A Novel Simulation-Based Framework for Predicting Lane-Level Pavement Deterioration Under Freight Loading and Stop-and-Go Urban Traffic

Sustainable and resilient road infrastructure requires the early identification of pavement deterioration mechanisms that emerge under complex urban traffic conditions, particularly at signalized intersections where repeated stop–go operations, queue persistence, and lane-wise freight concentration generate highly nonuniform structural loading. However, most existing intelligent transportation studies emphasize crash prediction, traffic-state estimation, or mobility optimization, while the infrastructure-performance consequences of freight-dominant interrupted flow remain insufficiently addressed. To support proactive pavement management and resilient urban road operation, this study proposes a traffic simulation-driven deep learning framework for predicting lane-level pavement deterioration under freight loading and stop–go urban traffic conditions. A high-resolution PTV Vissim 2024 microscopic simulation environment was developed for a four-leg signalized urban intersection, and a structured multi-scenario design was used to generate progressively increasing operational stress regimes, ranging from baseline flow to freight-dominant oversaturated operation. The resulting lane-wise dataset integrates direct traffic variables with pavement-oriented descriptors, including the Lane Freight Loading Index (LFLI), Stop–Go Severity Index (SGSI), ESAL proxy, queue persistence, and Loading Asymmetry Index (LAI). To learn the complex relationship between traffic operation and infrastructure degradation, a new Freight-Aware Lane Interaction Transformer Network (FLIT-Net) is introduced. The proposed model combines feature embedding, lane-interaction self-attention, freight-aware gating, residual refinement, and multi-task regression to jointly predict rutting risk, fatigue-cracking risk, and the Pavement Deterioration Index (PDI). Experimental results show that FLIT-Net outperforms MLP, CNN, LSTM, Bi-LSTM, and generic Transformer baselines, achieving RMSE/MAE/R2 values of 0.041/0.032/0.9687 for rutting risk, 0.044/0.034/0.9635 for fatigue-cracking risk, and 0.031/0.024/0.9824 for PDI. Sensitivity and scenario-wise analyses further confirm that deterioration increases monotonically with freight intensity, stop–go severity, and queue persistence, highlighting the importance of lane-resolved deterioration intelligence for sustainable maintenance prioritization. The proposed framework bridges traffic microsimulation, pavement-oriented feature engineering, and freight-aware deep learning, providing a decision-support basis for improving the performance, safety, and resilience of urban pavement infrastructure.