Review on Machine Learning Techniques for Developing Pavement Performance Prediction Models

Road transportation has always been inherent in developing societies, impacting between 10–20% of Gross Domestic Product (GDP). It is responsible for personal mobility (access to services, goods, and leisure), and that is why world economies rely upon the efficient and safe functioning of transportation facilities. Road maintenance is vital since the need for maintenance increases as road infrastructure ages and is based on sustainability, meaning that spending money now saves much more in the future. Furthermore, road maintenance plays a significant role in road safety. However, pavement management is a challenging task because available budgets are limited. Road agencies need to set programming plans for the short term and the long term to select and schedule maintenance and rehabilitation operations. Pavement performance prediction models (PPPMs) are a crucial element in pavement management systems (PMSs), providing the prediction of distresses and, therefore, allowing active and efficient management. This work aims to review the modeling techniques that are commonly used in the development of these models. The pavement deterioration process is stochastic by nature. It requires complex deterministic or probabilistic modeling techniques, which will be presented here, as well as the advantages and disadvantages of each of them. Finally, conclusions will be drawn, and some guidelines to support the development of PPPMs will be proposed.

[1]  J. Ware.  Linear Models for the Analysis of Longitudinal Studies , 1985 .

[2]  Raymond K Moore,et al.  Roughness Level Probability Prediction Using Artificial Neural Networks , 1997 .

[3]  Sameer A. Abu-Eisheh,et al.  An Optimum Design Approach for Flexible Pavements , 2003 .

[4]  Samer Madanat,et al.  Estimation of infrastructure transition probabilities from condition rating data , 1995 .

[5]  Seosamh B. Costello,et al.  Derivation of Transition Probability Matrices for Pavement Deterioration Modeling , 2006 .

[6]  Adel W. Sadek,et al.  Deterioration Prediction Modeling of Virginia's Interstate Highway System , 1996 .

[7]  K. W..  Arizona Pavement Management System : Phase 2-- Verification of Performance Prediction Models and Development of Data Base , .

[8]  Han Ping Hong,et al.  Stochastic Modeling of Pavement Performance , 2003 .

[9]  Khaled A. Abaza.  Performance-Based Models for Flexible Pavement Structural Overlay Design , 2005 .

[10]  Khaled A. Abaza,et al.  Dynamic Probabilistic Approach for Long-Term Pavement Restoration Program with Added User Cost , 2007 .

[11]  S. Travis Waller,et al.  Prediction of Pavement Performance: Application of Support Vector Regression with Different Kernels , 2016 .

[12]  Moshe Ben-Akiva,et al.  Infrastructure management under uncertainty: Latent performance approach , 1993 .

[13]  Kamal Golabi,et al.  A Statewide Pavement Management System , 1982 .

[14]  KaurDevinder,et al.  Comparitive analysis of fuzzy decision tree and logistic regression methods for pavement treatment prediction , 2008 .

[15]  J. Ware,et al.  Random-effects models for longitudinal data. , 1982, Biometrics.

[16]  Pablo Luis Durango-Cohen,et al.  Estimation of infrastructure performance models using state-space specifications of time series models , 2007 .

[17]  Jidong Yang,et al.  Use of Recurrent Markov Chains for Modeling the Crack Performance of Flexible Pavements , 2005 .

[18]  Khaled A. Abaza,et al.  Predicting Remaining Strength of Flexible Pavement and Overlay Design Thickness with Stochastic Modeling , 2009 .

[19]  Keshavan Nair,et al.  BAYESIAN METHODOLOGY FOR VERIFYING RECOMMENDATIONS TO MINIMIZE ASPHALT PAVEMENT DISTRESS , 1979 .

[20]  António Pais Antunes,et al.  A Segment-linked Optimization Model for Deterministic Pavement Management Systems , 2002 .

[21]  Samer Madanat,et al.  INCREMENTAL NONLINEAR MODEL FOR PREDICTING PAVEMENT SERVICEABILITY , 2003 .

[22]  M A Karan,et al.  DETERMINING INVESTMENT PRIORITIES FOR URBAN PAVEMENT IMPROVEMENTS , 1976 .

[23]  Khaled A. Abaza.  Stochastic Approach for Design of Flexible Pavement , 2011 .

[24]  Yu Liu,et al.  Predictive analytics using a nonhomogeneous semi-Markov model and inspection data , 2015 .

[25]  Tristan Lorino,et al.  Modeling the Road Degradation Process: Non-linear Mixed Effects Models for Correlation and Heteroscedasticity of Pavement Longitudinal Data , 2012 .

[26]  Moshe Ben-Akiva,et al.  Modeling Infrastructure Performance and User Costs , 1995 .

[27]  Haricharan Pulugurta,et al.  Pavement condition prediction using Markov process , 2009 .

[28]  Pablo Luis Durango-Cohen,et al.  A time series analysis framework for transportation infrastructure management , 2007 .

[29]  Samer Madanat,et al.  Statistical Model of Pavement Rutting in Asphalt Concrete Mixes , 2001 .

[30]  Samer Madanat,et al.  Computation of Infrastructure Transition Probabilities using Stochastic Duration Models , 2002 .

[31]  Donath Mrawira,et al.  Bayesian Regression in Pavement Deterioration Modeling: Revisiting the AASHO Road Test Rut Depth Model , 2011 .

[32]  Samuel H Carpenter,et al.  PAVEMENT PERFORMANCE PREDICTION MODEL USING THE MARKOV PROCESS , 1987 .

[33]  Karim Chatti,et al.  Effect of design and site factors on fatigue cracking of new flexible pavements in the LTPP SPS-1 experiment , 2009 .

[34]  Kelvin C. P. Wang,et al.  Probabilistic Behavior of Pavements , 1994 .

[35]  Amir Mosavi,et al.  Prediction of remaining service life of pavement using an optimized support vector machine (case study of Semnan–Firuzkuh road) , 2019, Engineering Applications of Computational Fluid Mechanics.

[36]  John P Zaniewski,et al.  Expert Project Recommendation Procedure for Arizona Department of Transportation’s Pavement Management System , 1997 .