UNEDITED REFERENCE

This record is being processed for inclusion into GeoRef. It may not yet have been indexed, given a translated title, or checked by a GeoRef editor.

Advancing predictive modeling in archaeology; an evaluation of regression and machine learning methods on the Grand Staircase-Escalante National Monument

Saved in:
Online Access: Get full text
doi: 10.1371/journal.pone.0239424
Authors:Yaworsky, Peter M.; Vernon, Kenneth B.; Spangler, Jerry D.; Brewer, Simon C.; Codding, Brian F.
Author Affiliations:Primary:
University of Utah, Department of Anthropology, Salt Lake City, UT, United States
Other:
Colorado Plateau Archaeological Alliance, United States
Volume Title:PLoS One
Source:PLoS One, 2020(e0239424). Publisher: Public Library of Science, San Francisco, CA, United States. ISSN: 1932-6203
Publication Date:2020
Note:In English. 95 refs.; illus., incl. 3 tables, sketch maps
Summary:Predictive models are central to both archaeological research and cultural resource management. Yet, archaeological applications of predictive models are often insufficient due to small training data sets, inadequate statistical techniques, and a lack of theoretical insight to explain the responses of past land use to predictor variables. Here we address these critiques and evaluate the predictive power of four statistical approaches widely used in ecological modeling-generalized linear models, generalized additive models, maximum entropy, and random forests-to predict the locations of Formative Period (2100-650 BP) archaeological sites in the Grand Staircase-Escalante National Monument. We assess each modeling approach using a threshold-independent measure, the area under the curve (AUC), and threshold-dependent measures, like the true skill statistic. We find that the majority of the modeling approaches struggle with archaeological datasets due to the frequent lack of true-absence locations, which violates model assumptions of generalized linear models, generalized additive models, and random forests, as well as measures of their predictive power (AUC). Maximum entropy is the only method tested here which is capable of utilizing pseudo-absence points (inferred absence data based on known presence data) and controlling for a non-representative sampling of the landscape, thus making maximum entropy the best modeling approach for common archaeological data when the goal is prediction. Regression-based approaches may be more applicable when prediction is not the goal, given their grounding in well-established statistical theory. Random forests, while the most powerful, is not applicable to archaeological data except in the rare case where true-absence data exist. Our results have significant implications for the application of predictive models by archaeologists for research and conservation purposes and highlight the importance of understanding model assumptions.
Subjects:Archaeological sites; Archaeology; Cenozoic; Holocene; Land management; Machine learning; Maximum entropy analysis; Numerical models; Prediction; Principal components analysis; Quaternary; Regression analysis; Statistical analysis; Upper Holocene; Garfield County Utah; Grand Staircase-Escalante National Monument; Kane County Utah; United States; Utah; Random forest analysis
Coordinates:N370000 N380000 W1105800 W1122500
Record ID:890359-1
Copyright Information:GeoRef, Copyright 2021 American Geosciences Institute.
Tags: Add Tag
No Tags, Be the first to tag this record!