Machine Learning–Driven Pavement Management System Framework for Bleeding Severity Classification Using Long-Term Pavement Performance Data

This study developed a machine learning–based framework to detect and classify bleeding severity in flexible pavements. It utilized nationally representative pavement performance data obtained from the Long-Term Pavement Performance program. Bleeding significantly reduces surface friction and increases crash risk, yet it remains difficult to detect through traditional inspection methods. The analysis was implemented on 3,781 observations from 658 pavement sections across 35 US states, incorporating structural, environmental, and traffic parameters. The methodology included feature selection, a new bleeding severity classification based on affected surface area, and comparative evaluation of seven classification models. Across all evaluated models, Light Gradient Boosting (LGB) and Extreme Gradient Boosting (XGB) demonstrated the strongest predictive performance. LGB achieved a Precision of 0.85, while XGB closely followed at 0.84; both models recorded a Recall of 0.83, with corresponding F1-scores of 0.83 and 0.82. The subsequent interpretability assessment, using feature importance, a representative decision tree, and partial dependence plots, confirmed that air voids, voids filled with asphalt, pavement age, and total annual precipitation consistently emerged as the dominant variables influencing bleeding severity. The results demonstrated the potential of machine learning to support Pavement Management Systems by enabling accurate identification of severe bleeding cases, thereby reducing inspection efforts and enabling targeted maintenance planning. Although some regions remained underrepresented in the available data, the framework provides a foundation for enhanced bleeding detection and classification. Future work should focus on expanding regional coverage, incorporating advanced sensor and imaging technologies, and developing predictive models for long-term maintenance planning and roadway safety.