Exploring generic fractions of multi-origin asphalts and revisiting the linkage to their bulk properties via machine learning

Abstract

Significant efforts have been made to investigate the relationship between generic fractions and bulk properties of asphalt, as the most used binder in road pavement engineering. However, due to limited data availability, advanced data mining techniques, such as machine learning (ML), have rarely been applied in the field. This study aimed to collect extensive data on asphalt generic fractions and bulk properties and to explore their underlying linkage using ML methods. A total of 800 datasets for asphalt fractions of the saturate, aromatic, resin, and asphaltene (SARA) were collected and analyzed across various asphalt types. The generic fractions and derived indices were used as input variables in ML models to predict key asphalt properties, including penetration, softening point, rutting factor, and rotational viscosity. The contribution of different generic fractions, derived indices, and additional variables (e.g., asphalt type and geographical origin) to these properties was quantified using the SHapley Additive exPlanations (SHAP) technique. Among the ML models evaluated, adaptive boosting (AdaBoost) showed the best predictive performance, while the support vector machine demonstrated greater robustness. SHAP analysis revealed that penetration was primarily influenced by the proportions of asphaltenes and saturates, while asphaltene content and the asphaltenes index were the most significant predictors for other properties, such as softening point, rutting factor, and rotational viscosity. Including asphalt type and geographical origin as categorical variables in the models further improved prediction accuracy. This study highlights the potential of ML techniques in uncovering complex relationships between asphalt fractions and their bulk properties, surpassing conventional statistical approaches, though challenges remain.

Keywords

Paving asphalt / generic fractions / fraction-property linkage / machine learning / model interpretation

References

[1] Hu M,Li M,Cheng H.Revealing the aging-induced chemical and microstructure evolution of asphalt via AFM-IR and quantum chemistry simulation.Fuel2025;395:135218

[2] Abdul Jameel, A. G.; Van Oudenhoven, V.; Emwas, A.; Sarathy, S. M. Predicting octane number using nuclear magnetic resonance spectroscopy and artificial neural networks.Energy Fuels2018;32:6309-29

[3] Alvarez E,Trejo F,Ancheyta J.Pyrolysis kinetics of atmospheric residue and its SARA fractions.Fuel2011;90:3602-7

[4] Chakravarthy R,Savalia A.Determination of naphthenic acid number in petroleum crude oils and their fractions by mid-fourier transform infrared spectroscopy.Energy Fuels2016;30:8579-86

[5] Corbett LW.Composition of asphalt based on generic fractionation, using solvent deasphaltening, elution-adsorption chromatography, and densimetric characterization.Anal Chem1969;41:576-9

[6] Elbaz AM,Hourani N,Sarathy SM.TG/DTG, FT-ICR mass spectrometry, and NMR spectroscopy study of heavy fuel oil.Energy Fuels2015;29:7825-35

[7] Lesueur D.The colloidal structure of bitumen: consequences on the rheology and on the mechanisms of bitumen modification.Adv Colloid Interface Sci2009;145:42-82

[8] Loeber L,Morel J.Bitumen in colloid science: a chemical, structural and rheological approach.Fuel1998;77:1443-50

[9] Pfeiffer JP.Asphaltic bitumen as colloid system.J Phys Chem1940;44:139-49

[10] Hu M,Pahlavan F,Sun D.Toward sustainable non-emitting asphalts: understanding diffusion–adsorption mechanisms of hazardous organic compounds.Adv Sustain Syst2025;9:2400868

[11] Roja KL.Influence of chemical constituents of asphalt binders on their rheological properties.Transp Res Rec J Transp Res Board2019;2673:458-66

[12] Wang J,Wang R.Prediction of the fundamental viscoelasticity of asphalt mixtures using ML algorithms.Constr Build Mater2024;442:137573

[13] Hofko B,Füssl J.Impact of maltene and asphaltene fraction on mechanical behavior and microstructure of bitumen.Mater Struct2016;49:829-41

[14] Sakib N,Hure R,Bhasin A.Examining the relationship between bitumen polar fractions, rheological performance benchmarks, and tensile strength.J Mater Civ Eng2020;32:04020143

[15] Xu Y,Shan L.Effect of SARA on rheological properties of asphalt binders.J Mater Civ Eng2019;31:04019086

[16] Weigel S.Relationships between the chemistry and the physical properties of bitumen.Road Mater Pavement Des2018;19:1636-50

[17] Wang T,Hou X.Effects of SARA fractions on low temperature properties of asphalt binders.Road Mater Pavement Des2021;22:539-56

[18] Wang J,Hou X.Modelling of rheological and chemical properties of asphalt binder considering SARA fraction.Fuel2019;238:320-30

[19] Qu X,Li T.Understanding of asphalt chemistry based on the six-fraction method.Constr Build Mater2021;311:125241

[20] Li J,Hou X,Wang J.Determination of SARA fractions in asphalts by mid-infrared spectroscopy and multivariate calibration.Measurement2022;198:111361

[21] Gong M,Zhang J,Tong T.Physical–chemical properties of aged asphalt rejuvenated by bio-oil derived from biodiesel residue.Constr Build Mater2016;105:35-45

[22] Xiao X,Wang T,Xiao F.Linear visco-elasticity of asphalt in view of proportion and polarity of SARA fractions.Fuel2024;363:130955

[23] Kim M,Kim HB.Geometric mean based boosting algorithm with over-sampling to resolve data imbalance problem for bankruptcy prediction.Expert Syst Appl2015;42:1074-82

[24] Li Z,Glocker B.Overfitting of neural nets under class imbalance: analysis and improvements for segmentation. In: Shen D, Liu T, Peters TM, Staib LH, Essert C, Zhou S, Yap P, Khan A, editors. Medical Image Computing and Computer Assisted Intervention - MICCAI 2019. Cham: Springer International Publishing; 2019. pp. 402-10.

[25] Koushik A,Nezamuddin N.SHapley Additive exPlanations for explaining artificial neural network based mode choice models.Transp Dev Econ2024;10:200

[26] Yan T,Xia T.Relation between fault characteristic frequencies and local interpretability shapley additive explanations for continuous machine health monitoring.Eng Appl Artif Intell2024;136:109046

[27] Shan L,Wagner NJ,Liu Y.Microstructure of neat and SBS modified asphalt binder by small-angle neutron scattering.Fuel2019;253:1589-96

[28] Yen TF.The colloidal aspect of a macrostructure of petroleum asphalt.Fuel Sci Technol Int1992;10:723-33

[29] Barré L,Morisset A,Simon S.Relation between nanoscale structure of asphaltene aggregates and their macroscopic solution properties.Oil Gas Sci Technol Rev IFP2009;64:617-28

[30] Tan Y,Dan L,Meng A.Research progress of bitumen microstructures and components.J Traffic Transp Eng2020;20:1-17