You can predict traffic with 90% accuracy just by looking at a map, so we don't really need all those sensors.
March 19, 2026
Original Paper
Fast and Scalable Traffic Volume Estimation using Modified betweenness Centrality
SSRN · 6356479
The Takeaway
City planners typically spend massive amounts of money on traffic sensors and complex human behavior surveys to estimate road usage. This research shows that the physical topology of the map itself—using 'edge betweenness centrality'—is enough to predict car volume with nearly the same precision as high-cost data models.
From the abstract
Many applications in transport systems analysis and planning-from travel time and accessibility calculations to environmental impact and noise assessments-make use of traffic volume and aggregate traffic flow estimates. Travel demand models can generate such estimates, but they often require extensive input data, long computational times, and are complex to validate. As a potentially less accurate but faster alternative, network science concepts like centrality measures have emerged. By default,