Climate-driven machine learning models for predicting asphalt pavement surface temperature for aging assessments

Understanding how climate variability influences asphalt pavement surface temperatures is critical for assessing the durability and long-term performance of bituminous materials in road construction. This study develops a computational framework that integrates physical and data-driven modeling techniques to characterize asphalt surface temperature dynamics across diverse Australian climates. Using high-resolution climate records from over 450 meteorological stations, we established a comprehensive pipeline for data preprocessing, imputation, and hybrid feature selection through Self-Organizing Maps (SOM), Gaussian Mixture Models (GMM), and SHapley Additive exPlanations (SHAP), offering explainability and cluster-wise insights into regional climate behavior. To address spatial heterogeneity in thermal loading, a national climate zoning scheme was developed using k-means clustering, enabling targeted material performance assessment across climate zones. Within this framework, four predictive models were designed and evaluated: a climate-driven multiple linear regression model (C-MLR), an annual climatic pavement stress model (ACPS), a physically-informed heat flux model (H-FLUX), and a symbolic regression model based on linear genetic programming (LGP). Bayesian optimization and Limited-memory Broyden–Fletcher–Goldfarb–Shanno with Bounds (L-BFGS-B) tuning enhanced each model's predictive accuracy, with LGP outperforming others while maintaining model interpretability. The resulting high-resolution asphalt surface temperature maps inform the evaluation of oxidative aging, rutting, and thermal cracking risks. By linking climate-driven temperature variation to pavement distress mechanisms, this work provides a transferable framework for engineering design, offering insights for the development of climate-resilient road infrastructure. This approach demonstrates the effective use of Artificial Intelligence (AI) techniques for real-world civil engineering challenges under environmental uncertainty.