Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Complementary Modeling of Gravel Road Traffic-Generated Dust Levels Using Bayesian Regularization Feedforward Neural Networks and Binary Probit Regression


Gravel roads require extensive maintenance and rehabilitation. That is because of the dynamic behavior of gravel road conditions. This study is aimed at investigating road condition factors affecting the traffic-generated dust on gravel roads. The study concerns Laramie County, Wyoming. The parametric binary probit regression structure and the non-parametric Bayesian regularization artificial neural network (BRANN) methods were implemented to model traffic-generated dust levels as a function of the factors that contribute to dust generation. The BRANNs method simplifies the model building process by precluding irrelevant and redundant weights of artificial neural networks (ANNs). In this study, the BRANN method is utilized with one single hidden layer using the MATLAB® function for neural networks. In the hidden layer, multiple neuron counts ranging from three to thirty were attempted. The parametric and non-parametric techniques mentioned were adopted to provide comprehensive insights into important factors that contribute to dust generation. Therefore, both techniques complement each other. A total of 206 gravel road segments were used for model building for both analyses. As per the results of the BRANN model, it was found that twenty neurons produced the most accurate results. Furthermore, it was found that the BRANN model had more variables than the binary probit regression model, whereas the probit model provided general insights into the factors affecting the dust on gravel roads such as average travel speed and soil type. Also, it would be an easy-to-use method to assist local agencies and DOT practitioners in addressing the dust problems on gravel roads.

This is a preview of subscription content, log in to check access.


  1. [1]

    O. Albatayneh, L. Forslöf, K. Ksaibati, Developing and validating an image processing algorithm for evaluating gravel road dust, Inter. J. Pavement Res. Technol. 12 (3) (2019) 288–296.

  2. [2]

    T. Henning, G. J. Giummarra, D. C. Roux, The development of gravel deterioration models for adoption in a New Zealand gravel road management system, Wellington, N.Z.: Land Transport New Zealand, No. 332, 2008, p. 1–96.

  3. [3]

    K. Linard, A system dynamics modelling approach to gravel road maintenance management, In ARRB Conference, ARRB Group Ltd. Melbourne, Australia, 2010.

  4. [4]

    K. T. Linard, Application of System Dynamics to Unsealed Pavement Maintenance, In International Conference on Systems Thinking in Management, Melbourne, Australia, 2008.

  5. [5]

    Federal Highway Administration (FHWA), Highway Statistics 2012, Washington, DC, USA 2012.

  6. [6]

    Federal Highway Administration (FHWA), Highway Statistics 2012, Washington, DC, USA, 2018.

  7. [7]

    W. Aleadelat, K. Ksaibati, A comprehensive approach for quantifying environmental costs associated with unpaved roads dust, J. Environ. Econom. Policy 7 (2) (2018) 130–144.

  8. [8]

    W. Aleadelat, K. Ksaibati, O. Albatayneh, An optimisation tool to select gravel roads for dust chemical treatment projects using genetic algorithms, Inter. J. Pavement Eng. (2018) 1–11

  9. [9]

    M. A. Okok, P. Saha, K. Ksaibati, Developing performance models for treated gravel roads to evaluate the cost-effectiveness of using dust chemical treatments, Inter. J. Pavement Eng. 20 (4) (2019) 393–401.

  10. [10]

    G. Huntington, K. Ksaibati, (2011). Improvement recommendations for unsealed gravel roads. Transportation Research Record, 2205(1), 165–172.

  11. [11]

    D. Ibrahim, An overview of soft computing, Proc. Computer Sci. 102(2016)34–38.

  12. [12]

    M. A. Khasawneh, M.M. Taamneh, O. Albatayneh, Inter. J. Pavement Res. Technol. 12 (1) (2019) 43–53.

  13. [13]

    A. Bianchini, P. Bandini, Prediction of pavement performance through neuro-fuzzy reasoning, Computer-Aided Civ. Infras. Eng. 25 (1) (2010) 39–54.

  14. [14]

    G. Bosurgi, G. W. Flintsch, F. Trifirò, Artificial Neural Network Applications in Transportation Infrastructure Asset Management. In 2nd SIIV International Congress: new technologies and modeling tools for roadsapplications to design and management, Florence, Italy, 2004, pp. 27–29.

  15. [15]

    S. H. Chen, A. J. Jakeman, J. P. Norton, Artificial intelligence techniques: an introduction to their use for modelling environmental systems, Math. Computers Simulation 78 (2–3) (2008) 379–400.

  16. [16]

    A. S. Oladele, Pavement Monitoring and Performance Assessment of Gravel Road Networks for Optimal Maintenance Interventions in Botswana, 2017.

  17. [17]

    K. Linard, A system dynamics modelling approach to gravel road maintenance management, In ARRB Conference, ARRB Group Ltd., Melbourne, Australia, 2010.

  18. [18]

    G. T. Rohde, M. G. Henderson, A. Van Der Gryp, An Integrated Paved and Gravel Road Fund Allocation Methodology, International Convention Centre (ICC), CSIR Transportek, Durban, South Africa, Volume 4, 1998.

  19. [19]

    J. Lampinen, A. Vehtari, Bayesian approach for neural networks—review and case studies, Neural Networks 14 (3) (2001) 257–274.

  20. [20]

    T. Yamamoto, J. Hashiji, V. N. Shankar, Underreporting in traffic accident data, bias in parameters and the structure of injury severity models, Accident Analysis Prevention 40 (4) (2008) 1320–1329.

  21. [21]

    R. Yu, M. Abdel-Aty, Using hierarchical Bayesian binary probit models to analyze crash injury severity on high speed facilities with real-time traffic data, Accident Analysis Prevention 62 (2014) 161–167.

  22. [22]

    R. Tay, A random parameters probit model of urban and rural intersection crashes, Accident Analysis Prevention 84 (2015) 38–40.

  23. [23]

    L. Liu, S. Dissanayake, Factors affecting crash severity on gravel roads, J. Transp. Safety Security 1 (4) (2009) 254–267.

  24. [24]

    Department of the Army, Unsurfaced Road Maintenance Management. Technical Manual Number 5–626. Department of the Army, Washington, D.C., USA, 1995.

  25. [25]

    B. Das, K. Sobhan, Classification of Soil, In Principles of Geotechnical Engineering Eight Edition, Cengage Learning, Stamford, Connecticut, USA, 2012, p. 123–145.

  26. [26]

    D. Walker, L. Entine, S. Kummer, Pavement Surface Evaluation Rating Manual - Gravel Roads. Wisconsin Transportation Information Center, University of Wisconsin-Madison, Madison, Wisconsin, USA, 2002.

  27. [27]

    A. Agresti, An introduction to categorical data analysis, John Wiley & Sons, Inc., Hoboken, New Jersey, USA, 2018.

  28. [28]

    N. Eluru, C. Bhat, D. Hensher, A Mxed Generalized Ordered Response Model for Examining Pedestrian and Bicyclist Injury Severity Level in Traffic Crashes, Accident Analysis Prevention 40 (3) (2008) 1033–1054.

  29. [29]

    S. Yasmin, N. Eluru, A. Pinjari, Analyzing the Continuum of Fatal Crashes: A Generalized Ordered Approach, Anal. Methods Accident Res. 7 (2015) 1–15.

  30. [30]

    S. Jackman, Models for ordered outcomes, Politic. Sci. C 200 (2000) 1–20.

  31. [31]

    A. Ghasemzadeh, M. M. Ahmed, Complementary parametric probit regression and nonparametric classification tree modeling approaches to analyze factors affecting severity of work zone weather-related crashes, J. Modern Transp. 27 (2) (2019) 1–12.

  32. [32]

    M. T. Hagan, M. B. Menhaj, Training feedforward networks with the Marquardt algorithm, IEEE transactions on Neural Networks, 5 (6) (1994) 989–993.

  33. [33]

    L. M. Saini, Peak load forecasting using Bayesian regularization, Resilient and adaptive backpropagation learning based artificial neural networks, Elec. Power Syst. Res. 78 (7) (2008) 1302–1310.

  34. [34]

    I. N. Daliakopoulos, P. Coulibaly, I. K. Tsanis, Groundwater level forecasting using artificial neural networks, J. Hydrol. 309 (1–4) (2005) 229–240.

  35. [35]

    N. Feng, F. Wang, Y. Qiu, Novel approach for promoting the generalization ability of neural networks, Inter. J. Signal Process. 2(2) (2006) 2789–2793.

  36. [36]

    H. Okut, Bayesian regularized neural networks for small n big p data, In Artificial Neural Networks-Models and Applications, IntechOpen, 2016

  37. [37]

    H. J. Wang, F. Ji, C. S. Leung, P. F. Sum, Regularization parameter selection for faulty neural networks, Inter. J. Intelligent Syst. Technol. 4 (1) (2009) 45–48.

  38. [38]

    F. Burden, D. Winkler, Bayesian regularization of neural networks. In Artificial neural networks, Humana Press, Totowa, New Jersey, USA, 2008, p. 23–42.

  39. [39]

    V. Etyemezian, H. Kuhns, J. Gillies, J. Chow, K. Hendrickson, Vehicle-based road dust emission measurement ( III ): effect of speed, traffic volume, location, and season on PM 10 road dust emissions in the Treasure Valley, ID, Atmospheric Environ. 37 (32) (2003) 4583–4593.

  40. [40]

    G. Thenoux, J. P. Bellolio, F. Halles, Development of a Methodology for Measurement of Vehicle Dust Generation on Unpaved Roads, Transp. Res. Rec. 1989 (1) (2007) 299–304.

  41. [41]

    Sanders, G. Thomas, J. Addo, A. Ariniello, F. H. Heiden, Relative Effectiveness of Road Dust Suppressants, J. Transpor 4 (40) (1997) 393–397.

Download references


The authors gratefully acknowledge the generous financial support from the Mountain-Plains Consortium (MPC) for this study. All opinions, finding and results are solely those of the authors.

Author information

Correspondence to Omar Albatayneh.

Additional information

Peer review under responsibility of Chinese Society of Pavement Engineering.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Albatayneh, O., Moomen, M., Farid, A. et al. Complementary Modeling of Gravel Road Traffic-Generated Dust Levels Using Bayesian Regularization Feedforward Neural Networks and Binary Probit Regression. Int. J. Pavement Res. Technol. (2020).

Download citation


  • Gravel roads
  • Dust control
  • Artificial neural networks
  • Logistic regression