Resilient modulus (Mr) is key for understanding the stiffness and stress‒strain properties of road materials for flexible pavement design. Measuring Mr in a laboratory requires conducting dynamic triaxial loading tests with varying confining and deviatoric stresses, which can be costly and time-consuming process. This study evaluates various machine learning (ML) models to predict the Mr of cement-stabilized magnetite and hematite iron ore tailings based on multiple variables such as cement content, curing time, bulk stress, and deviatoric stress, which are considered as input parameters. For developing ML models, a set of data from experimental studies was collected. After comparison, Gaussian Process Regression outperformed other methods in predicting Mr of both MIOT and HIOT. For the MIOT and HIOT materials, the R² values were 0.9936 and 0.9876, and 0.9893 and 0.9825 for the train and test datasets, respectively. The sensitivity analysis revealed that the curing time was the least important input variable, whereas the Portland cement percentage was the most effective for predicting the Mr of cement-stabilized iron ore tailings. Additionally, a parametric study was undertaken to investigate the impact of each input variable on Mr.

Pavement performance models are considered a key element in pavement management systems since they can predict the future condition of pavements using historical data. Several indicators are used to evaluate the condition of pavements (such as the pavement condition index, rutting depth, and cracking severity), and the international roughness index (IRI), which is the most widely employed worldwide. This study aimed to develop an accurate IRI prediction model. Ten prediction methods were trained on a dataset of 35 independent variables. The performance of the methods was compared, and the light gradient boosting machine was identified as the best-performing method for IRI prediction. Then, the SHAP was synchronized with the best-performing method to prioritize variables based on their relative influence on IRI. The results suggested that initial IRI, mean annual temperature, and the duration between data collections had the strongest relative influence on IRI prediction. Another objective of this study was to determine the optimal uncertainty model for IRI prediction. In this regard, 12 uncertainty models were developed based on different conformal prediction methods. Gray relational analysis was performed to identify the optimal uncertainty model. The results showed that Minmax/80 was the optimal uncertainty model for IRI prediction, with an effective coverage of 93.4% and an average interval width of 0.256 m/km. Finally, a further analysis was performed on the outcomes of the optimal uncertainty model, and initial IRI, duration, annual precipitation, and a few distress parameters were identified as uncertain. The results of the framework indicate in which situations the predicted IRI may be unreliable.