Commercial motor vehicle (CMV) safety is a major concern in the United States, including the District of Columbia (DC), where CMVs make up 15% of traffic. This research uses a comprehensive approach, combining statistical analysis and machine learning techniques, to investigate the impact of road pavement conditions on CMV accidents. The study integrates traffic crash data from the Traffic Accident Reporting and Analysis Systems Version 2.0 (TARAS2) database with pavement condition data provided by the District Department of Transportation (DDOT). Data spanning from 2016 to 2020 was collected and analyzed, focusing on CMV routes in DC. The analysis employs binary logistic regression to explore relationships between injury occurrence after a CMV crash and multiple independent variables. Additionally, Artificial Neural Network (ANN) models were developed to classify CMV crash injury severity. Importantly, the inclusion of pavement condition variables (International Roughness Index and Pavement Condition Index) substantially enhanced the accuracy of the logistic regression model, increasing predictability from 0.8% to 41%. The study also demonstrates the potential of Artificial Neural Network models in predicting CMV crash injury severity, achieving an accuracy of 60% and an F-measure of 0.52. These results highlight the importance of considering road pavement conditions in road safety policies and interventions. The study provides valuable insights for policymakers and stakeholders aiming to enhance road safety for CMVs in the District of Columbia and showcases the potential of machine learning techniques in understanding the complex interplay between road conditions and CMV crash occurrences.

Publication Date


Publication Type



Transportation Engineering, Transportation Technology

Digital Object Identifier


MTI Project



vehicle accident, car crash, road conditions


Artificial Intelligence and Robotics | Transportation