The intrinsic variability associated with waste-derived bitumen modifiers poses persistent limitations for conventional deterministic pavement design approaches. This study establishes a hybrid modelling architecture that integrates physics-informed boundary constraints with stochastic simulation components to predict the rheological performance of asphalt binders modified with waste frying oil. Literature-derived parameter ranges are embedded within a Gaussian copula-based dependency structure and expanded through large-scale Monte Carlo simulation to generate a statistically convergent dataset comprising 1,000,000 realizations. The integrated modelling structure preserves the nonlinear relationships among key rheological indicators, including penetration, softening point, and modifier dosage, while maintaining physical consistency. The predictive capability of the proposed architecture is validated using standard statistical metrics, achieving coefficients of determination exceeding 0.98 for penetration and 0.93 for softening point. A mode-based master curve is further constructed to provide a stable and computationally efficient representation of binder behaviour across varying modifier contents. The results demonstrate that the proposed hybrid modelling structure offers a reliable alternative to extensive laboratory testing, reducing experimental effort while retaining predictive fidelity. From a system perspective, the framework provides a structured basis for incorporating material variability into pavement performance evaluation and can be interpreted as a simplified digital twin component for asphalt material systems. The study thereby contributes to the integration of stochastic modelling within engineering-oriented predictive structures for sustainable pavement design.
Open Access
News 
Journal Metrics
Journal Overview
Associated Journals
