Development of a Real-time Crash Risk Prediction Model Incorporating the Various Crash Mechanisms across Different Traffic States

ABSTRACT<b><i>Objective:</i></b> This study aimed to identify the traffic flow variables contributing to crash risks under different traffic states, and to develop a real-time crash risk model incorporating the varying crash mechanisms across different traffic states.<b><i>Methods:</i></b> The crash, traffic and geometric data were collected on the I-880N freeway in California, United States in 2008 and 2009. This study considered four different traffic states in the Wu's four-phase traffic theory. They are free fluid traffic, bunched fluid traffic, bunched congested traffic and standing congested traffic. Several different statistical methods were used to accomplish the research objective.<b><i>Results:</i></b> The preliminary analysis showed that traffic states significantly affected crash likelihood, collision type, and injury severity. The nonlinear canonical correlation analysis (NLCCA) was conducted to identify the underlying phenomena that made certain traffic states more hazardous than others. The results suggested that different traffic states were associated with various collision types and injury severities. The matching of traffic flow characteristics and crash characteristics in NLCCA revealed how traffic states affected traffic safety. The logistic regression analyses showed that the contributing factors to crash risks were quite different across various traffic states. To incorporate the varying crash mechanisms across different traffic states, the random-parameters logistic regression was used to develop the real-time crash risk model. Bayesian inference based on Markov chain Monte Carlo (MCMC) simulations was used for model estimation. The parameters of traffic flow variables in the model were allowed to vary across different traffic states. Compared with the standard logistic regression model, the proposed model significantly improved the goodness-of-fit and the predictive performance.<b><i>Conclusions:</i></b> These results can promote a better understanding of the relationship between traffic flow characteristics and crash risks, which is valuable knowledge in the pursuit of improving traffic safety on freeways through the use of dynamic safety management systems.

摘要
<b><i>研究目的：</i></b> 本研究旨在识别不同交通状态下影响碰撞风险的交通流变量，并构建可融合不同交通状态下差异化碰撞机理的实时碰撞风险模型。
<b><i>研究方法：</i></b> 本研究收集了2008年至2009年美国加利福尼亚州I-880N高速公路的碰撞数据、交通数据及几何设计数据。本研究采用吴式四阶段交通流理论中的四类交通状态，分别为自由流体交通、束状流体交通、束状拥挤交通及静止拥挤交通。为达成研究目标，本研究运用了多种统计分析方法。
<b><i>研究结果：</i></b> 初步分析结果表明，交通状态对碰撞发生概率、碰撞类型及伤害严重程度均存在显著影响。本研究开展了非线性典型相关分析（Nonlinear Canonical Correlation Analysis，NLCCA），以识别导致特定交通状态危险性更高的潜在现象。结果显示，不同交通状态与各异的碰撞类型及伤害严重程度密切相关。通过非线性典型相关分析中交通流特性与碰撞特性的匹配关系，阐明了交通状态对交通安全的影响路径。逻辑回归分析结果表明，不同交通状态下影响碰撞风险的贡献因子存在显著差异。为融合不同交通状态下的差异化碰撞机理，本研究采用随机参数逻辑回归方法构建实时碰撞风险模型，并基于马尔可夫链蒙特卡洛（Markov Chain Monte Carlo，MCMC）模拟的贝叶斯推断完成模型参数估计。模型中交通流变量的参数允许随不同交通状态发生变化。与标准逻辑回归模型相比，本研究提出的模型在拟合优度与预测性能上均有显著提升。
<b><i>研究结论：</i></b> 本研究结果可增进对交通流特性与碰撞风险之间关联的认知，对于依托动态安全管理系统提升高速公路交通安全水平具有重要参考价值。