A stochastic neural network based approach for metamodelling of mechanical asphalt concrete properties

Research output: Contribution to journalResearch articleContributedpeer-review


This study introduces a stochastic approach based on Convolutional Neural Networks (CNNs) for predicting mechanical Asphalt Concrete (AC) properties with dependency on the mixture composition, temperature and loading frequency. The underlying CNN metamodels were evaluated by a comprehensive database of AC properties with a total of 7400 dynamic modulus records. The CNN approach shows an improved accuracy compared to other state of the art machine learning approaches found in literature. Stochastic CNN based metamodels were developed to take into account the uncertainty of mechanical properties resulting from arbitrarily arranged aggregates and air voids in AC. The data used for the stochastic metamodels contain a total of 3645 dynamic modulus and phase angle values. They were obtained from microscale Finite Element (FE) simulations considering a heterogenous material composition and viscoelastic material behaviour of the AC binder. The developed stochastic CNN metamodels provide highly accurate predictions for the statistical characteristics such as mean values, standard deviations and empirical distribution functions of the dynamic modulus and the phase angle.


Original languageEnglish
Article number2177650
Number of pages17
JournalInternational Journal of Pavement Engineering
Issue number1
Publication statusPublished - 6 Dec 2023

External IDs

unpaywall 10.1080/10298436.2023.2177650
Scopus 85150911612
Mendeley 27a7ae74-0e43-3c13-ae28-def2fe201b74
WOS 000952736100001



  • Convolutional neural networks, asphalt concrete, dynamic modulus, machine learning, phase angle, stochastic metamodelling, Phase angle, Asphalt concrete, Machine learning, Dynamic modulus, Stochastic metamodelling