An Efficient and Explainable Ensemble Learning Model for Asphalt Pavement Condition Prediction Based on LTPP Dataset

Accurate prediction of asphalt pavement condition is important to guide pavement maintenance practices. The existing models for pavement condition predictions are predominantly based on linear regressions or simple machine learning techniques. However, additional work on these models is needed to improve their basic assumptions, training efficiency, and interpretability. To this end, a new modeling approach is proposed in this manuscript, which includes a ThunderGBM-based ensemble learning model, coupled with the Shapley Additive Explanation (SHAP) method, to predict the International Roughness Index (IRI) of asphalt pavements. The SHAP method was applied to interpret the underlying influencing factors and their interactions. Twenty features were initially identified as the model inputs, and 2,699 observations were extracted from the Long-Term Pavement Performance (LTPP) database. Three benchmark models, namely the Mechanistic-Empirical Pavement Design Guide (MEPDG) model, the ANN model and the RF model, were used for comparison. The results showed that the developed model achieved a satisfactory result with a R-squared ($\mathbf {R}^{2}$) value of 0.88 and Root Mean Square Error (RMSE) of 0.08, both better than three benchmark models. It ran 86 times and 2.3 times faster than the ANN and RF model, respectively. Feature interpretation was performed to identify the top influencing factors of IRI. The 20-feature model was further simplified based on the analysis result. The simplified model only required six features to efficiently and effectively predict IRI using the proposed ThunderGBM-based approach, which can reduce the workload in data collection and management for pavement engineers.