HAA-284842-22 | Digital Humanities: Digital Humanities Advancement Grants | Vanderbilt University | Changing Communities of Ancient Builders: Machine Learning-based Analysis of Mortars from Caesarea Maritima (Israel) | 1/1/2022 - 12/31/2024 | $49,289.00 | Markus | | Eberl | | | | Vanderbilt University | Nashville | TN | 37203-2416 | USA | 2021 | Archaeology | Digital Humanities Advancement Grants | Digital Humanities | 49289 | 0 | 41515 | 0 | 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. |