Prediction of Airport Pavement Roughness Using Random Forest Model Based on Hyperparameter Optimization Algorithms

ABSTRACT Airport pavement roughness is a critical factor influencing aircraft safety, operational efficiency, and maintenance costs. Accurate prediction of pavement roughness is essential for effective pavement management and timely maintenance interventions. However, existing prediction methods often suffer from limited accuracy and inadequate adaptability to varying climatic conditions. To address these challenges, a random forest (RF) model optimized via hyperparameter optimization algorithms was developed to accurately predict airport pavement roughness based on data collected from 6 airports across 5 distinct climatic zones. Feature variables were selected, and their dimensionality was reduced through Pearson correlation coefficients. The grid search (GS), differential evolution (DE), and Bayesian optimization (BO) algorithms were then used to optimize the three different roughness prediction models: support vector machine (SVM), eXtreme gradient boosting (XGBoost), and RF. The performances of the three different models were further compared. Additionally, model interpretation is conducted by the Shapley additive explanations (SHAP) method. The results indicate that the RF model significantly outperforms the SVM and XGBoost models, showing notable improvements in overall prediction accuracy, such as R2, root mean squared error, mean absolute error, and mean absolute percentage error. Compared with the GS and DE algorithms, the BO algorithm is the most effective method for enhancing the precision of the RF roughness prediction model. The BO-RF model shows significant improvements in both accuracy and efficiency, particularly with a sharp reduction in runtime and a substantial increase in precision. SHAP analysis reveals the three key feature variables that significantly influence airport pavement predict roughness model: total sunshine hours, average relative humidity, and impact stiffness modulus. These findings and the optimized BO-RF model provide a robust and efficient approach that can be applied globally to improve airport pavement roughness prediction, supporting better maintenance decision-making under diverse climatic conditions.