Evaluating the efficacy of regression and machine learning models to predict prehistoric land-use patterns

Update item information
Publication Type Poster
Research Institute University of Utah Archaeological Center
Creator Yaworsky, Peter
Other Author Vernon, Kenneth Blake; Spangler, Jerry D.; Brewer, Simon C.; Codding, Brian F.
Title Evaluating the efficacy of regression and machine learning models to predict prehistoric land-use patterns
Date 2019
Description Predictive modeling in archaeology is critical to making informed land management decisions and answering key anthropological research questions. However, archaeological predictive modeling su#30;ers from several theoretical, empirical, and analytical problems. To address these shortcomings, we build on theory from behavioral ecology and statistical innovations from ecology. Here we apply four modeling approaches and evaluate their performance using a threshold-independent measure. Two are regression- based: generalized linear (GLM) and generalized additive (GAM) models. Two are machine-learning based: maximum entropy (MaxEnt) and random forests (RF). The results of this analysis establish a foundation for future applications of predictive models in archaeology.
Type Image/StillImage
Publisher University of Utah
Subject Grand Staircase-Escalante National Monument; Archaeology; Predictive Modeling; Machine Learning
Language eng
Format Medium application/pdf
ARK ark:/87278/s6d552cm
Setname ir_su
Date Created 2019-04-17
Date Modified 2019-05-01
ID 1422682
Reference URL https://collections.lib.utah.edu/ark:/87278/s6d552cm
Back to Search Results