Scalable Learning of Segment-Level Traffic Congestion Functions

TL;DR

This paper introduces a scalable, data-driven neural network framework for modeling traffic congestion at segment level across multiple cities, outperforming traditional methods on highway roads and generalizing well to unobserved segments and new cities.

Contribution

The study presents a novel neural network approach that learns a universal congestion function applicable across all road segments and cities, improving scalability and transferability.

Findings

Outperforms segment-specific models on highway congestion prediction.

Shows strong generalization to unobserved segments and new cities.

Can approximate segment attributes like critical densities using static features.

Abstract

We propose and study a data-driven framework for identifying traffic congestion functions (numerical relationships between observations of traffic variables) at global scale and segment-level granularity. In contrast to methods that estimate a separate set of parameters for each roadway, ours learns a single black-box function over all roadways in a metropolitan area. First, we pool traffic data from all segments into one dataset, combining static attributes with dynamic time-dependent features. Second, we train a feed-forward neural network on this dataset, which we can then use on any segment in the area. We evaluate how well our framework identifies congestion functions on observed segments and how it generalizes to unobserved segments and predicts segment attributes on a large dataset covering multiple cities worldwide. For identification error on observed segments, our single data-driven congestion function compares favorably to segment-specific model-based functions on highway roads, but has room to improve on arterial roads. For generalization, our approach shows strong performance across cities and road types: both on unobserved segments in the same city and on zero-shot transfer learning between cities. Finally, for predicting segment attributes, we find that our approach can approximate critical densities for individual segments using their static properties.