Traditional and digital typologies compared: the example of Italian protohistory

The study of material culture, particularly ceramics, is an important aspect of archaeol-ogy. The classification and typology of ceramics is often a key focus, with traditional methods basedon the observation of specific morphological characteristics and the creation of taxonomies basedon these types. However, recent advances in digital technologies and the use of Machine Learninghave led to the development of new, digital approaches to ceramic classification. These approachesrely on statistical methods and computer science techniques to quantify vessel morphology and cre-ate multivariate datasets. The aim of this study is to compare a traditional approach elaborated byRenato Peroni and applied by many of his students, especially in the field of Italian protohistory,with a proposed digital method of ceramic classification. The comparison will be conducted using adatabase of approximately 1400 records from several Italian Bronze and Iron Age funerary contexts,including Casinalbo and other contexts in the Po Valley and northern Italy, as well as Pianellodi Genga and Torre Galli. The proposed digital approach involves a combination of a non-lineardimensionality reduction algorithm and density-based clustering for the automated classification ofceramics. The study will consider the similarities and differences between the two methods and thepotential for combining them in a complementary manner. The results of the study will providea deeper understanding of traditional typologies and explore the potential for digital methods toenhance, improve, and complement them.