Estimation of Archaeological Potential with a Page Rank Based Predictive Model: the Urban Area of Pisa

We present an analysis of multi-faceted, GIS managed data for determining the archaeological potential of the urban area of Pisa (www.mappaproject.org). The identification of relations among finds is a key issue for the data mining in the archaeological interpretation process: spatial and functional organization levels allow only particular configurations of parameters defining the potential. A PageRank based model is applied, since the criteria for assigning importance to web pages by search engines are also based on relations. The procedure includes the categorization of finds; the assignment of initial absolute values of potential to the available data, through an automatic procedure; the definition of functional areas (urban, suburban, rural); and the application of a PageRank based algorithm. The results, including the map of archaeological potential, are to be considered as the first steps towards an automatic, formally definable, and repeatable, approach to the computation of archaeological potential.