Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions

Part of: Society for American Archaeology 90th Annual Meeting, Denver, CO (2025)

This collection contains the abstracts of the papers presented in the session entitled "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" at the 90th annual meeting of the Society for American Archaeology.

Archaeologists have long used quantitative statistical analyses to understand past human-environmental interactions on a wide range of topics, including past foodways, landscape use, and social organization. Zooarchaeology and environmental archaeology, in particular, are well positioned to tackle these issues as analyses of faunal remains, climatic variability, and landscape dynamics, among other things, provides critical insights into past peoples and societies. Moreover, many of these analysts have begun using cutting-edge machine-learning statistical techniques to answer research questions on these same topics. The goal of this session is to highlight the applicability and analytical power of machine learning statistical approaches to answering questions about long term human-environmental interactions. These new tools have the power to significantly contribute to and help answer a diverse array of theoretically informed research questions.

Other Keywords
Zooarchaeology • Quantitative and Spatial Analysis • Worldwide

Resources Inside This Collection (Viewing 1-8 of 8)

  • Documents (8)
Documents
  • Dogs in Space: An Application of Machine-Learning Geometric Morphometric Analyses for Species Determination of Large Canids Using Mandibles (2025)
    DOCUMENT Citation Only Abigail Fisher.

    This is an abstract from the "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" session, at the 90th annual meeting of the Society for American Archaeology. A persistent issue in zooarchaeology is the differentiation of domesticated dogs from wolves and coyotes from fragmentary archaeological remains. This is particularly problematic in regions where size cannot be used as a factor, such as the North American northern Great Plains. This poster presents the use...

  • Impacts of settler-colonial Invasion on ecosystem structure and animal occurrence in the Bear River Basin (2025)
    DOCUMENT Citation Only Kasey Cole.

    This is an abstract from the "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" session, at the 90th annual meeting of the Society for American Archaeology. Exogenous factors, such as climate, and endogenous dynamics, such as human resource and landscape modification influence ecological conditions. Over long temporal scales, these dynamics create socio-environmental systems (SES) that influence the distribution of plant and animal species across the...

  • Mapping Zoological Baselines Through Time in the Bear River Range: When Archaeology Meets Wildlife Science (2025)
    DOCUMENT Citation Only Auriana Dunn.

    This is an abstract from the "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" session, at the 90th annual meeting of the Society for American Archaeology. Zoological baselines are key data sets when evaluating climate issues and wildlife conservation projects. This project looks at three types of ecological surveys in the Bear River Basin. 1) A zooarchaeological survey of two cave assemblages, 2) modern camera trap data, and 3) modern museum live trapping...

  • Modeling the Landscape Ranging Ecology of Clovis Groups: A Spatial Analysis of Lithic Raw Material Transport in the Great Lakes Region (2025)
    DOCUMENT Citation Only Chase Peterson.

    This is an abstract from the "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" session, at the 90th annual meeting of the Society for American Archaeology. Fluted-point technology, like Clovis, is associated with some of the earliest modern-human dispersals across the Americas. Forager groups utilizing this technology emerged and proliferated in North America approximately 13,000 years ago. Archaeologists generally agree that Clovis groups dispersed their...

  • Past Movement and New Models: Reconstructing Past Mobility in the Absaroka Mountains by Applying Bayesian Neural Networks Towards Refining Trace Element Modeling (2025)
    DOCUMENT Citation Only Daniel Dalmas.

    This is an abstract from the "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" session, at the 90th annual meeting of the Society for American Archaeology. Sourcing lithic raw materials in North America has become increasingly valuable for understanding past human behavior. However, the process often faces challenges due to monetary costs and the need to remove materials from their original landscape. Refining pXRF obsidian sourcing methods can help mitigate...

  • Paw-sitive Identification: Machine Learning with Biometrics Improves Canid Detection (2025)
    DOCUMENT Citation Only Martin Welker.

    This is an abstract from the "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" session, at the 90th annual meeting of the Society for American Archaeology. Zooarchaeological canid identifications are made using an array of techniques, many of which were only ever designed to separate dogs from wolves and have never been tested against large samples. Skeletal measurements (termed biometrics) coupled with statistical analyses can improve identification...

  • Using Past Ecosystems to Understand Modern Climate Change: A Case Study from Utah’s House Mountain Range (2025)
    DOCUMENT Citation Only Jane Damstedt.

    This is an abstract from the "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" session, at the 90th annual meeting of the Society for American Archaeology. As human impacts on ecosystems accelerate, there is a growing emphasis in conservation planning towards maximizing the capacity of ecosystems to respond to anticipated changes in the near future. Doing so requires understanding how ecosystems responded to past changes (e.g., human impacts, altered...

  • Using Wyoming Ground Squirrel Burrows to Investigate if Surface Artifact Density Accurately Represents Subsurface Artifact Density. (2025)
    DOCUMENT Citation Only Ethan Reid.

    This is an abstract from the "Machine-Learning Approaches to Studying Ancient Human-Environmental Interactions" session, at the 90th annual meeting of the Society for American Archaeology. Subsurface artifact density is an important part of the archeological record for a site but is more difficult data to obtain than artifact density found on the surface. This is because examining subsurface artifact records requires excavation, auguring, and/or the use of ground-penetrating radar. These...