Around 50% of the global population lives in metropolitan areas, and this is expected to grow to 75% by 2050. Mobility within these areas is complex as it involves multiple modalities of transport, multiple managing authorities, as well as several millions of citizens. The cost of inefficiency in transport and mobility are enormous. For example, inefficiency costs the UK economy €5.8 billion each year. €583 million is wasted on fuel (e.g. traffic congestion) alone each year, which attributes to increased urban pollution and CO2. Hold-ups to business or freight vehicles amounts to €1.5bn annually.
Mobility generates huge amounts of data thought thousands of sensors, city cameras, and connected cars, as well as millions of citizens connected through their mobile devices. If properly managed, this data can be used to understand, optimise and manage mobility and make it more efficient, sustainable and resilient.
SETA will address this challenge, creating a technology and methodology able to use this wealth of data to change the way mobility is organised, monitored and planned in large metropolitan areas. The solution will be able to collect, process, link and fuse high-volume, high-velocity, multi-dimensional, heterogeneous, cross-media, cross-sectorial data and to use it to model mobility with a precision, granularity and dynamicity that is impossible with today’s technologies. Such models will be the basis of pervasive services to citizens and business, as well as decision makers to support safe, sustainable, effective, efficient and resilient mobility.
The project has the potential to impact the everyday lives of millions of people, their health and the environment with enormous financial and social impact.
SETA’s solution will be evaluated rigorously by citizens, business and decision makers in 3 cities across Europe.
The proposal includes a commercialisation plan and describes the economy of managing the SETA ecosystem in a metropolitan area.
Aimsun’s primary role in SETA was performance evaluation of a range of methods for generating local and network-wide traffic flows and travel demand predictors for private vehicular traffic. Additionally the team calibrated and validated the underlying traffic network models for the two use cases involved in the project.
Results from one of the cases, the City of Santander, was used as part of a local and network-wide traffic and demand prediction methodology demonstration and sensitivity analysis to show each method’s robustness and scalability for handling large data sets and large-scale applications.
In performance assessment, methods were compared with corresponding conventional methods used in practice to identify and demonstrate improvements. In particular it was demonstrated that: