Use of Bayesian Model Averaging to Estimate Model Uncertainty for Predicting Strain in a Four-Layered Flexible Pavement
Publication: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 7, Issue 1
Abstract
Because most of the numerical approaches are intensive in terms of computational effort and time, researchers have resorted to the use of surrogate models. For example, surrogate models for predicting the response of flexible pavement under given traffic and environmental conditions rely on the conventional approach of relating covariates with the response through simplified models. Usually, these covariates are chosen based on experience and data availability. Further, the form of the model is finalized based on statistical indicators and goodness-of-fit values. Thus, the concept of uncertainty in selecting the model is completely ignored, often leading to overconfident results and an increased risk in the prediction. Under these circumstances, Bayesian model averaging (BMA) could be a potential model building tool. The current study presents a BMA-based approach to choose influencing variables and quantify the uncertainty associated with linear regression models used to predict strain in a four-layered pavement structure. Initially, modulus and thickness of individual layers were used as input into a surrogate model building exercise. Out of 128 possible models, the best 100 models were used in conjunction with the BMA technique to rank various models and variables. Further, model uncertainty was represented by plotting the marginal density function of the coefficients, coefficient of variation, and normalized uncertainty range. BMA indicated that modulus (asphaltic layer and binder layer) and thickness of the asphaltic layer accounted for the majority of variability (up to 88%) associated with tensile strain in the asphaltic layer. Similarly, the thickness of the asphaltic layer and modulus of subgrade affected vertical compressive strain prediction models up to 38%. These variables also had lower uncertainty indicators when compared to other variables. Also, ranking based on the posterior inclusion probability can be used as an alternative for traditional sensitivity analysis.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
References
Ahirwar, S. K., and J. N. Mandal. 2017. “Finite element analysis of flexible pavement with geogrids.” Procedia Eng. 189 (Jan): 411–416. https://doi.org/10.1016/j.proeng.2017.05.065.
Alqadi, A. N., K. N. B. Mustapha, S. Naganathan, and Q. N. Al-Kadi. 2012. “Uses of central composite design and surface response to evaluate the influence of constituent materials on fresh and hardened properties of self-compacting concrete.” J. Civ. Eng. 16 (3): 407–416. https://doi.org/10.1007/s12205-012-1308-z.
Araujo, L. N. M., F. Costa, H. C. Jesus, and M. A. Bezerra. 2012. “Factorial and Doehlert designs in the optimization of a separation procedure using polyurethane foam as a solid phase extractant for platinum determination in ferrous matrices using inductively coupled plasma optical emission spectroscopy.” Anal. Methods 4 (2): 508–512. https://doi.org/10.1039/C2AY05672K.
Bezerra, M., and R. E. Santelli. 2008. “Response surface methodology (RSM) as a tool for optimization in analytical chemistry.” Talanta 76 (5): 965–977. https://doi.org/10.1016/j.talanta.2008.05.019.
Ceylan, H., and K. Gopalakrishnan. 2011. “Computationally efficient surrogate response models for mechanistic—Empirical pavement analysis and design.” Struct. Infrastruct. Eng. 7 (4): 297–306. https://doi.org/10.1080/15732470802550077.
Das, A., and B. B. Pandey. 1999. “Mechanistic-empirical design of bituminous roads: An Indian perspective.” J. Transp. Eng. 125 (5): 463–471. https://doi.org/10.1061/(ASCE)0733-947X(1999)125:5(463).
Dilip, D. M., and G. L. Sivakumar Babu. 2013. “Methodology for pavement design reliability and back analysis using markov chain monte carlo simulation.” J. Transp. Eng. 139 (1): 65–74. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000455.
Dilip, D. M., and G. L. S. Sivakumar Babu. 2016. “Methodology for global sensitivity analysis of flexible pavements in a Bayesian back-analysis framework.” J. Risk Uncertainty Eng. Syst. 2 (4): 04016002. https://doi.org/10.1061/AJRUA6.0000865.
Dong, J., and W. Whitt. 2015. “Using a birth-and-death process to estimate the steady-state distribution of a periodic queue.” Nav. Res. Logist. 62 (8): 664–685.
Duan, Q., N. K. Ajami, X. Gao, and S. Sorooshian. 2007. “Multi-model ensemble hydrologic prediction using Bayesian model averaging.” Adv. Water Resour. 30 (5): 1371–1386. https://doi.org/10.1016/j.advwatres.2006.11.014.
Fan, Y., G. W. Peters, and S. A. Sisson. 2009. “Automating and evaluating reversible jump MCMC proposal distributions.” Stat. Comput. 19 (4): 409–421. https://doi.org/10.1007/s11222-008-9101-z.
Fokoue, E., and Ly Vi 2014. Frequent approximation of the Bayesian posterior inclusion probability by stochastic subsampling. Rochester, NY: Rochester Institute of Technology.
Fragoso, T. M., W. Bertoli, and F. L. Neto. 2015. “Bayesian model averaging: A systematic review and conceptual classification.” Int. Stat. Rev. 86 (1): 1–28.
Hoeting, J. A., D. Madigan, A. E. Raftery, and C. T. Volinsky. 1999. “Bayesian model averaging: A tutorial.” Stat. Sci. 14 (4): 382–417.
Hong, F., and J. A. Prozzi. 2006. “Estimation of pavement performance deterioration using Bayesian approach.” J. Infrastruct. Syst. 12 (2): 77–86. https://doi.org/10.1061/(ASCE)1076-0342(2006)12:2(77).
Indian Roads Congress. 2018. Guidelines for the design of flexible pavements. New Delhi, India: Indian Roads Congress.
Johnson, V. E., R. O. Deaner, and P. Carel. 2002. “Bayesian analysis of rank data with application to primate intelligence experiments.” J. Am. Stat. Assoc. 97 (457): 8–17. https://doi.org/10.1198/016214502753479185.
Kabir, G., S. Tesfamariam, and R. Sadiq. 2015. “Bayesian model averaging for the prediction of water main failure for small to large Canadian municipalities.” Can. J. Civ. Eng. 43 (3): 233–240. https://doi.org/10.1139/cjce-2015-0374.
Li, G., and J. Shi. 2010. “Application of Bayesian model averaging in modeling long-term wind speed distributions.” Renew. Energy 35 (6): 1192–1202. https://doi.org/10.1016/j.renene.2009.09.003.
Liu, L., and N. G. Gharaibeh. 2014. “Bayesian model for predicting the performance of pavements treated with thin hot-mix asphalt overlays.” Transp. Res. Rec. 2431 (1): 33–41. https://doi.org/10.3141/2431-05.
Madigan, D., and A. E. Raftery. 1994. “Model selection and accounting for model uncertainty in graphical models using Occam’s window.” J. Am. Stat. Assoc. 89 (428): 1535–1546. https://doi.org/10.1080/01621459.1994.10476894.
Madigan, D., J. York, and D. Allard. 1995. “Bayesian graphical models for discrete.” Int. Stat. Rev. 63 (2): 215–232. https://doi.org/10.2307/1403615.
Maji, A., and A. Das. 2008. “Reliability considerations of bituminous pavement design by mechanistic—Empirical approach.” Int. J. Pavement Eng. 9 (1): 19–31. https://doi.org/10.1080/10298430600997240.
Montgomery, D. C. 1996. Introduction to statistical quality control, 3rd ed. New York: Wiley.
Park, E. S., R. E. Smith, T. J. Freeman, and C. H. Spiegelman. 2008. “A Bayesian approach for improved pavement performance prediction.” J. Appl. Stat. 35 (11): 1219–1238. https://doi.org/10.1080/02664760802318651.
Raftery, A. E., D. Madigan, and J. A. Hoeting. 1997. “Bayesian model averaging for linear regression models.” J. Am. Stat. Assoc. 92 (437): 179–191. https://doi.org/10.1080/01621459.1997.10473615.
Rema, A., and A. K. Swamy. 2017. “Investigation of sampling strategy on estimating strains in flexible pavements through response surface method (RSM).” In Proc., 10th Int. Conf. on the Bearing Capacity of Roads, Railways and Airfields (BCRRA 2017). London: CRC Press.
Rubinstein, R. Y., and D. P. Kroese. 2017. Simulation and the Monte Carlo method, 3rd ed. New York: Wiley.
Sarkar, A. 2016. “Numerical comparison of flexible pavement dynamic response under different axles.” Int. J. Pavement Eng. 17 (5): 377–387. https://doi.org/10.1080/10298436.2014.993195.
Tijana, R., I. Vujanovic, and D. Ivanovic. 2014. “Comparison of full factorial design, central composite design, and box-behnken design in chromatographic method development for the determination of fluconazole and its impurities.” Anal. Lett. 47 (8): 1334–1347. https://doi.org/10.1080/00032719.2013.867503.
Wasserman, L. 2000. “Bayesian model selection and model averaging.” J. Math. Psychol. 44 (1): 92–107. https://doi.org/10.1006/jmps.1999.1278.
Yamany, M. S., T. U. Saeed, M. Volovski, and A. Ahmed. 2020. “Characterizing the performance of interstate flexible pavements using artificial neural networks and random parameters regression.” J. Infrastruct. Syst. 26 (2): 04020010. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000542.
Zeugner, S. 2011. “Bayesian model averaging with BMS.” Tutor R-package BMS. Accessed May 5, 2011. https://cran.r-project.org/web/packages/BMS/vignettes/bms.pdf.
Zeugner, S., and M. Feldkircher. 2015. “Bayesian model averaging employing fixed and flexible priors: The BMS package for R.” J. Stat. Software 68 (4): 1–30. https://doi.org/10.18637/jss.v068.i04.
Zheng, W., and Y. Yu. 2013. Bayesian probabilistic framework for damage identification of steel truss bridges under joint uncertainties. London: Hindawi.
Information & Authors
Information
Published In
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Aug 19, 2020
Accepted: Nov 24, 2020
Published online: Jan 11, 2021
Published in print: Mar 1, 2021
Discussion open until: Jun 11, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.