Getting Real: The Challenge of Building and Validating a Large-Scale Digital Twin of Barcelona’s Traffic with Empirical Data

Abstract

Large-scale microsimulations are increasingly resourceful tools for analysing in detail citywide effects and alternative scenarios of our policy decisions, approximating the ideal of ‘urban digital twins’. Yet, these models are costly and impractical, and there are surprisingly few published examples robustly validated with empirical data. This paper, therefore, presents a new large-scale agent-based traffic microsimulation for the Barcelona urban area using SUMO to show the possibilities and challenges of building these scenarios based on novel fine-grained empirical big data. It combines novel mobility data from real cell phone records with conventional surveys to calibrate the model comparing two different dynamic assignment methods for getting an operationally realistic and efficient simulation. Including through traffic and the use of a stochastic adaptive routing approach results in a larger 24-hour model closer to reality. Based on an extensive multi-scalar evaluation including traffic counts, hourly distribution of trips, and macroscopic metrics, this model expands and outperforms previous large-scale scenarios, which provides new operational opportunities in city co-creation and policy. The novelty of this work relies on the effective modelling approach using newly available data and the realistic robust evaluation. This allows the identification of the fundamental challenges of simulation to accurately capture real-world dynamical systems and to their predictive power at a large scale, even when fed by big data, as envisioned by the digital twin concept applied to smart cities.

How Routing Strategies Impact Urban Emissions

“…We download Milan's road network 𝐺 = (𝑉 , 𝐸) from Open-StreetMap (|𝑉 | = 5551 nodes and |𝐸| = 36, 945 edges) and preprocess it to fix incorrect information regarding turns, intersections, road interruptions, the number of lanes per road, and other inaccuracies that characterise these data [4].…”

“…Based on the matrix 𝑀 and the road network 𝐺, we compute the mobility demand 𝐷 with 𝑁 = 15, 000 vehicles using the procedure described in Section 3.2. We choose 𝑁 = 15, 000 because it minimises the difference between the distribution of travel time of real trajectories and simulated ones, a common way to assess the realism of a simulated urban traffic [4] (see Appendix B for detail).…”

Digital Twins: Potentials, Ethical Issues, and Limitations

“…Let us start with traffic flows. 42 Here, one can find a range of diverse congestion patterns, which depend on the traffic volume and inhomogeneities along the road (such as on-and off-ramps, gradients, or changes in the number of lanes). 43 Interestingly, due to the interactions of many vehicles, traffic flows are multi-stable, i.e.…”

A Framework to Develop Urban Aerial Networks by Using a Digital Twin Approach

“…The employment of digital twin approaches to simulate processes and evolutions of territorial realities has becoming more and more usual, with the aim of describing in a quantitative and detailed way the physical world to simulate and predict the effects of actions. The concept of digital twin was first formalized by Grieves [35] for some industrial contexts, but it is now used in several other fields such as road infrastructures [36], harbours [37], boats [30] and other civil sectors [38] to evaluate noise and air pollution, solar potential, and the effects of future urban development [39], or for simulating, planning and managing urban transportation networks [40,41].…”