Exploring multimodal mobility patterns with big data in the city of Lisbon

Short abstract

The research reported in this paper is anchored in the pioneer research “Integrative Learning from Urban Data and Situational Context for City Mobility Optimization” a project in the field of artificial intelligence applied to urban mobility

Abstract

Worldwide, city municipalities are establishing efforts to collect urban data in order to gain more comprehensive views of the city dynamics and support enhanced mobility decisions. Hence, cities are becoming sensorized and heterogeneous data is being consolidated to allow monitoring of multimodal traffic patterns. Multimodal traffic patterns encompass all modes (road, railway and inlands waterways, as well as active modes such as walking and cycling). Detection of mobility patterns can offer data-centric views ensuring: 1) the city mobility plan is sensitive to changes (self-adaptation); 2) fully transparent decisions to the citizens, enhancing the accountability of authorities; and 3) an objective coordination between the different authorities involved in mobility management. To meet this purpose, big data are currently being consolidated in the Intelligent Management Platform of the City of Lisbon (PGIL). Still, the potentialities of exploring existing heterogenous data through an integrative manner for the purpose of meeting sustainable mobility goals are still untapped.

The research reported in this paper is anchored in the pioneer research and innovation project “Integrative Learning from Urban Data and Situational Context for City Mobility Optimization” (DSAIPA/DS/0111/2018), a project in the field of artificial intelligence applied to urban mobility that joins two research institutes and the City of Lisbon. The manuscript will focus on its first stage, delving into the discovery and analysis of relevant multimodal patterns in passengers’ public transport, offering three major contributions:
• A structured view on the technical opportunities and challenges for multimodal mobility decisions grounded on the available urban data;
• Principles for the discovery of multimodal patterns from heterogeneous sources of urban data;
• The analysis of indicators and multimodal patterns from the available urban data, and a discussion on the relevance of cross-modal pattern analysis in the articulation between operators and alignment of the public transport offering with the self-actualizing city dynamics.