Targeted contingency measures have proven highly effective at reducing the duration and harm caused by incidents. This study utilized the Classification and Regression Trees (CART) data mining technique to predict and quantify the duration of incidents. To achieve this, multisensor data collected from the Hangzhou freeway in China spanning from 2019 to 2021 was utilized to construct a regression tree with eight levels and 14 leaf nodes. By extracting 14 rules from the tree and establishing contingency measures based on these rules, accurate incident assessment and effective implementation of post-incident emergency plans were achieved. In addition, to more accurately apply the research findings to actual incidents, the CART method was compared with XGBoost, Random Forest (RF), and AFT (accelerated failure time) models. The results indicated that the prediction accuracy of the CART model is better than the other three models. Furthermore, the CART method has strong interpretability. Interactions between explanatory variables, up to seven, are captured in the CART method, rather than merely analyzing the effect of individual variables on the incident duration, aligning more closely with actual incidents. This study has important practical implications for advancing the engineering application of machine learning methods and the analysis of sensor data.

To enhance the efficiency of freeway emergency management and mitigate the occurrence of secondary incidents, this study builds a random-parameter (RP) accelerated-failure-time (AFT) model with heterogeneity in means (RPHM) to investigate the influencing factors of freeway incident duration and their potential heterogeneity. Given the incident data collected from the G2504 Hangzhou freeway in China, the proposed RPHM AFT model is compared with the AFT model and the RP AFT model. Results show that the RPHM AFT model has the best fitting accuracy, and can better reveal the potential heterogeneous effects among influencing factors. Fourteen covariates, including collision with fixed objects, scratches, rollovers, and fire, significantly affect the incident duration. Among all factors, the parameter of lane-closure effect on incident duration exhibits spatial variation. Scratches, heavy vehicles, multi-vehicle incidents, rainy conditions, and Lane-1 closure display random characteristics. Collision with fixed objects has a significant heterogeneous effect on the mean value of the index RPs of heavy vehicles and positively affects the incident duration. Furthermore, the temporal factor of the peak-hour index does not have a significant impact, indicating that the operation and management of domestic freeways are significantly different from foreign freeways and previous studies may not be directly applied to China. The research results provide a theoretical foundation for relevant departments to formulate differentiated emergency-response plans for freeways. Moreover, these findings are of great significance in improving the safety-management level of China’s freeways.