Chenqiang Zhu

As critical nodes in urban transportation networks, the operational resilience of urban tunnels directly affects roadway network efficiency and public safety. Existing studies on tunnel resilience exhibit deficiencies in the attention paid to routine incidents, the interpretability of evaluation methods, and the robustness of underlying data. To address these gaps, this paper constructs a three-layer resilience evaluation framework (pre-event, during-event, and post-event) based on 1123 accident records, hourly traffic flow data, and expert scoring data from 10 urban tunnels in Shanghai in 2024. The framework integrates the Analytic Hierarchy Process (AHP) and min–max normalization to derive comprehensive resilience scores. Furthermore, two explainable artificial intelligence (XAI) techniques—SHAP (SHapley Additive exPlanations) feature importance analysis and K-means clustering—are introduced to identify key drivers of resilience differentiation and typical resilience patterns, respectively. Empirical results reveal that (1) half of the 10 tunnels achieve a B-level rating or above, while C/D-level tunnels still account for 50%, indicating considerable room for improvement; (2) SHAP analysis suggests that during-event absorption capacity contributes most significantly to resilience differences (50.24%), with the average traffic reduction rate being the most influential single indicator within this model; and (3) K-means clustering classifies the tunnels into four patterns: high-resilience balanced type, pre-event weak type, post-event weak type, and during-event weak type, each corresponding to distinct resilience enhancement strategies. The methodological framework developed in this paper effectively enables the quantification, interpretation, and pattern recognition of tunnel resilience, providing data-driven decision support for urban tunnel operation and management. It should be noted that the A–D ratings are sensitive to the normalization method: under an alternative normalization, 7 out of 10 tunnels change grade. The ratings should therefore be interpreted as relative to the selected sample rather than as absolute performance levels.

To mitigate the frequent occurrence of rear-end collisions on urban expressways under rainy weather conditions, firstly, accident risk levels were classified using traffic conflict indicators. Secondly, three machine learning models were employed to predict the accident severity across different scenarios. Furthermore, key influencing factors of rear-end collisions were identified and analyzed based on SHAP values. Case studies were conducted by simulating vehicle trajectory data under light, moderate, and heavy rain scenarios, using an open urban expressway dataset and car-following parameters for rainy conditions. Next, the Modified Time-to-Collision (MTTC) metric was calculated. Risk thresholds for low-, medium-, and high-risk levels were established for each rainfall category using percentile-based cumulative distribution analysis. Finally, real-time risk prediction under the three rainfall scenarios was conducted using XGBoost, LightGBM, and Random Forest models. The model performances were evaluated in terms of accuracy, recall, precision, and AUC. Overall, the study finds that the LightGBM model achieves the highest predictive capability, with AUC values exceeding 0.78 under all weather conditions. Moreover, the study concludes that factors ranked by SHAP values reveal that the minimum distance has the greatest influence in light rain scenarios. As rainfall intensity increases, the influences of minimum headway time and average vehicle speed are found to grow, highlighting an interaction pattern characterized by “speed-distance-flow” coupling.

In accident scenarios on freeways, traffic congestion, sharp declines in capacity, and the limitations of closed systems where vehicles cannot turn around or exit freely often pose serious challenges. To address these issues, this study develops an improved Markov Decision Process (MDP) framework for dynamic emergency lane opening. Compared with traditional MDP-based traffic control models, the proposed method integrates three enhancements: Firstly, an explicit action decision space transition mechanism that couples variable speed limits with emergency lane opening decisions; Secondly, vehicle-type–differentiated actions to support fine-grained and adaptive opening strategies; and a redesigned reward function incorporating congestion cost, action cost, rewards earned and penalty received to ensure decision rationality and operational feasibility. Based on this improved structure, the optimal strategy is derived using the value iteration algorithm. Finally, simulation results using SUMO demonstrate that under the innermost-lane accident scenario, the optimal strategy is to first implement “variable speed limits”, followed by “opening the emergency lane to all vehicles”. This approach increases average speed by 10.81% but enlarges the headway between vehicles at the detection cross-section, leading to an 8.79% decrease in vehicle throughput. Under the outermost-lane accident scenario, the optimal strategy is to first implement “variable speed limits”, followed by “opening the emergency lane to HOVs”, which increases average speed by 5.47% while reducing vehicle throughput by 3.13%. These results validate the effectiveness of the proposed model.