Cited by 104Archaeological Research and ProtectionSpecies Distribution and Climate ChangeArchaeology and Cultural Heritage

Advancing predictive modeling in archaeology: an evaluation of regression and machine learning methods on the grand staircase-escalante national monument

Open access
Yaworsky, Peter M., Vernon, Kenneth B., Spangler, Jerry D., Brewer, Simon C., Codding, Brian F.·2020·PLOS One

Abstract

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.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0239424

Cites

87 of 87 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 11

  1. PB Mink, 2006, GIS and archaeological site location modeling, 219
  2. JD Spangler, 2018, Hisatsinom of the High Plateaus: A Class I Overview of Prehistoric Cultural Resources in Grand Staircase-Escalante National Monument
  3. AM Berg, 2003, Prehistoric Occupation of the Confluence Valley between the Vermillion Cliffs and Short Creek: Archaeological Investigations of 16 Sites for the Hildale Wastewater Treatment Facility, Hildale, Utah, and Colorado City, Arizona
  4. AA Nielson, 1998, Excavation/Mitigation Report, Three Sites near Hildale, Utah: 42Ws2195, 42Ws2196, AZ B:1:35 (BLM) Reservoir Site)
  5. H Roberts, 2018, The Jackson Flat Archaeological Project
  6. DT Yoder, 2005, Storage and mobility among the Fremont: changing forms through time
  7. Schaub M. Slab-lined Pit Features of Big Flat in Grand Staircase-Escalante National Monument. Dissertation, Brigham Young University, 2003.
  8. RK Talbot, 2006, Learning from the Land, 317
  9. J O’Donoughue, 2007, Paleoindian Settlement in the Southeastern United States: Insights from Examining Regional Databases, N Am, 4
  10. GH Orians, 1979, On the theory of central place foraging, Anal Ecol Syst Ohio State Univ Press Columb, 155
  11. Hastie TJ, Tibshirani RJ. Generalized additive models. CRC Press, https://books.google.com/books?hl=en&lr=&id=qa29r1Ze1coC&oi=fnd&pg=PR13&dq=Generalized+additive+models.+Chapman+and+Hall/CRC,+Boca+Raton,+Fla.&ots=j32Ohsz_qL&sig=zPBnJCzrsYWZ7Stfa5pZ8Job0qU (1990, accessed 15 August 2016).

Cited by

Sorted by citations

Authors
Yaworsky, P. M., Vernon, K. B., Spangler, J. D., Brewer, S. C., & Codding, B. F.
Venue
PLOS One
Published
2020-10-01
Volume
15
Issue
10
Pages
e0239424
ISSN
1932-6203 (ISSN-L)
OpenAlex
W3090779497
Cited by
104
References
87
Citations by year
2026: 22 · 2025: 26 · 2024: 19 · 2023: 16 · 2022: 15 · 2021: 4 · 2019: 1 · 2018: 1
FWCI
12.87
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • University of Utah
  • U.S. Bureau of Land Management
Topics
  • Physical Sciences › Earth and Planetary Sciences › Space and Planetary Science › Archaeological Research and Protection
  • Physical Sciences › Environmental Science › Ecological Modeling › Species Distribution and Climate Change
  • Social Sciences › Cultural Studies › Archaeology and Cultural Heritage
Keywords
archaeological site prediction, predictive modeling, Grand Staircase-Escalante National Monument, Formative period, maximum entropy, random forest, generalized additive models, generalized linear models, model evaluation, area under the curve, true skill statistic, cultural resource management, land use
MeSH terms
Machine Learning, Archaeology, Regression Analysis, Models, Statistical, Area Under Curve

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review