Machine Learning for Pavement Friction Prediction Using Scikit-Learn

  • Pedro MarcelinoEmail author
  • Maria de Lurdes Antunes
  • Eduardo Fortunato
  • Marta Castilho Gomes
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10423)


During the last decades, the advent of Artificial Intelligence (AI) has been taking place in several technical and scientific areas. Despite its success, AI applications to solve real-life problems in pavement engineering are far from reaching its potential. In this paper, a Python machine learning library, scikit-learn, is used to predict asphalt pavement friction. Using data from the Long-Term Pavement Performance (LTPP) database, 113 different sections of asphalt concrete pavement, spread all over the United States, were selected. Two machine learning models were built from these data to predict friction, one based on linear regression and the other on regularized regression with lasso. Both models showed to be feasible and perform similarly. According to the results, initial friction plays an essential role in the way friction evolves over time. The results of this study also showed that scikit-learn can be a versatile tool to solve pavement engineering problems. By applying machine learning methods to predict asphalt pavements friction, this paper emphasizes how theory and practice can be effectively coupled to solve real-life problems in contemporary transportation.


Machine learning Pavement engineering Friction prediction Scikit-learn Python 


  1. 1.
    Wallman, C.G., Åström, H.: Friction Measurement Methods and the Correlation Between Road Friction and Traffic Safety. VTI, Sweden (2001)Google Scholar
  2. 2.
    Hastie, T., Tibshirani, R., Friedman, J.J.H.: The Elements of Statistical Learning. Springer, Heidelberg (2001)CrossRefzbMATHGoogle Scholar
  3. 3.
    Murphy, K.: Machine Learning: A Probabilistic Perspective. MIT Press, Cambridge (2012)zbMATHGoogle Scholar
  4. 4.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, É.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Seabold, S., Perktold, J.: Statsmodels: econometric and statistical modeling with python. In: Proceedings of the 9th Python in Science Conference, vol. 57, Austin (2010)Google Scholar
  6. 6.
    Van der Walt, S., Colbert, S.C., Varoquaux, G.: The numpy array: a structure for efficient numerical computation. Comput. Sci. Eng. 13, 22–30 (2011)CrossRefGoogle Scholar
  7. 7.
    Hunter, J.D.: Matplotlib: a 2D graphics environment. Comput. Sci. Eng. 9, 90–95 (2007)CrossRefGoogle Scholar
  8. 8.
    McKinney, W.: Python for Data Analysis. O’Reilly, Springfield (2012)Google Scholar
  9. 9.
    Kane, M., Scharnigg, K.: D10: report on different parameters influencing skid resistance, rolling resistance and noise emissions. Technical report, TYROSAFE project (2009)Google Scholar
  10. 10.
    Henry, J.J.: Evaluation of pavement friction characteristics a synthesis of highway practice. In: NCHRP synthesis 291. Transportation Research Board (2000)Google Scholar
  11. 11.
    Wilson, D.J.: The effect of rainfall and contaminants on road pavement skid resistance. Research report, New Zealand Transport Agency (2013)Google Scholar
  12. 12.
    Cenek, P.D., Alabaster, D.J., Davies, R.B.: Seasonal and weather normalisation of skid resistance measurements. Research report, Transfund New Zealand (1999)Google Scholar
  13. 13.
    Chen, X., Dai, S., Guo, Y., Yang, J., Huang, X.: Polishing of asphalt pavements: from macro- to micro-scale. J. Test. Eval. 44(2), 882–894 (2015)Google Scholar
  14. 14.
    Long-Term Pavement Performance (LTPP) Database. LTPP InfoPave (2017). Accessed Feb 2017
  15. 15.
    Standard, A.S.T.M.: Standard test method for skid resistance of paved surfaces using a full-scale tire. ASTM International, West Conshohocken (2009)Google Scholar
  16. 16.
    Titus-Glover, L., Tayabji, S.D.: Assessment of LTPP friction data. Technical report, Federal Highway Administration (1999)Google Scholar
  17. 17.
    Rada, G.: SHRP-LTPP monitoring data: five-year report. Technical report, Strategic Highway Research Program (1994)Google Scholar
  18. 18.
    Hall, J.W., Smith, K.L., Titus-Glover, L.: Guide for pavement friction. Technical report, Transportation Research Board (2009)Google Scholar
  19. 19.
    Ahammed, M.A., Tighe, S.L.: Early-Life, long-term, and seasonal variations in skid resistance in flexible and rigid pavements. Trans. Res. Rec. 2094(1), 112–120 (2009)CrossRefGoogle Scholar
  20. 20.
    Saito, K., Henry, J.J.: Mechanistic model for predicting seasonal variations in skid resistance. Trans. Res. Rec. 946, 29–37 (1983)Google Scholar
  21. 21.
    Fuentes, L., Asce, M., Gunaratne, M., Hess, D.: Evaluation of the effect of pavement roughness on skid resistance. J. Trans. Eng. 136(7), 640–653 (2010)CrossRefGoogle Scholar
  22. 22.
    Hair, J.F., Black, W.C., Babin, B.J., Anderson, R.E.: Multivariate Data Analysis. Pearson, London (2014)Google Scholar
  23. 23.
    Stone, M.: Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. 36(2), 111–147 (1974)MathSciNetzbMATHGoogle Scholar
  24. 24.
    Krstajic, D., Buturovic, L.J., Leahy, D.E., Thomas, S.: Cross-validation pitfalls when selecting and assessing regression and classification models. J. Chem. Inf. 6(10), 1–15 (2014)Google Scholar
  25. 25.
    Varma, S., Simon, R.: Bias in error estimation when using cross-validation for model selection. BMC Bioinf. 7, 1–8 (2006)CrossRefGoogle Scholar
  26. 26.
    Harrell, F.E.: Regression Modeling Strategies. Springer, Heidelberg (2015)CrossRefzbMATHGoogle Scholar
  27. 27.
    Flintsch, G., McGhee, K., Izeppi, E.L., Najafi, S.: The Little Book of Tire Pavement Friction. Pavement Surface Properties Consortium (2012)Google Scholar
  28. 28.
    Song, W., Chen, X., Smith, T., Hedfi, A.: Investigation of hot mix asphalt surfaced pavements skid resistance in Maryland state highway network system. In: TRB 85th Annual Meeting (2006)Google Scholar
  29. 29.
    Ahammed, M.A., Tighe, S.L.: Effect of short-term and long-term weather on pavement surface friction. Int. J. Pavement Res. Technol. 3(6), 295–302 (2010)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Pedro Marcelino
    • 1
    Email author
  • Maria de Lurdes Antunes
    • 1
  • Eduardo Fortunato
    • 1
  • Marta Castilho Gomes
    • 2
  1. 1.LNECLisbonPortugal
  2. 2.ISTLisbonPortugal

Personalised recommendations