How to predict city traffic


Feb 28, 2023

A new machine learning model can predict city traffic activity in different urban zones. To do so, a Complexity Science Hub researcher used data from a main car-sharing company in Italy as a proxy for overall city traffic. Understanding how different urban zones interact can help avoid traffic jams, for example, and enable targeted responses of policy makers – such as local expansion of public transportation.

Understanding people’s mobility patterns will be central to improving urban traffic flow. “As populations grow in urban areas, this knowledge can help policymakers design and implement effective transportation policies and inclusive urban planning”, says Simone Daniotti of the Complexity Science Hub. 

 

For example, if the model shows that there is a nontrivial connection between two zones, i.e., that people commute from one zone to another for certain reasons, services could be provided that compensate for this interaction. If, on the flip side, the model shows that there is little activity in a particular location, policymakers could use that knowledge to invest in structures to change that.

MODEL ALSO FOR OTHER CITIES LIKE VIENNA

For this study a major car-sharing company provided the data: the location of all cars in their fleet in four Italian cities (Rome, Turin, Milan, and Florence) in 2017. The data was obtained by constantly querying the service provider’s web APIs, recording the parking location of each car, as well as the start and end timestamps. “This information allows us to identify the origin and destination of each trip,” Daniotti explains. 

 

Daniotti used that as a proxy for all city traffic and created a model that not only allows accurate spatio-temporal forecasting in different urban areas, but also accurate anomaly detection. Anomalies such as strikes and bad weather conditions, both of which are related to traffic. 

 

The model could also make predictions about traffic patterns for other cities such as Vienna. “However, this would require appropriate data,” Daniotti points out.

Predict traffic in cities © Complexity Science Hub, Sony CS

OUTPERFORMING OTHER MODELS

While there are already many models designed to predict traffic behavior in cities, “the vast majority of prediction models on aggregated data are not fully interpretable. Even though some structure of the model connects two zones, they cannot be interpreted as an interaction” explains Daniotti. This limits understanding of the underlying mechanisms that govern citizens’ daily routines.

 

Since only a minimal number of constraints are considered and all parameters represent actual interactions, the new model is fully interpretable.

Predict traffic in cities © Complexity Science Hub, Sony CS

BUT WHAT IS PREDICTION WITHOUT INTERPRETATION?

“Of course it is important to make predictions,” Daniotti explains, “but you can make very accurate predictions, and if you don’t interpret the results correctly, you sometimes run the risk of drawing very wrong conclusions.” 

 

Without knowing the reason why the model is showing a particular result, it is difficult to control for events where the model was not showing what you expected. “Inspecting the model and understanding it, helps us, and also policy makers, to not draw wrong conclusions,” Daniotti points out.

FIND OUT MORE

The study “A maximum entropy approach for the modelling of car-sharing parking dynamics” has been published in Scientific Reports.


Press

Es gibt auch gute Klima-Nachrichten


SZ, Sep 22, 2023

Press

Study reveals organized crime is the fifth-largest employer in Mexico


El Pais, Sep 22, 2023

Publication

S. Juhász, G. Pintér, et al.

Amenity complexity and urban locations of socio-economic mixing

EPJ Data Science 12 (2023) 34

News

Sep 21, 2023

Curbing the Violence by Mexican Cartels

News

Sep 18, 2023

Why do some environmental shocks lead to disaster while others don't?

Publication

B. Méro, A. Borsos, et al.

A High-Resolution, Data-Driven Agent-Based Model of the Housing Market

Journal of Economic Dynamics and Control (2023) 104738

News

Sep 18, 2023

Unlocking Urban Diversity: The Magnetism of Complex Amenities

Press

175.000 personas al servicio de los cárteles mexicanos, según estudio


CNN, Sep 22, 2023

Publication

R. Prieto-Curiel, G. M. Capedelli, A. Hope

Reducing cartel recruitment is the only way to lower violence in Mexico

Science 381(6664) (2023) 1312-1316

News

Sep 21, 2023

Curbing the Violence by Mexican Cartels

News

Sep 18, 2023

Unlocking Urban Diversity: The Magnetism of Complex Amenities

News

Sep 18, 2023

Why do some environmental shocks lead to disaster while others don't?

News

Aug 31, 2023

New study uncovers the Causes of the Qing Dynasty's Collapse

News

Aug 28, 2023

CSH hosts workshop on visualizing complexity science

Spotlight

Aug 22, 2023

Wallet 2.0: What Does the Future of Money Look Like?

Spotlight

Aug 14, 2023

Open Arms Grant: How conferences can ensure global participation

News

Aug 1, 2023

Scientists develop method to spot the spread of armed conflicts

News

Jul 27, 2023

A lot of exchanges and discussions at NetSci

News

Jul 20, 2023

Prenatal malnutrition increases diabetes incidence later in life

Spotlight

Jun 29, 2023

CSH Spin-Off Iknaio receives aws seed funding

Press

175.000 personas al servicio de los cárteles mexicanos, según estudio


CNN, Sep 22, 2023

Press

Study reveals organized crime is the fifth-largest employer in Mexico


El Pais, Sep 22, 2023

Press

Es gibt auch gute Klima-Nachrichten


SZ, Sep 22, 2023

Press

Kindesmissbrauch: Wie Kriminelle die Anonymität des Darknets nutzen


Kurier, Sep 7, 2023

Press

L'effondrement de la dernière dynastie chinoise des Qing, un avertissement pour le futur ?


GEO, Sep 6, 2023

Press

Warum Saudi-Arabiens ehrgeizige Stadt der Zukunft nicht optimal ist


Spektrum der Wissenschaft, Sep 6, 2023

Press

Qing Dynasty’s Collapse Driven By Three Things, And They Could Happen To Us


IFL Science, Sep 4, 2023

Press

Warum die Qing-Dynastie unterging


ORF, Sep 5, 2023

Press

There are thousands of cities in the world, and there’s a reason none is in the shape of a line


Fast Company, Aug 12, 2023

Publication

R. Prieto-Curiel, G. M. Capedelli, A. Hope

Reducing cartel recruitment is the only way to lower violence in Mexico

Science 381(6664) (2023) 1312-1316

Publication

B. Méro, A. Borsos, et al.

A High-Resolution, Data-Driven Agent-Based Model of the Housing Market

Journal of Economic Dynamics and Control (2023) 104738

Publication

S. Juhász, G. Pintér, et al.

Amenity complexity and urban locations of socio-economic mixing

EPJ Data Science 12 (2023) 34

Publication

R. Hanel, S. Thurner

Equivalence of information production and generalised entropies in complex processes

PLOS ONE 18(9) (2023) e0290695

Publication

K. Frenken, F. Neffke, A. van Dam

Capabilities, institutions and regional economic development: a proposed synthesis

Cambridge Journal of Regions, Economy and Society (2023) rsad021

Publication

G. Orlandi, D. Hoyer, et al.

Structural-demographic analysis of the Qing Dynasty (1644–1912) collapse in China

PLoS ONE 18(8) (2023) e0289748

Publication

N. Kushwaha, E.D. Lee

Discovering the mesoscale for chains of conflict

PNAS Nexus 2(7) (2023) pgad228

Publication

H. Metzler, D. Garcia

Social Drivers and Algorithmic Mechanisms on Digital Media

Perspectives on Psychological Science (2023)

Publication

M. Laber, P. Klimek, et al.

Shock propagation from the Russia–Ukraine conflict on international multilayer food production network determines global food availability

Nature Food (2023) doi: 10.1038/s43016-023-00771-4

Publication

M. Kaleta, et al.

Diabetes incidence in Austria: The role of famines on diabetes and related NCDs

Helyion, Volume 9, Issue 7, July 2023, e17570

Publication

D. R. Lo Sardo, S. Thurner, et al.

Systematic population-wide ecological analysis of regional variability in disease prevalence

Heliyon 9(4) (2023) e15377

Publication

R. Prieto-Curiel, J. E. Patino, B. Anderson

Scaling of the morphology of African cities

PNAS 120 (9) (2023) e2214254120