Early detection of traffic flow breakdown at highway bottleneck using section-based transitional instability

Abstract

Traffic flow breakdowns refer to abrupt transitions from free-flow to congested conditions, typically occurring at freeway bottlenecks. Due to their sudden onset and the complex interactions driving them, early detection remains a challenging task in traffic operations. These events are often preceded by a transitional state—referred to as the pre-breakdown state—during which traffic conditions exhibit growing instability. Most existing studies define breakdowns using threshold-based criteria such as a sudden shift in speed at a single detector. Although such point-based methods can capture local changes, they often fail to reflect broader spatial interactions across adjacent sections. This study proposes a section-based framework that jointly analyzes upstream and downstream conditions to capture the spatial heterogeneity within a segment. A composite metric, the Dynamic Instability Score (DIS), is introduced to quantify sectional instability based on short-term temporal responsiveness and spatial imbalance. The methodology includes traffic state identification, DIS computation, and early warning detection. The DIS is calibrated using ROC-based thresholding at the boundary between free-flow and transitional states, ensuring sensitivity to early instability while minimizing false alarms. Empirical evaluations on freeway segments with recurrent bottlenecks demonstrate that DIS serves as a reliable leading indicator. Compared to point-based measures, it achieves higher accuracy and lower false-alarm rates, while preserving practical lead times. These results highlight the importance of capturing transitional instability during the pre-breakdown state and support the use of section-based indicators for proactive congestion management.