A Traffic Conflict Risk Assessment Model for Highway Construction Zones Based on Trajectory Data

Highway construction zones present substantial safety challenges due to their dynamic and unpredictable traffic conditions. With the rising number of highway projects, limited accident data during brief construction phases underscores the need for alternative safety evaluation methods, such as traffic conflict analysis. This study addresses vehicular safety issues within the Kunshan section of the Shanghai-Nanjing Expressway, focusing on conflict risk assessment through a spatio-temporal analysis of a construction zone. Using drone-captured video, vehicle trajectories were extracted to derive key operational indicators, including speed and acceleration, providing a spatio-temporal foundation for analyzing traffic flow and conflict dynamics. A novel **Comprehensive Collision Risk Index (CCRI)** was introduced, integrating Time-to-Distance-to-Collision (TDTC) and Enhanced Time-to-Collision (ETTC) metrics to enable a multidimensional assessment of conflict risk. The CCRI captures both longitudinal and lateral risks across varied traffic scenarios, offering a robust indicator of conflict distribution, severity, and spatial characteristics within the zone. Conflicts with CCRI values exceeding 20 seconds are considered non-critical, indicating minimal risk. To predict conflict severity, three machine learning models—Logistic Regression, Random Forest, and Multi-Layer Perceptron (MLP) Neural Network—were developed and compared. The Random Forest and MLP models demonstrated superior predictive accuracy and stability, with MLP achieving balanced performance across both severe and general conflict categories. Additionally, spatio-temporal analysis of CCRI values identified transition zones as lower-risk areas, with factors such as speed and distance differentials emerging as primary contributors to conflict severity. This research advances traffic safety evaluation in construction zones by introducing CCRI as a comprehensive, spatio-temporal risk metric and leveraging machine learning for precise conflict severity prediction. The findings provide valuable insights for developing targeted safety interventions and adaptive traffic management strategies, offering crucial support for transportation engineers, safety practitioners, and policymakers in enhancing safety within dynamic, high-risk construction environments.