Exploring interacting effects of risk factors on run-off-road crash severity: An interpretable machine learning model joint with latent class clustering

Abstract

Run-Off-Road (ROR) crashes are frequent and pose a significant risk of injury and fatality. Given the complexity of their mechanisms and the interaction of multiple factors, this study aims to comprehensively investigate the factors influencing the severity of ROR crashes, which have been understudied. Furthermore, addressing the current methodological challenge in machine learning (ML) crash modeling, this study proposes an approach to tackle unobserved heterogeneity in ML. An interpretable ML joint with prior latent class clustering is implemented. The significant risk factors and interactions are interpreted using SHAP (SHapley Additive exPlanations) method across clusters. This study utilizes ROR crash records, traffic, and geometric data from main suburban freeways in Iran collected over a 5-year period. The key interacting factors associated with severe ROR during adverse weather (cluster 1) are: co-occurrence of low congestion and higher speed variation; low congestion, nighttime darkness and rollover; roadway departure by buses and mini-buses and rollover occurrence; vehicle departure and collision with fixed objects. Moreover, the critical interactions for nighttime condition (cluster 2) are: curve sections combined with longitudinal slope; inside shoulder width <1.5 m and a hit median concrete NewJersey barrier. The risky interactions for crashes occurred in curves (cluster 3) are: departing in two-lane sections in low congestion conditions; vehicles collisions with the median concrete NewJersey barriers. The findings of this study enhance comprehension of the significant effects of interactions under various conditions, offering valuable insights for policymakers. Additionally, recommendations are offered to mitigate the risk of severe ROR crashes.