Changing Communities of Ancient Builders: Machine Learning-based Analysis of Mortars from Caesarea Maritima (Israel)

FAIN: HAA-284842-22

Vanderbilt University (Nashville, TN 37203-2416)
Markus Eberl (Project Director: June 2021 to present)

The creation of machine learning methods to identify microartifacts from archaeological sites. 

Mortars are ubiquitous and essential parts of construction. Ancient builders prepared them as members of changing communities of practice. We ask to what degree interactions among contemporaries led to standardized mortars and whether builders learnt from culturally different predecessors. These issues require studying a large data set objectively. Our Level 1 project proposes to analyze 1000 mortar samples and ~1 billion particles with a dynamic image particle analyzer. We train machine learning algorithms to identify experimentally reproduced mortar constituents in archaeological samples. The latter come from the ancient port city of Caesarea Maritima that Roman, Jewish, Byzantine, Abassid-Fatimid Muslim, and Crusader builders constructed between 22 B.C.E. and 1265 C.E. Our approach – dynamic image analysis, experimental archaeology, and machine learning – can be extended to other parts of the ancient Mediterranean as well as to other microartifacts.

Media Coverage

Deep Learning in Archaeology: Understanding the Composition of Ancient Mortars (Media Coverage)
Author(s): Charreau Bell
Publication: Vanderbilt University: Data Science Institute
Date: 10/22/2022
Abstract: Mortar is an essential part of construction, and has been used by builders for centuries. Ancient builders prepared them as members of changing communities of practice. But, to what degree did interactions among contemporaries lead to standardized mortars? Did builders learn from culturally different predecessors? In partnership with the Vanderbilt Data Science Institute, Dr. Markus Eberl, archaeologist and Vanderbilt University Associate Professor of Anthropology, aims to find the answers to these questions.
URL: https://www.vanderbilt.edu/datascience/2022/10/27/deep-learning-in-archaeology-understanding-the-composition-of-ancient-mortars/

Archaeologists and Data Scientists Team Up to Unearth Ancient Building Practices (Media Coverage)
Author(s): Katie Elyce Jones
Publication: PillarQ
Date: 2/21/2023
Abstract: In 2021, archaeologist Markus Eberl of Vanderbilt University visited the Mediterranean port city of Caesarea, Israel, to collect ancient specks of sand and concrete mixes known as mortar. While they may sound unassuming, such mortar samples tell a rich history of the city’s builders and their construction practices.
URL: https://www.pillarqnews.com/02/archaeologists-and-data-scientists-team-up-to-unearth-new-insights-on-ancient-building-practices/

AI in Archaeology (Media Coverage)
Author(s): Markus Eberl
Publication: Presentation: Vanderbilt Data Science Institute
Date: 3/28/2023
Abstract: Presentation during the annual symposium, this year on "AI Revolutions"
URL: https://www.vanderbilt.edu/datascience/events/symposium/

Machine learning-based identification of lithic microdebitage (Media Coverage)
Author(s): Eberl, Markus, Zimmerman, Paul, Webster, Chris
Publication: Archaeology Podcast network
Date: 8/17/2023
Abstract: We talk to Dr. Markus Eberl about his team’s use of a particle scanner to analyze micro-debitage. They used machine learning to analyze the data set and tried to learn more about early life than we could otherwise. [I discuss my recent work on ancient mortars as well]
URL: https://www.archaeologypodcastnetwork.com/archaeotech/207