Slow Big Data: exploring the nexus between urban mobility and heritage through GeoAI

Starting from analyzing the new mobility paradigm (Sheller & Urry, 2006), the proposed work explores the use of spatial Big Data related to urban mobility and their connection with cultural and landscape heritage at the local scale. The focus is investigating the nexus between slow mobility and heritage in Pisa. In this sense, the work employs GeoAI and Big Data analysis techniques to examine and forecast spatial patterns of slow mobility at the (intra) urban scale. First, through the analysis of 151,000 GPS tracks of walking and running trips recorded by Strava platform users over a period of one year (province of Pisa), the work highlights the popular locations for slow mobility and predicts the areas where people tend to linger. Secondly, we deeply study the case study of the municipality of Pisa where 16,000 walking trips have been recorded in 2022. This case study enables us to critically discuss a) the influence of heritage on such spatial trends, b) the role of data as an input in GeoAI models. Furthermore, the analysis of these patterns is helpful in terms of policies: the identification of the most used corridors and the possibility of proposing alternative solutions for wider access to the urban heritage, which also includes "minor" sites; the development of GeoAI models to know and plan walking and running routes in real-time and encourage slow mobility practices and the fruition of cultural and landscape heritage.