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.

[1]  Jouko Lampinen,et al.  Bayesian approach for neural networks--review and case studies , 2001, Neural Networks.

[2]  A. Agresti.  An introduction to categorical data analysis , 1997 .

[3]  K. Ksaibati,et al.  A comprehensive approach for quantifying environmental costs associated with unpaved roads dust , 2017 .

[4]  Khaled Ksaibati,et al.  An optimisation tool to select gravel roads for dust chemical treatment projects using genetic algorithms , 2018, International Journal of Pavement Engineering.

[5]  Paola Bandini,et al.  Prediction of Pavement Performance through Neuro‐Fuzzy Reasoning , 2010, Comput. Aided Civ. Infrastructure Eng..

[6]  G J Giummarra,et al.  The Development of Gravel Deterioration Models for Adoption in a New Zealand Gravel Road Management System , 2008 .

[7]  Thomas G. Sanders,et al.  Relative effectiveness of road dust suppressants , 1997 .

[8]  Keith Linard.  A system dynamics modelling approach to gravel road maintenance management , 2010 .

[9]  Khaled Ksaibati,et al.  Improvement Recommendations for Unsealed Gravel Roads , 2011 .

[10]  Sunanda Dissanayake,et al.  Factors Affecting Crash Severity on Gravel Roads , 2009 .

[11]  Dave Winkler,et al.  Bayesian Regularization of Neural Networks , 2009, Artificial Neural Networks.

[12]  Lalit Mohan Saini,et al.  Peak load forecasting using Bayesian regularization, Resilient and adaptive backpropagation learning based artificial neural networks , 2008 .

[13]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[14]  Yuhui Qiu,et al.  Novel Approach for Promoting the Generalization Ability of Neural Networks , 2008 .

[15]  Omar Albatayneh,et al.  Evaluation of static creep of FORTA-FI strengthened asphalt mixtures using experimental, statistical and feed-forward back-propagation ANN techniques , 2019, International Journal of Pavement Research and Technology.

[16]  Paulin Coulibaly,et al.  Groundwater level forecasting using artificial neural networks , 2005 .

[17]  Hayrettin Okut,et al.  Bayesian Regularized Neural Networks for Small n Big p Data , 2016 .

[18]  Anthony J. Jakeman,et al.  Artificial Intelligence techniques: An introduction to their use for modelling environmental systems , 2008, Math. Comput. Simul..

[19]  Khaled Ksaibati,et al.  Developing and validating an image processing algorithm for evaluating gravel road dust , 2019, International Journal of Pavement Research and Technology.

[20]  Mohamed Abdel-Aty,et al.  Using hierarchical Bayesian binary probit models to analyze crash injury severity on high speed facilities with real-time traffic data. , 2014, Accident; analysis and prevention.

[21]  John A. Gillies,et al.  Vehicle-based road dust emission measurement (III):: effect of speed, traffic volume, location, and season on PM10 road dust emissions in the Treasure Valley, ID , 2003 .

[22]  Guillermo Thenoux,et al.  Development of a Methodology for Measurement of Vehicle Dust Generation on Unpaved Roads , 2007 .

[23]  Robert A Eaton,et al.  UNSURFACED ROAD MAINTENANCE MANAGEMENT , 1992 .

[24]  D. Hensher,et al.  A mixed generalized ordered response model for examining pedestrian and bicyclist injury severity level in traffic crashes. , 2008, Accident; analysis and prevention.

[25]  Mohamed Ahmed,et al.  Complementary parametric probit regression and nonparametric classification tree modeling approaches to analyze factors affecting severity of work zone weather-related crashes , 2019 .

[26]  Dogan Ibrahim,et al.  An Overview of Soft Computing , 2016 .

[27]  Richard Tay,et al.  A random parameters probit model of urban and rural intersection crashes. , 2015, Accident; analysis and prevention.

[28]  Shamsunnahar Yasmin,et al.  Analyzing Continuum of Fatal Crashes: Generalized Ordered Approach , 2015 .

[29]  Toshiyuki Yamamoto,et al.  Underreporting in traffic accident data, bias in parameters and the structure of injury severity models. , 2008, Accident; analysis and prevention.

[30]  Khaled Ksaibati,et al.  Developing performance models for treated gravel roads to evaluate the cost-effectiveness of using dust chemical treatments , 2019 .