Based on the interpretable Machine learning algorithm gradient boosting machine (GBM), this study employs the long-term pavement performance (LTPP) database to predict the rut depth of asphalt pavement by considering various influential factors, including environmental, traffic, structural, and material variables. Compared with artificial neural network (ANN) and support vector machines (SVM), the GBM model provides superior interpretability by explaining the partial dependence of key factors. The results show that, compared with ANN and SVM, the GBM model reduces the RMSE by 0.75 and 0.25, and the MAE by 0.54 and 0.07, respectively, on the test datasets. The main factors affecting rut depth include the initial rutting depth measurement, time elapsed since the first measurement, total asphalt pavement thickness, and cumulative equivalent single axle load (ESAL). The partial dependency analysis helps pavement maintenance departments better understand rutting development under various influential factors, thereby supporting more effective pavement maintenance and management decisions.

This study applies machine learning techniques to predict the international roughness index (IRI) of asphalt pavement using structural, performance, environmental, and traffic-related variables. Data were obtained from the long-term pavement performance (LTPP) database and Chinese pavement datasets, with 3066 asphalt pavement sections (construction number =1) selected for analysis. Model parameters were optimized using cross-validation combined with grid search. Considering the selected factors, three machine learning models, namely artificial neural networks (ANN), support vector machines (SVM), and XGBoost, were employed to predict IRI. Their performance was evaluated using R², root mean square error (RMSE) and mean absolute error (MAE). The results show that XGBoost achieved the best predictive performance (R² = 0.96, RMSE=0.08, MAE=0.05). Feature importance analysis based on XGBoost indicates that the initial IRI is the most influential factor. These results show that XGBoost can accurately predict asphalt pavement IRI and provide a reference model for pavement management systems.