Stylistic clusters and the Syrian/South Syrian tradition of first-millennium BCE Levantine ivory carving: a machine learning approach

Abstract

Thousands of first-millennium BCE ivory carvings have been excavated from Neo-Assyrian sites in Mesopotamia (primarily Nimrud, Khorsabad, and Arslan Tash) hundreds of miles from their Levantine production contexts. At present, their specific manufacture dates and workshop localities are unknown. Relying on subjective, visual methods, scholars have grappled with their classification and regional attribution for over a century. This study combines visual approaches with machine-learning techniques to offer data-driven perspectives on the classification and attribution of this early Iron Age corpus.The study sample consisted of 162 sculptures of female figures. Among them are examples that have been conventionally attributed to three main regional carving traditions: "Phoenician," "North Syrian," "Syrian/South Syrian/Intermediate". We have developed an algorithm that clusters the ivories based on a combination of descriptive and anthropometric data. The resulting categories, which are based on purely statistical criteria, show good agreement with conventional art historical classifications, while revealing new perspectives, especially with regard to the contested "Syrian/South Syrian/Intermediate" tradition. Specifically, we have identified that objects of the Syrian/South Syrian/Intermediate tradition may be more closely related to Phoenician objects than to North Syrian objects; we offer a reconsideration of a subset of "Phoenician" objects, and we confirm Syrian/South Syrian/Intermediate stylistic subgroups that might distinguish networks of acquisition among the sites of Nimrud, Khorsabad, Arslan Tash and the Levant. We have also identified which features are most significant in our cluster assignments and might thereby be most diagnostic of regional carving traditions. In short, our 2 study both corroborates traditional visual classification methods and demonstrates how machinelearning techniques may be employed to reveal complementary information not accessible through the exclusively visual analysis of an archaeological corpus.

Classifying Iron Age Levantine Ivories: Impracticalities and a New Approach

“…This, together with the above-suggested imitations of Phoenician prototypes, may suggest that South Syrian ivories were either contemporary with or slightly later in time than the latter. The stylistic clusters resulting from Amy Gansell's machine-learning analysis of a sample of female figures suggest that South Syrian ivories are more closely related to Phoenician than North Syrian ivories (Gansell et al 2014). Arianna Cinquatti (in this volume) reaches similar conclusions.…”

Forensic Archaeometry Applied to Antiquities Trafficking: The Beginnings of an Investigation at the Frontiers of Knowledge

“…However, there remains a lack of effective protocols to enable their sufficient characterization and to determine their provenience, if not the exact site, then at least a more or less delimited area. To this end, the main geological and biological parameters that could be used for such characterizations should be defined (Gansell et al 2014;Oonk and Spijker 2015). From a technical perspective, the application of new computer methodologies for indexing, data mining, and smart queries can be used in contexts in which looting and illicit trafficking are carried out, as well as to facilitate the establishment of the area of provenience of an object.…”

Forensic Archaeometry Applied to Antiquities Trafficking: An Investigation at the Frontiers of Knowledge

“…However, there remains a lack of effective protocols to enable their sufficient characterization and to determine their provenience, if not the exact site, then at least a more or less delimited area. To this end, the main geological and biological parameters that could be used for such characterizations should be defined (Gansell et al 2014;Oonk, Spijker 2015). From a technical perspective, the application of new computer methodologies for indexing, data mining, and smart queries can be used in contexts in which looting and illicit trafficking are carried out, as well as to facilitate the establishment of the area of provenience of an object.…”