COVID-19 outbreak response, a dataset to assess mobility changes in Italy following national lockdown

Abstract

Italy has been severely affected by the COVID-19 pandemic, reporting the highest death toll in Europe as of April 2020. Following the identification of the first infections, on February 21, 2020, national authorities have put in place an increasing number of restrictions aimed at containing the outbreak and delaying the epidemic peak. On March 12, the government imposed a national lockdown. To aid the evaluation of the impact of interventions, we present daily time-series of three different aggregated mobility metrics: the origin-destination movements between Italian provinces, the radius of gyration, and the average degree of a spatial proximity network. All metrics were computed by processing a large-scale dataset of anonymously shared positions of about 170,000 de-identified smartphone users before and during the outbreak, at the sub-national scale. This dataset can help to monitor the impact of the lockdown on the epidemic trajectory and inform future public health decision making.

Fig. 1

Timeline of data collection and major events in the early phase of the COVID-19 outbreak in Italy.

Fig. 2

Workflow of the data processing pipeline (a). Spatial distribution of the user panel by province (b).

Fig. 3

Weekly number of active users in the panel under study. Date on the x-axis refers to the first Sunday of a week.

Fig. 4

Workflow to build the users’ proximity network. Users’ trajectories are generated (a). A circle of fixed radius is drawn around each user’s stop (b). The proximity network is defined by the intersecting circles of different users (c).

Fig. 5

Scatterplot of the number of users assigned to each Italian province against the resident population reported by the Italian census in each province, as a fraction of the totals. Color code correspond to the three main geographic areas of Italy: North, Center, South.