Quantifying ancient architecture: Stone-level machine learning reveals architectural variation and settlement growth at Shivta
7 affiliations
- 1Department of Archaeology, School of Archaeology and Maritime Cultures, University of Haifa, Haifa 3498838, Israel
- 2The Leon Recanati Institute for Maritime Studies, University of Haifa, Haifa 3498838, Israel
- 3Negaunee Integrative Research Center, Field Museum of Natural History, Chicago, IL 60605
- 4Department of Anthropology, University of Illinois-Chicago, Chicago, IL 60607
- 5Department of Anthropology, Northwestern University, Evanston, IL 60208
- 6The Institute for the Study of Ancient Cultures, West Asia and North Africa, University of Chicago, Chicago, IL 60637
- 7The Zinman Institute of Archaeology, University of Haifa, Haifa 3498838, Israel
Abstract
Built environments provide durable evidence for how ancient settlements were organized, expanded, and transformed over time. Yet quantitative approaches to documenting architectural variability are generally labor-intensive, limited to individual structures, or dependent on aggregate volumetric estimates. We present a scalable, machine-learning-based framework that shifts the unit of analysis to the individual building stone and combines two complementary datasets: low-altitude drone imagery of surface remains and close-range photographs of standing walls. Applied to the Late Antique settlement of Shivta in the Negev Desert, the method automatically digitized approximately 235,000 surface stones and 12,000 stones in 604 walls, quantifying stone size, shape regularity, and masonry arrangement across walls, households, insulae, and the settlement as a whole. Higher masonry scores cluster around churches and parts of the settlement boundary, while the spatial distribution of masonry variation reveals a previously unidentified earlier boundary and provides evidence for outward expansion from a southern core. Combined with architectural sequencing, these patterns indicate the use of larger and more regularly shaped stones during Shivta’s principal phase of growth. The framework combines analytical flexibility with demonstrated robustness, supporting broader application across diverse stone-built archaeological contexts while complementing architectural energetics and enabling settlement-wide and cross-site comparisons of construction practices and settlement change.
Related
- Tracing settlement dynamics in Latium vetus: Explainable machine learning perspectives from the Bronze to the Early iron age
- Quantifying nonlinear thresholds of grey-green space morphology on urban carbon metabolism across local climate zones: a machine learning study in Changchun city
- Quantifying meteorological impacts on local landfill methane emissions by using field measurements and machine learning
- Multi-data source based quantifying urban flood severity in major Chinese cities (2000–2024) using a hybrid machine-learning weighting framework
- Co-production as a mechanism for long-term Nature-based Solution viability: evidence from urban biofilters in an informal settlement of the Global South
BibTeX
@article{uziel2026quantifying,
title = {{Quantifying ancient architecture: Stone-level machine learning reveals architectural variation and settlement growth at Shivta}},
author = {Erel Uziel and Gideon Avni and Gary M. Feinman and Guy Bar-Oz and Yitzchak Y. Jaffe},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
year = {2026},
month = oct,
doi = {10.1073/pnas.2628851123},
url = {https://doi.org/10.1073/pnas.2628851123},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Quantifying ancient architecture: Stone-level machine learning reveals architectural variation and settlement growth at Shivta
AU - Erel Uziel
AU - Gideon Avni
AU - Gary M. Feinman
AU - Guy Bar-Oz
AU - Yitzchak Y. Jaffe
PY - 2026
DA - 2026/10/28
JO - Proceedings of the National Academy of Sciences of the United States of America
DO - 10.1073/pnas.2628851123
UR - https://doi.org/10.1073/pnas.2628851123
AB - Built environments provide durable evidence for how ancient settlements were organized, expanded, and transformed over time. Yet quantitative approaches to documenting architectural variability are generally labor-intensive, limited to individual structures, or dependent on aggregate volumetric estimates. We present a scalable, machine-learning-based framework that shifts the unit of analysis to the individual building stone and combines two complementary datasets: low-altitude drone imagery of surface remains and close-range photographs of standing walls. Applied to the Late Antique settlement of Shivta in the Negev Desert, the method automatically digitized approximately 235,000 surface stones and 12,000 stones in 604 walls, quantifying stone size, shape regularity, and masonry arrangement across walls, households, insulae, and the settlement as a whole. Higher masonry scores cluster around churches and parts of the settlement boundary, while the spatial distribution of masonry variation reveals a previously unidentified earlier boundary and provides evidence for outward expansion from a southern core. Combined with architectural sequencing, these patterns indicate the use of larger and more regularly shaped stones during Shivta’s principal phase of growth. The framework combines analytical flexibility with demonstrated robustness, supporting broader application across diverse stone-built archaeological contexts while complementing architectural energetics and enabling settlement-wide and cross-site comparisons of construction practices and settlement change.
SN - 0027-8424
SN - 1091-6490
ER -