of the Following Collections

• Society for American Archaeology 89th Annual Meeting, New Orleans, LA (2024)   •
• *SE The State of Theory in Southeastern Archaeology

Keywords

Spatial Coverage

Record Identifiers

Abstract Id(s): 39019.0