Decomposing Habitat Suitability With Theory-Driven Machine-Learning

Author(s): Kenneth Vernon; Peter Yaworsky; Brian Codding

Year: 2019


This is an abstract from the "Fifty Years of Fretwell and Lucas: Archaeological Applications of Ideal Distribution Models" session, at the 84th annual meeting of the Society for American Archaeology.

Archaeological applications of ideal distribution models have advanced beyond the study of straightforward settlement decisions to address a variety of important but difficult anthropological questions. To aid in these investigations, we demonstrate a method for (i) decomposing habitat suitability into its ecological components and (ii) showing how their relative contributions to settlement change through time. This method relies on the maximum entropy approach to species distribution modeling from ecology coupled with the prey-choice model from behavioral ecology. We use the extensive record of subsistence and settlement provided by the distribution of archaeological sites within the Grand Staircase-Escalante National Monument to test predictions.

Cite this Record

Decomposing Habitat Suitability With Theory-Driven Machine-Learning. Kenneth Vernon, Peter Yaworsky, Brian Codding. Presented at The 84th Annual Meeting of the Society for American Archaeology, Albuquerque, NM. 2019 ( tDAR id: 452093)

Spatial Coverage

min long: -123.97; min lat: 37.996 ; max long: -101.997; max lat: 46.134 ;

Record Identifiers

Abstract Id(s): 25531