Prediction of asphalt rheological properties for paving and maintenance assistance using explainable machine learning
Loading...
Access rights
openAccess
CC BY
CC BY
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Date
2025-09-15
Department
Major/Subject
Mcode
Degree programme
Language
en
Pages
15
Series
Fuel, Volume 396
Abstract
Conventional frequency-temperature sweep tests for evaluating asphalt rheological properties are time-consuming and resource-intensive. The characterization efficiency can be significantly improved by establishing a robust predictive model that links rheological properties to chemical composition. To this end, this study investigates the correlation between asphalt's chemical and rheological properties and develops precise predictive models using machine learning techniques. The input features include eleven key functional groups measured by Fourier Transform Infrared Spectroscopy (FTIR), while the output variables are the complex modulus (|G*|) and phase angle (δ) from Dynamic Shear Rheometer (DSR). Five machine learning algorithms—multiple linear regression, support vector regression, artificial neural network, random forest, and eXtreme gradient boosting (XGBoost)—were utilized to construct the predictive models. A Bayesian optimization strategy was employed to fine-tune their hyperparameters. Laboratory findings revealed that a strong correlation was identified between changes in these functional groups, especially oxygen-containing functional groups, and the |G*| and δ values of asphalt binders. The optimized XGBoost model achieved exceptional predictive accuracy, with R2 values of 0.9998 for |G*| and 0.9999 for δ. Additionally, SHapley Additive exPlanations (SHAP) values were used to elucidate the underlying principles of the predictions. By leveraging FTIR data and rheological indicators, this work provides a novel data-driven approach to accurately estimate asphalt binder behaviour, reducing experimental effort while ensuring reliable performance evaluation.Description
Publisher Copyright: © 2025 The Author(s)
Keywords
Asphalt binders, Chemical composition, Explainable machine learning, Rheological properties, SHAP
Other note
Citation
Zhang, F, Cannone Falchetto, A, Wang, D, Li, Z, Sun, Y & Lin, W 2025, ' Prediction of asphalt rheological properties for paving and maintenance assistance using explainable machine learning ', Fuel, vol. 396, 135319 . https://doi.org/10.1016/j.fuel.2025.135319