NEXICA: Discovering Road Traffic Causality (Extended arXiv Version)

2025-08-12

AI Summary

This study addresses the challenge of identifying critical road segments that drive congestion propagation in highway systems. Conventional approaches, which model continuous speed measurements, suffer from noise sensitivity and high computational complexity. To overcome these limitations, we propose an event-driven paradigm: modeling congestion occurrences as binary temporal events rather than continuous speeds, constructing a causal probabilistic graphical model via maximum likelihood estimation, and learning inter-segment causal relationships using a lightweight binary classifier. Our method integrates event detection, probabilistic graph modeling, and supervised learning to significantly improve both accuracy and efficiency of causal inference. Experiments on six months of real-world traffic data from 195 sensors in Los Angeles demonstrate that our approach outperforms state-of-the-art methods by +4.2% in accuracy and achieves a 3.8× speedup in inference time. The framework thus provides a scalable, real-time solution for congestion root-cause analysis and proactive traffic management.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements

Abstract

Road traffic congestion is a persistent problem. Focusing resources on the causes of congestion is a potentially efficient strategy for reducing slowdowns. We present NEXICA, an algorithm to discover which parts of the highway system tend to cause slowdowns on other parts of the highway. We use time series of road speeds as inputs to our causal discovery algorithm. Finding other algorithms inadequate, we develop a new approach that is novel in three ways. First, it concentrates on just the presence or absence of events in the time series, where an event indicates the temporal beginning of a traffic slowdown. Second, we develop a probabilistic model using maximum likelihood estimation to compute the probabilities of spontaneous and caused slowdowns between two locations on the highway. Third, we train a binary classifier to identify pairs of cause/effect locations trained on pairs of road locations where we are reasonably certain a priori of their causal connections, both positive and negative. We test our approach on six months of road speed data from 195 different highway speed sensors in the Los Angeles area, showing that our approach is superior to state-of-the-art baselines in both accuracy and computation speed.

Problem

• Identify highway segments causing traffic slowdowns elsewhere
• Develop probabilistic model for spontaneous and caused slowdowns
• Improve accuracy and speed in traffic causality detection

Innovation

• Event-based time series analysis for traffic slowdowns
• Probabilistic model with maximum likelihood estimation
• Binary classifier trained on known cause-effect pairs