Articles by Nevio Dubbini

Ceramic, which is one of the most precious sources for the reconstruction of the past, constitutes the main discovery during archaeological excavations. The classification of ceramic sherds based on origin/dating/typology would require a long, and sometimes tedious, work by specialized archaeologists who could better use their time to carry out investigations on the dig site and for this reason these fragments often remain unclassified in the warehouses of universities and superintendencies for very long periods of time. AI and robotics can help automate this process: this project tries to address a possible solution by presenting the development of a robotic arm that carries out the pick-and-place of fragments classified using ArchAIDE, an AI-based ceramic classification application. The contribution of this article is an automated system which, after having recognized the fragments using the ArchAIDE AI, trained on 66 ceramic classes, collects them and places them in appropriate containers based on the assigned class.

Data and the possibility to circulate and spread them are the key infrastructure of archaeology. Part of the (interpretative) information underlying data is connected to the know-how of each single researcher. Data, instead, are firm points. In this paper, we describe how open data can be used for determining the archaeological potential. We used a sizable number of datasets, in order to consider the problem of estimation of archaeological potential in all of its aspects: archaeological, historical, and geomorphological data. As the identification of relations among finds is a key issue in archaeological interpretation process, we applied a modified version of the PageRank algorithm. The procedure included a categorization of archaeological data, the assignment of initial values of potential to the available data, the creation of geomorphological maps, the definition of functional areas (i.e. the levels of spatial and functional organization: urban, suburban and rural areas), and the application of the PageRank based algorithm. The model has been applied on the urban area of Pisa, and tested through the data of 14 new cores. The map of archaeological potential consists of the composition of the 7 layers, one for each archaeological period under consideration. The results, including the archaeological potential map, are to be considered as the first steps towards an automatic, formally definable, and repeatable approach to the computation of archaeological potential.