Asphalt concrete dynamic modulus prediction: Bayesian neural network approach

References

• Advanced Research Associates, 2004. Design guide: design of New and rehabilitated pavement structures, NCHRP 1-37A project. Washington, DC: National Cooperative Highway Research Program, National Research Council.
   Google Scholar
• Ai, X., et al., 2022. Performance evaluation of recycled asphalt mixtures with various percentages of RAP from the rotary decomposition process. Construction and Building Materials, 321, 126406.
   Web of Science ®Google Scholar
• Al-Khateeb, G., et al., 2006. A new simplistic model for dynamic modulus predictions of asphalt paving mixtures. Journal of the Association of Asphalt Paving Technologists, 75, 1254–1293.
   Google Scholar
• Al-Qadi, I.L., et al., 2012. Impact of high RAP contents on structural and performance properties of asphalt mixtures. Rantoul, IL: Illinois Center for Transportation.
   Google Scholar
• Al-Qadi, I.L., et al., 2015. Testing protocols to ensure performance of high asphalt binder replacement mixes using RAP and RAS. Rantoul, IL: Illinois Center for Transportation.
   Google Scholar
• Ali, Y., et al., 2021. An eXtreme gradient boosting model for predicting dynamic modulus of asphalt concrete mixtures. Construction and Building Materials, 295, 123642.
   Web of Science ®Google Scholar
• Amirkhanian, S., Xiao, F., and Corley, M., 2018. Characterization of asphalt concrete dynamic modulus in South Carolina. Pendleton, SC: Tri County Technical College.
   Google Scholar
• Azari, H., et al., 2007. Comparison of simple performance test| E*| of accelerated loading facility mixtures and prediction| E*| use of NCHRP 1-37A and Witczak’s new equations. Transportation Research Record: Journal of the Transportation Research Board, 1998 (1), 1–9.
   Google Scholar
• Bari, J., 2005. Development of a new revised version of the witczak E* predictive models for hot mix asphalt mixtures. Tempe, AZ: Arizona State University.
   Google Scholar
• Barugahare, J., et al., 2020. Predicting the dynamic modulus of hot mix asphalt mixtures using bagged trees ensemble. Construction and Building Materials, 260, 120468.
   Web of Science ®Google Scholar
• Barugahare, J., et al., 2021. Evaluation of ANN-based dynamic modulus models of asphalt mixtures. Journal of Materials in Civil Engineering, 33 (6), 4021099.
   Web of Science ®Google Scholar
• Batioja-Alvarez, D., Lee, J., and Nantung, T, 2019. Evaluating dynamic modulus for Indiana mechanistic-empirical pavement design guide practice. Transportation Research Record: Journal of the Transportation Research Board, 2673 (2), 346–357.
   Web of Science ®Google Scholar
• Bech, N., and Vandenbossche, J.M, 2022. Relationship between backcalculated dynamic modulus, estimated dynamic modulus, and fatigue damage in asphalt concrete. International Journal of Pavement Engineering, 1–14.
   Web of Science ®Google Scholar
• Behnood, A., and Daneshvar, D, 2020. A machine learning study of the dynamic modulus of asphalt concretes: An application of M5P model tree algorithm. Construction and Building Materials, 262, 120544.
   Web of Science ®Google Scholar
• Bennert, T., 2009. Dynamic modulus of hot mix asphalt: final report, June 2009.
   Google Scholar
• Birgisson, B., Sholar, G., and Roque, R, 2005. Evaluation of a predicted dynamic modulus for Florida mixtures. Transportation Research Record: Journal of the Transportation Research Board, 1929 (1), 200–207.
   Google Scholar
• Blundell, C., et al., 2015. Weight uncertainty in neural network. In: International conference on machine learning. Lille, France: JMLR: W&CP, 1613–1622.
   Google Scholar
• Bonaquist, R.F., 2010. Wisconsin mixture characterization using the asphalt mixture performance tester (AMPT) on historical aggregate structures. Madison, WI: Wisconsin Highway Research Program.
   Google Scholar
• Ceylan, H., et al., 2009. Accuracy of predictive models for dynamic modulus of hot-mix asphalt. Journal of Materials in Civil Engineering, 21 (6), 286–293.
   Web of Science ®Google Scholar
• Ceylan, H., Gopalakrishnan, K., and Kim, S, 2008. Advanced approaches to hot-mix asphalt dynamic modulus prediction. Canadian Journal of Civil Engineering, 35 (7), 699–707.
   Web of Science ®Google Scholar
• Ceylan, H., Kim, S., and Gopalakrishnan, K, 2007. Hot mix asphalt dynamic modulus prediction models using neural network approach. Intelligent Engineering Systems Through Artificial Neural Networks, 17, 117–124.
   Google Scholar
• Christensen, D.W., and Bonaquist, R, 2015. Improved hirsch model for estimating the modulus of hot-mix asphalt. Road Materials and Pavement Design, 16 (sup2), 254–274.
   Web of Science ®Google Scholar
• Christensen, D.W., Jr., Pellinen, T., and Bonaquist, R.F., 2003. Hirsch model for estimating the modulus of asphalt concrete. Journal of the Association of Asphalt Paving Technologists, 72, 97–121.
   Google Scholar
• Clyne, T.R., et al., 2003. Dynamic and Resilient Modulus of Mn/DOT Asphalt Mixtures.
   Google Scholar
• Cross, S.A., Jakatimath, Y., S, KC, et al., 2007. Determination of dynamic modulus master curves for Oklahoma HMA mixtures. Oklahoma City, OK: Oklahoma Department of Transportation.
   Google Scholar
• Daneshvar, D., and Behnood, A, 2022. Estimation of the dynamic modulus of asphalt concretes using random forests algorithm. International Journal of Pavement Engineering, 23 (2), 250–260.
   Web of Science ®Google Scholar
• Daniel, J.S., and Mogawer, W.S., 2010. Determining the effective PG grade of binder in RAP mixes. Fall River, MA: New England Transportation Consortium.
   Google Scholar
• Darabi, M.K., et al., 2020. Time-dependent drucker-prager-Cap model coupled with PANDA (pavement analysis using nonlinear damage approach) to predict rutting performance of flexible pavements. Construction and Building Materials, 244, 118326.
   Web of Science ®Google Scholar
• El-Badawy, S., Abd El-Hakim, R., and Awed, A, 2018. Comparing artificial neural networks with regression models for hot-mix asphalt dynamic modulus prediction. Journal of Materials in Civil Engineering, 30 (7), 4018128.
   Web of Science ®Google Scholar
• Eleyedath, A., and Swamy, A.K, 2022. Prediction of dynamic modulus of asphalt concrete using hybrid machine learning technique. International Journal of Pavement Engineering, 23 (6), 2083–2098.
   Web of Science ®Google Scholar
• Esfandiarpour, S, 2017. Calibrating MEPDG inputs prediction models for asphalt mixes containing reclaimed asphalt pavement. Winnipeg, Manitoba, Canada: University of Manitoba.
   Google Scholar
• Fang, K., Shen, C., and Kifer, D, 2019. Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictions. arXiv Preprint. arXiv:1906.04595.
   Google Scholar
• Far, M.S.S., et al., 2009. Application of artificial neural networks for estimating dynamic modulus of asphalt concrete. Transportation Research Record: Journal of the Transportation Research Board, 2127 (1), 173–186.
   Web of Science ®Google Scholar
• Gal, Y., and Ghahramani, Z., 2016. Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International conference on machine learning. New York, NY: JMLR: W&CP, 1050–1059.
   Google Scholar
• Georgouli, K., Loizos, A., and Plati, C, 2016. Calibration of dynamic modulus predictive model. Construction and Building Materials, 102, 65–75.
   Web of Science ®Google Scholar
• Ghasemi, P., et al., 2019. Principal component neural networks for modeling, prediction, and optimization of hot mix asphalt dynamics modulus. Infrastructures, 4 (3), 53.
   Google Scholar
• Gong, H., et al., 2020. Improved estimation of dynamic modulus for hot mix asphalt using deep learning. Construction and Building Materials, 263, 119912.
   Web of Science ®Google Scholar
• Gong, H., et al., 2022. An efficient and robust method for predicting asphalt concrete dynamic modulus. International Journal of Pavement Engineering, 23 (8), 2565–2576.
   Web of Science ®Google Scholar
• González, S., et al., 2020. A practical tutorial on bagging and boosting based ensembles for machine learning: algorithms, software tools, performance study, practical perspectives and opportunities. Information Fusion, 64, 205–237.
   Web of Science ®Google Scholar
• Gopalakrishnan, K., and Kim, S, 2011. Support vector machines approach to HMA stiffness prediction. Journal of Engineering Mechanics, 137 (2), 138–146.
   Web of Science ®Google Scholar
• Heidaripanah, A., and Hassani, A, 2021. Adaptive neuro-fuzzy inference system to predict the dynamic modulus of Hot Mix asphalt. Journal of Transportation Engineering, Part B: Pavements, 147 (3), 4021043.
   Web of Science ®Google Scholar
• Hernandez, J.A., Gamez, A., and Al-Qadi, I.L, 2016. Effect of wide-base tires on nationwide flexible pavement systems: numerical modeling. Transportation Research Record: Journal of the Transportation Research Board, 2590 (1), 104–112.
   Google Scholar
• Huang, J., et al., 2021. Accurately predicting dynamic modulus of asphalt mixtures in low-temperature regions using hybrid artificial intelligence model. Construction and Building Materials, 297, 123655.
   Web of Science ®Google Scholar
• Khattab, A.M., El-Badawy, S.M., Elmwafi, M., et al., 2014. Evaluation of witczak E* predictive models for the implementation of AASHTOWare-pavement ME design in the kingdom of Saudi arabia. Construction and Building Materials, 64, 360–369.
   Web of Science ®Google Scholar
• Kim, Y.R., et al., 2011. LTPP computed parameter: dynamic modulus.
   Google Scholar
• Kim, Y.-R., Im, S., and Ban, H., 2010. Layer moduli of Nebraska pavements for the new mechanistic-empirical pavement design guide (MEPDG).
   Google Scholar
• Kingma, D.P., and Ba, J, 2014. Adam: A method for stochastic optimization. arXiv Preprint. arXiv:1412.6980.
   Google Scholar
• Kingma, D.P., and Welling, M, 2013. Auto-encoding variational Bayes. arXiv Preprint. arXiv:1312.6114.
   Google Scholar
• Kullback, S., and Leibler, R.A, 1951. On information and sufficiency. The Annals of Mathematical Statistics, 22 (1), 79–86.
   Google Scholar
• Li, M., et al., 2022. Surface layer modulus prediction of asphalt pavement based on LTPP database and machine learning for mechanical-empirical rehabilitation design applications. Construction and Building Materials, 344, 128303.
   Web of Science ®Google Scholar
• Lippert, D.L., et al., 2017. Construction and performance monitoring of various asphalt mixes in Illinois: 2016 interim report.
   Google Scholar
• Liu, J., et al., 2017. Prediction models of mixtures’ dynamic modulus using gene expression programming. International Journal of Pavement Engineering, 18 (11), 971–980.
   Web of Science ®Google Scholar
• Liu, F.T., Ting, K.M., and Zhou, Z.-H., 2008. Isolation forest. In: 2008 eighth IEEE international conference on data mining, 413–422.
   Google Scholar
• Loulizi, A., Flintsch, G.W., and McGhee, K, 2007. Determination of in-place hot-mix asphalt layer modulus for rehabilitation projects by a mechanistic–empirical procedure. Transportation Research Record: Journal of the Transportation Research Board, 2037 (1), 53–62.
   Google Scholar
• Lundberg, S.M., and Lee, S.-I, 2017. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.
   Google Scholar
• Lundy, J.R., 2005. Asphalt mix characterization using dynamic modulus and APA testing. Oregon Department of Transportation, Research Unit.
   Google Scholar
• Mallela, J., et al., 2000. Implementation of the AASHTO mechanistic-empirical pavement design guide for Colorado.
   Google Scholar
• Mohammad, L.N., et al., 2014. Characterization of Louisiana asphalt mixtures using simple performance tests and MEPDG.
   Google Scholar
• Mohammadi Golafshani, E., Behnood, A., and Karimi, M.M., 2021. Predicting the dynamic modulus of asphalt mixture using hybridized artificial neural network and grey wolf optimizer. International Journal of Pavement Engineering, 1–11.
   Web of Science ®Google Scholar
• Molnar, C, 2020. Interpretable machine learning. Lulu.com.
   Google Scholar
• Moussa, G.S., and Owais, M, 2020. Pre-trained deep learning for hot-mix asphalt dynamic modulus prediction with laboratory effort reduction. Construction and Building Materials, 265, 120239.
   Web of Science ®Google Scholar
• Moussa, G.S., and Owais, M, 2021. Modeling Hot-Mix asphalt dynamic modulus using deep residual neural networks: parametric and sensitivity analysis study. Construction and Building Materials, 294, 123589.
   Web of Science ®Google Scholar
• Neal, R.M., and Hinton, G.E, 1998. A view of the EM algorithm that justifies incremental, sparse, and other variants. In: Michael Jordan, ed. Learning in graphical models. Cambridge, MA: Springer, 355–368.
   Google Scholar
• Okte, E., and Al-Qadi, I.L, 2021. Prediction of flexible pavement 3-D finite element responses using Bayesian neural networks. International Journal of Pavement Engineering, 23 (14), 1–11.
   Web of Science ®Google Scholar
• Olivier, A., Shields, M.D., and Graham-Brady, L, 2021. Bayesian neural networks for uncertainty quantification in data-driven materials modeling. Computer Methods in Applied Mechanics and Engineering, 386, 114079.
   Web of Science ®Google Scholar
• Osband, I., et al., 2016. Deep exploration via bootstrapped DQN. Advances in Neural Information Processing Systems, 29, 4026–4034.
   Google Scholar
• Pearce, T., et al., 2018. Bayesian inference with anchored ensembles of neural networks, and application to exploration in reinforcement learning. arXiv Preprint. arXiv:1805.11324.
   Google Scholar
• Pellinen, T.K., 2001. Investigation of the use of dynamic modulus as an indicator of hot-mix asphalt peformance. Tempe, AZ: Arizona State University.
   Google Scholar
• Ping, W.V., and Xiao, Y., 2008. A comparative study of laboratory measured and predicted dynamic modulus for characterizing Florida asphalt mixtures. In: Jeffery Roesler et al., ed. Airfield and highway pavements: efficient pavements supporting transportation’s future. Bellevue, WA: American Society of Civil Engineers, 147–158.
   Google Scholar
• Sakhaeifar, M.S., Kim, Y.R., and Kabir, P, 2015. New predictive models for the dynamic modulus of hot mix asphalt. Construction and Building Materials, 76, 221–231.
   Web of Science ®Google Scholar
• Salimans, T., Kingma, D., and Welling, M., 2015. Markov chain Monte Carlo and variational inference: bridging the gap. In: International conference on machine learning. Lille, France: JMLR: W&CP, 1218–1226.
   Google Scholar
• Singh, D., Zaman, M., and Commuri, S, 2013. Artificial neural network modeling for dynamic modulus of hot mix asphalt using aggregate shape properties. Journal of Materials in Civil Engineering, 25 (1), 54–62.
   Web of Science ®Google Scholar
• Srivastava, N., et al., 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15 (1), 1929–1958.
   Google Scholar
• Tashman, L., and Elangovan, M.A, 2008. Dynamic Modulus Test-Laboratory Investigation and Future Implementation in the State of Washington.
   Google Scholar
• Tran, N.H., Taylor, A., and Willis, R, 2012. Effect of rejuvenator on performance properties of HMA mixtures with high RAP and RAS contents. NCAT Report, 12-05 (1), 5–12.
   Google Scholar
• Wen, H., et al., 2015. IDAHO TRANSPO.
   Google Scholar
• Witczak, M.W., 2002. Simple performance test for superpave mix design. Washington, DC: Transportation Research Board.
   Google Scholar
• Witczak, M.W., and Fonseca, O.A, 1996. Revised predictive model for dynamic (complex) modulus of asphalt mixtures. Transportation Research Record: Journal of the Transportation Research Board, 1540 (1), 15–23.
   Google Scholar
• Worthey, H., Yang, J.J., and Kim, S.S, 2021. Tree-Based ensemble methods: predicting asphalt mixture dynamic modulus for flexible pavement design. KSCE Journal of Civil Engineering, 25 (11), 4231–4239.
   Web of Science ®Google Scholar
• Yu, J., 2012. Modification of dynamic modulus predictive models for asphalt mixtures containing recycled asphalt shingles. Ames, IA: Iowa State University.
   Google Scholar
• Zhang, J., et al., 2013. Comparison of flow number, dynamic modulus, and repeated load tests for evaluation of HMA permanent deformation. Construction and Building Materials, 44, 391–398.
   Web of Science ®Google Scholar