Asphalt property prediction through high‐throughput molecular dynamics simulation

Abstract

The relationship between saturate, aromatic, resin, and asphaltene (SARA) contents and asphalt properties remains unclear. This study aimed to propose a high‐throughput molecular dynamics simulation framework and demonstrate its application in rapidly building asphalt molecular models of various SARA ratios and predicting their properties, using density as an example. Based on the framework, 400 models with varying SARA ratios with different aging degrees were generated to calculate their densities and used to train machine learning algorithms. The ordinary least squares model achieved R2 values exceeding 80%, and quantitative formulas linking asphalt density to SARA ratios were derived. It was found that saturate content negatively correlates with asphalt density, while resin content positively correlates with asphalt density. Additionally, asphalt density and viscosity increase with aging, influenced simultaneously by the SARA ratio and aging degree. Overall, this paper creates a rapid, high‐throughput molecular simulation pathway to predict asphalt behavior.