Integrative analysis of traffic and situational context data to support urban mobility planning

Abstract

European cities are placing a larger emphasis on urban data consolidation and analysis for optimizing public transportation in response to urban mobility dynamics. In spite of the existing efforts, traffic data analysis often disregards vital situational context, such as social distancing norms, public events, weather, traffic generation poles, or traffic interdictions. Some of these sources of situational context data are still private, dispersed or unavailable for the purpose of planning or managing urban mobility. The Lisbon City Council has already started efforts for gathering of historic and prospective sources of situational context in semi-structured repositories, triggering new opportunities for context-aware traffic data analysis. In this context, this paper adds value to the current theory and practice with three major contributions. First, we propose a methodology to integrate situational context around urban mobility in descriptive and predictive analysis of traffic data, with a focus on the following major spatiotemporal traffic data structures: i) geo-referenced time series data; ii) origin-destination tensor data; iii) raw event data. Second, we introduce additional principles for the online consolidation and labeling of heterogeneous sources of situational context. Third, we offer compelling empirical evidence of the impact produced by situational context aspects on urban mobility, with particular incidence on public passenger transport data gathered from card validations along the bus (CARRIS), subway (METRO) and bike sharing (GIRA) modes in Lisbon. The research reported in this paper is anchored in the ongoing contributions made available in the pioneer research and innovation ILU project, a project that joins the Lisbon city Council and two research institutes with the aim of applying current advances in the field of artificial intelligence to move towards context-aware and sustainable passengers’ mobility.