Data-Driven Estimation of Rheological Behavior of Asphalt Mixture Using the K-Nearest Neighbors Algorithm

Document Type : Research Paper

Authors

1 Assistant Professor, Faculty of Civil Engineering, K. N. Toosi University of Technology, Tehran, I. R. Iran.

2 Qom Municipality, Qom, I. R. Iran.

Abstract

Dynamic modulus (|E*|) and phase angle (φ) are key parameters for describing the viscoelastic performance of asphalt mixtures. However, their experimental evaluation involves lengthy testing and costly laboratory procedures. To overcome these limitations, several predictive models have been introduced, among which the Witczak and Hirsch models are the most recognized. In recent years, machine learning (ML) techniques have gained attention in engineering applications due to their strong capabilities in data analysis, optimization, and prediction. This study introduces the K-Nearest Neighbors (KNN) algorithm as an ML-based method to estimate the viscoelastic behavior of asphalt mixtures. The model was trained and validated using an extensive dataset comprising bitumen characteristics, volumetric parameters, and measured values of dynamic modulus and phase angle at various temperatures and loading frequencies, totaling over 5500 data points. The results demonstrate that the proposed ML model provides high prediction accuracy and represents a promising alternative for estimating the viscoelastic properties of asphalt mixtures.

Keywords

Main Subjects

References

Abu Abdo, A., Bayomy, F., Nielsen, R., Weaver, T. and Jung, S. J. 2009. “Prediction of the dynamic modulus of Superpave mixes”. Proc. 8th Int. Conf. Bearing Capacity Roads, Railways, Airfields, 305–314. DOI: 10.1201/9780203865286.ch33
Ahmed, M. S., N’diaye, M., Attouch, M. K., et al. 2023. “K-nearest neighbors prediction and classification for spatial data”. J. Spat. Econom., 4: 12. https://doi.org/10.1007/s43071-023-00041-2
Aksoy, A., Iskender, E. and Kahraman, H. T. 2012. “Application of the intuitive KNN estimator for prediction of the Marshall test (ASTM D1559) results for asphalt mixtures”. Constr. Build. Mater. 34: 561–569. https://doi.org/10.1016/j.conbuildmat.2012.02.091
Al-Dosary, N. M. N., Al-Hamed, S. A. and Aboukarima, A. M. 2019. “K-nearest neighbors method for prediction of fuel consumption in tractor–chisel plow systems”. Eng. Agric., 39(6): 729-736. https://doi.org/10.1590/1809-4430-Eng.Agric.v39n6p729-736/2019
Al-Khateeb, G., Shenoy, A., Gibson, N. and Harman, T. 2006. “A new simplistic model for dynamic modulus predictions of asphalt paving mixtures”. J. Assoc. Asphalt Paving Technol., 75: 1254–1293. https://doi.org/10.1016/j.cscm.2022.e01580
Alnaqbi, A., Zeiada, W. and Al-Khateeb, G. G. 2024. “Machine learning modeling of pavement performance and IRI prediction in flexible pavement”. Innov. Infrastruct. Solut., 9: 385. https://doi.org/10.1007 /s41062-024-01688-y
Andrei, D., Mirza, W. and Witczak, M. W. 1999. “Development of a revised predictive model for the dynamic (complex) modulus of asphalt mixtures”. NCHRP Rep. 1-37A. https://doi.org/10.4236/ojce.202 0.103018
Atakan, M.  and Yıldız, K. 2023. “Prediction of Marshall design parameters of asphalt mixtures via machine learning algorithms based on literature data”. Road Mater. Pavement Design, 25(3): 454–473. https://doi.org/10.1080/14680629.2023.2213774
Bajic, M., Pour, S. M., Skar, A., Pettinari, M., Levenberg, E. and Alstrøm, T. S. 2021. “Road roughness estimation using machine learning”. arXiv preprint arXiv:2107.01199. https://doi.org/10.48550/arXiv.2 107.01199
Bari, J. and Witczak, M. W. 2006. “Development of a new revised version of the Witczak E* predictive model for hot mix asphalt mixtures”. J. Assoc. Asphalt Paving Technol., 75: 381–424. https://doi.org/10.1016/j.conbuildmat.2014.11.011
Behnood, A. and Mohammadi Golafshani, E. 2021. “Predicting the dynamic modulus of asphalt mixture using machine learning techniques”. Constr. Build. Mater., 266 (Part A): 120983. https://doi.org/10.1016 /j.conbuildmat.2020.120983
Beskopylny, A. N., Stelmakh, S. A., Shcherban, E. M., Mailyan, L. R., Meskhi, B., Razveeva, I., Chernilnik, A. and Beskopylny. N. 2022. “Concrete strength prediction using machine learning methods”. Appl. Sci., 12: 10864. https://doi.org/10.3390/app122110864
Biligiri, K. P., Kaloush, K. and Uzan, J. 2010. “Evaluation of asphalt mixtures’ viscoelastic properties using phase angle relationships”. Int. J. Pavement Eng., 11(2): 143–152. https://doi.org/10.1080/102984309030 33354
Birgisson, B., Roque, R., Kim, J. and Pham, L. V. 2004. “The use of complex modulus to characterize the performance of asphalt mixtures and pavements in Florida”. University of Florida. https://doi.org/10.1080/14680629.2018.1441065?urlappend=%3Futm_source%3Dresearchgate.net%26medium%3Darticle
Botella, R., Lo Presti, D., Vasconcelos, K., et al. 2022. “Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement”. Mater. Struct., 55: 112. https://doi.org/10.1617 /s11527-022-01933-9
Chaabene, W. B., Flah, M. and Nehdi, M. L. 2020. “Machine learning prediction of mechanical properties of concrete”. Constr. Build. Mater., 260: 119889. https://doi.org/10.1016/j.conbuildmat.2020.119889
Christensen, D. W., Pellinen, T. and Bonaquist, R. F. 2003. “Hirsch model for estimating the modulus of asphalt concrete”. J. Assoc. Asphalt Paving Technol., 72: 97–121. https://doi.org/10.1061/(ASCE)MT.19 43-5533.0002099
Choi, H. J. , Kim, S., Kim, Y. and Won, J. 2022. “Predicting frost depth of soils in South Korea using machine learning”. Sustain., 14: 9767. https://doi.org/10.3390/su14159767
Dhar, V. and Stein, R. 1997. “Intelligent decision support methods”. Prentice-Hall, Upper Saddle River, N. J. https://doi.org/10.1007/978-1-4615-1147-2_7
Flintsch, G., Loulizi, A., Diefenderfer, S. D., Galal, K. A. and Diefenderfer, B. K. 2007. “Asphalt materials characterization in support of M-E PDG implementation”. Rep. VTRC 07-CR10, Virginia Tech. https://doi.org/10.3141/2057-14

Ghorbani, B., Yaghoubi, E., Wasantha, P. L. P., van Staden, R., Guerrieri, M. and Fragomeni, S. 2023. “Machine learning-based prediction of resilient modulus for blends of tire-derived aggregates and demolition wastes”. Road Mater. Pavement Design, 25(4): 694–715. https://doi.org/10.1080/14680629. 2023.2222176

Gul, M. A., Islam, M. K., Awan, H. H., et al. 2022. “Prediction of Marshall stability and Marshall flow using ML”. Symmetry, 14: 2324. https://doi.org/10.3390/sym14112324
Huang, Y., Molavi Nojumi, M., Ansari, S., Hashemian, L. and Bayat, A. 2023. “Evaluating the use of ML for moisture content prediction”. Road Mater. Pavement Design, 24(12): 2910–2928. https://doi.org/10.108 0 /14680629.2023.2182135
Justo-Silva, R., Ferreira, A. and Flintsch, G. 2021. “Review on ML techniques for pavement performance”. Sustain., 13: 5248. https://doi.org/10.3390/su13095248
Khambra, G. and Shukla, P. 2021. “Novel ML applications on fly ash-based concrete”. Mater. Today Proc., 80: 6245. https://doi.org/10.1016/j.matpr.2021.07.262
Leiva-Villacorta, F. and Vargas-Nordcbeck, A. 2019. “Neural network-based model to estimate dynamic modulus E*”. J. Soft Comput. Civ. Eng., 3(2): 1–15. https://doi.org/10.1016/j.jrmge.2019.03.005
Majidifard, H., Jahangiri, B., Buttlar, W. G. and Alavi, A. H. 2019. “New ML-based prediction models for fracture energy”. Measurement, 135: 438–451. https://doi.org/10.1016/j.measurement.2018.11.081
Martínez, F. and Angelone, S. 2010. “The estimation of the dynamic modulus using ANN”. 11th Int. Conf. Asphalt Pavements, Vol. 1, 354–363. https://doi.org/10.1016/j.conbuildmat.2020.119912
Naik, A. K. and Biligiri, K. P. 2014. “Predictive models to estimate phase angle”. J. Mater. Civ. Eng., 27(8). https://doi.org/10.1061/(ASCE)MT.1943-5533.0001197
Picado-Santos, L., Capitao, S. D. and Pais, J. C. 2003. “Stiffness modulus and phase angle prediction models for high modulus bituminous mixtures”. Int. J. Pavements, 2(3). https://doi.org/10.1016/j.conbuildmat .2018.09.160
Rahman, S., Bhasin, A. and Smit, A. 2021. “Exploring ML to predict asphalt mixture performance”. Constr. Build. Mater., 295: 123585. https://doi.org/10.1016/j.conbuildmat.2021.123585
Rondinella, F., Daneluz, F., Baldo, N. and Hofko, B. 2023. “Improved predictions of asphalt concretes’ dynamic modulus”. Constr. Build. Mater., 400: 132709. https://doi.org/10.1016/j.conbuildmat.2023.13 2709
Rondinella, F., Daneluz, F., Hofko, B. and Baldo, N. 2024. “ML approach for simultaneous prediction of E* and phase angle”. Adv. Res. Technol. Inf. Innov. Sustain., 1935. https://doi.org/10.1007/978-3-031-48858-0_40
Seman, G., Shoop, S., McGrath, S. and Rollings, R. 2006. “Soil strength prediction with KNN”. Proc. 59th Can. Geotech. Conf. https://doi.org/10.1177/03611981241245679
Shu, X. and Huang, B. 2009. “Predicting dynamic modulus with differential method”. Road Mater. Pavement Design, 10(2): 337–359. https://doi.org/10.1061/(ASCE)MT.1943-5533.0001048
Singh, D., Zaman, M. and Commuri, S. 2011. “Evaluation of predictive models for estimating dynamic modulus”. Transp. Res. Record, 2210: 57–72. https://doi.org/10.3141/2210-07?urlappend=%3Futm_sou rce%3Dresearchgate.net%26medium%3Darticle

Suleymanov, A., Tuktarova, I., Belan, L., et al. 2023. “Spatial prediction of soil properties using random forest, k-nearest neighbors and cubist approaches in the foothills of the Ural Mountains, Russia”.  Model. Earth Syst. Environ., 9: 3461–3471. https://doi.org/10.1007/s40808-023-01723-4

Tangga, A. A., Al Mufargi, H., Milad, A., et al. 2024. “Utilising machine learning algorithms to predict the Marshall characteristics of asphalt pavement layers”. Innov. Infrastruct. Solut. 9: 381. https://doi.org/10.1007/s41062-024-01698-w
Tran, N. and Hall, K. 2005. “Evaluating the predictive equation for dynamic moduli”. J. Assoc. Asphalt Paving Technol., 74: 1–17. https://www.tandfonline.com/action/showCitFormats?doi=10.1080/10298436 .2020.1841191
Upadhya, A., Thakur, M. S. and Sihag, P. 2024. “Predicting Marshall stability of carbon fiber–reinforced asphalt concrete”. Int. J. Pavement Res. Technol., 17: 102–122. https://doi.org/10.1007/s42947-022-00223-5
Useche-Castelblanco, J. S., Reyes-Ortiz, O. J. and Alvarez, A. E. 2023. “Application of ML models for wax-modified asphalt binders”. Constr. Build. Mater., 395: 132352. https://doi.org/10.1016/j.conbuildmat.202 3.132352
Uwanuakwa, I. D., Busari, A., Ali, S. I. A., et al. 2022. “Comparing ML models with Witczak NCHRP 1-40D model”. Arab. J. Sci. Eng., 47: 13579–13591. https://doi.org/10.1007/s13369-022-06935-x
Venudharan, V. and Biligiri, K. P. 2015. “Estimation of phase angles using resilient modulus test”. Constr. Build. Mater., 82: 274–286. https://doi.org/10.1016/j.conbuildmat.2015.02.061
Weiss, S. M. and Kulikowski, C. A. 1991. “Computer systems that learn”. Morgan Kaufmann Publ., San Mateo, CA. https://doi.org/10.1016/S0957-4174(02)00026-X
Witczak, M. W. 2005. “NCHRP Proj. 9-19, Superpave support and performance models management”. Final Rep. https://doi.org/10.1051/matecconf/201712007003
Witczak, M. W. and Fonseca, O. A. 1996. “Revised predictive model for dynamic (complex) modulus”. Transp. Res. Record, 1540(1): 15–23. https://doi.org/10.1177/0361198196154000103
Yang, X. and You, Z. 2015. “New predictive equations for dynamic modulus and phase angle using nonlinear least-squares regression”. J. Mater. Civ. Eng., 27(3). https://doi.org/10.1061/(ASCE)MT.1943-5533.0001070
Zhang, C. and Shen, S. 2017. “Modification of the Hirsch dynamic modulus prediction model”. J. Mater. Civ. Eng., 29(12). https://doi.org/10.1061/(ASCE)MT.1943-5533.0002099
Journal of Transportation Infrastructure Engineering
Volume 11, Issue 3 - Serial Number 43
In Progress
November 2025
Pages 117-136

Files

History

  • Receive Date: 16 November 2025
  • Revise Date: 02 December 2025
  • Accept Date: 04 December 2025

Share

How to cite

Statistics