Modelling of pavement performance evolution considering uncertainty and interpretability: a machine learning based framework

References

• Amin, S.R., and Amador-Jiménez, L.E, 2017. Backpropagation neural network to estimate pavement performance: dealing with measurement errors. Road Materials and Pavement Design, 18 (5), 1218–1238.
   Web of Science ®Google Scholar
• Barber, D., and Bishop, C.M, 1998. Ensemble learning in Bayesian neural networks. Nato ASI Series F Computer and Systems Sciences, 168, 215–238.
   Google Scholar
• Blundell, C., et al., 2015. Weight uncertainty in neural networks.
   Google Scholar
• Braswell, E., et al., 2021. Refinement of climate-, depth-, and time-based laboratory aging procedure for asphalt mixtures. Transportation Research Record, 2675 (2), 207–218.
   Web of Science ®Google Scholar
• Cai, J., et al., 2018. Feature selection in machine learning: a new perspective. Neurocomputing, 300, 70–79.
   Web of Science ®Google Scholar
• Choi, J.H., Adams, T.M., and Bahia, H.U, 2004. Pavement roughness modeling using back-propagation neural networks. Computer-Aided Civil and Infrastructure Engineering, 19 (4), 295–303.
   Web of Science ®Google Scholar
• Choi, S., and Do, M, 2020. Development of the road pavement deterioration model based on the deep learning method. Electronics, 9 (1), 3.
   Web of Science ®Google Scholar
• Dong, Y., et al., 2019. Forecasting pavement performance with a feature fusion LSTM-BPNN model. Proceedings of the 28th ACM international conference on information and knowledge management, 1953–1962.
   Google Scholar
• El-Hakim, A., and El-Badawy, S, 2013. International roughness index prediction for rigid pavements: an artificial neural network application. Advanced Materials Research, 723, 854–860.
   Google Scholar
• Gal, Y., and Ghahramani, Z., 2015. Dropout as a Bayesian approximation: insights and applications. In Deep Learning Workshop, ICML (Vol. 1, p. 2).
   Google Scholar
• Gal, Y., and Ghahramani, Z., 2016. Dropout as a Bayesian approximation: representing model uncertainty in deep learning. 33rd international conference on machine learning. New York, NY.
   Google Scholar
• Gal, Y., Hron, J., and Kendall, A, 2017. Concrete dropout. arXiv preprint arXiv:1705.07832.
   Google Scholar
• Gong, H., et al., 2018. Use of random forests regression for predicting IRI of asphalt pavements. Construction and Building Materials, 189, 890–897.
   Web of Science ®Google Scholar
• Gong, H., et al., 2019. Investigating impacts of asphalt mixture properties on pavement performance using LTPP data through random forests. Construction and Building Materials, 204, 203–212.
   Web of Science ®Google Scholar
• Guler, S.I., and Madanat, S, 2011. Axle load power for pavement fatigue cracking: empirical estimation and policy implications. Transportation Research Record, 2225 (1), 21–24.
   Google Scholar
• Guo, F., Gregory, J., and Kirchain, R, 2020. Incorporating cost uncertainty and path dependence into treatment selection for pavement networks. Transportation Research Part C: Emerging Technologies, 110, 40–55.
   Web of Science ®Google Scholar
• Han, C., et al., 2020. Intelligent decision model of road maintenance based on improved weight random forest algorithm. International Journal of Pavement Engineering, 1–13.
   Web of Science ®Google Scholar
• Hong, F., and Prozzi, J.A, 2006. Estimation of pavement performance deterioration using Bayesian approach. Journal of Infrastructure Systems, 12 (2), 77–86.
   Web of Science ®Google Scholar
• Hossain, M., Gopisetti, L., and Miah, M, 2019. International roughness index prediction of flexible pavements using neural networks. Journal of Transportation Engineering, Part B: Pavements, 145 (1), 04018058.
   Web of Science ®Google Scholar
• Kargah-Ostadi, N., and Stoffels, S.M, 2015. Framework for development and comprehensive comparison of empirical pavement performance models. Journal of Transportation Engineering, 141 (8), 04015012.
   Google Scholar
• Karlaftis, A.G., and Badr, A, 2015. Predicting asphalt pavement crack initiation following rehabilitation treatments. Transportation Research Part C: Emerging Technologies, 55, 510–517.
   Web of Science ®Google Scholar
• Keany, E, 2020. Borutashap: a wrapper feature selection method which combines the Boruta feature selection algorithm with Shapley values. (Version 1.1). Zenodo. doi:10.5281/zenodo.4247618.
   Google Scholar
• Kendall, A., and Gal, Y, 2017. What uncertainties do we need in Bayesian deep learning for computer vision? arXiv preprint arXiv:1703.04977.
   Google Scholar
• Kırbaş, U., and Karaşahin, M, 2016. Performance models for hot mix asphalt pavements in urban roads. Construction and Building Materials, 116, 281–288.
   Web of Science ®Google Scholar
• Kobayashi, K., Kaito, K., and Lethanh, N, 2012. A statistical deterioration forecasting method using hidden markov model for infrastructure management. Transportation Research Part B: Methodological, 46 (4), 544–561.
   Web of Science ®Google Scholar
• Kursa, M.B., and Rudnicki, W.R, 2010. Feature selection with the Boruta package. Journal of Statistical Software, 36 (11), 1–13.
   Web of Science ®Google Scholar
• Li, Q., et al., 2011. Mechanistic-empirical pavement design guide (mepdg): a bird’s-eye view. Journal of Modern Transportation, 19 (2), 114–133.
   Google Scholar
• Lundberg, S.M., et al., 2020. From local explanations to global understanding with explainable ai for trees. Nature Machine Intelligence, 2 (1), 56–67.
   PubMedGoogle Scholar
• Lundberg, S., and Lee, S.-I, 2017. A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874.
   Google Scholar
• Madeh Piryonesi, S, and El-Diraby, T.E., 2021. Using machine learning to examine impact of type of performance indicator on flexible pavement deterioration modeling. Journal of Infrastructure Systems, 27 (2), 4021005.
   Web of Science ®Google Scholar
• Mazari, M., and Rodriguez, D.D, 2016. Prediction of pavement roughness using a hybrid gene expression programming-neural network technique. Journal of Traffic and Transportation Engineering (English Edition), 3 (5), 448–455.
   Google Scholar
• Molnar, C., 2018. A guide for making black box models explainable. https://christophm. github. io/interpretable-ml-book.
   Google Scholar
• Onayev, A., and Swei, O, 2021. Iri deterioration model for asphalt concrete pavements: capturing performance improvements over time. Construction and Building Materials, 271, 121768.
   Web of Science ®Google Scholar
• Osorio-Lird, A., et al., 2018. Application of Markov chains and Monte Carlo simulations for developing pavement performance models for urban network management. Structure and Infrastructure Engineering, 14 (9), 1169–1181.
   Web of Science ®Google Scholar
• Piryonesi, S.M., and El-Diraby, T.E, 2020. Data analytics in asset management: cost-effective prediction of the pavement condition index. Journal of Infrastructure Systems, 26 (1), 04019036.
   Web of Science ®Google Scholar
• Prozzi, J.A., and Madanat, S.M, 2003. Incremental nonlinear model for predicting pavement serviceability. Journal of Transportation Engineering, 129 (6), 635–641.
   Web of Science ®Google Scholar
• Prozzi, J., and Madanat, S, 2004. Development of pavement performance models by combining experimental and field data. Journal of Infrastructure Systems, 10 (1), 9–22.
   Google Scholar
• Rahman, M.M., Uddin, M.M., and Gassman, S.L, 2017. Pavement performance evaluation models for South Carolina. KSCE Journal of Civil Engineering, 21 (7), 2695–2706.
   Web of Science ®Google Scholar
• Roberts, R., Inzerillo, L., and Di Mino, G., 2021. Exploiting data analytics and deep learning systems to support pavement maintenance decisions. Applied Sciences, 11 (6), 2458.
   Google Scholar
• Ryu, S., Kwon, Y., and Kim, W.Y, 2019. Uncertainty quantification of molecular property prediction with bayesian neural networks. arXiv preprint arXiv:1903.08375.
   Google Scholar
• Saltelli, A, 1999. Sensitivity analysis: could better methods be used? Journal of Geophysical Research: Atmospheres, 104 (D3), 3789–3793.
   Web of Science ®Google Scholar
• Saltelli, A., et al., 2019. Why so many published sensitivity analyses are false: a systematic review of sensitivity analysis practices. Environmental Modelling & Software, 114, 29–39.
   Web of Science ®Google Scholar
• Shrikumar, A., Greenside, P., and Kundaje, A., 2017. Learning important features through propagating activation differencesed. International conference on machine learningPMLR, 3145–3153.
   Google Scholar
• Tabatabaee, N., Ziyadi, M., and Shafahi, Y, 2013. Two-stage support vector classifier and recurrent neural network predictor for pavement performance modeling. Journal of Infrastructure Systems, 19 (3), 266–274.
   Web of Science ®Google Scholar
• Wittek, P., 2014. Quantum machine learning: what quantum computing means to data mining. San Diego: Academic Press.
   Google Scholar
• Yao, L., et al., 2019. Establishment of prediction models of asphalt pavement performance based on a novel data calibration method and neural network. Transportation Research Record, 2673 (1), 66–82.
   Web of Science ®Google Scholar
• Yao, L., et al., 2020. Deep reinforcement learning for long-term pavement maintenance planning. Computer-Aided Civil and Infrastructure Engineering, 35 (11), 1230–1245.
   Web of Science ®Google Scholar
• Yehia, A., and Swei, O, 2020. Probabilistic infrastructure performance models: an iterative-methods approach. Transportation Research Part C: Emerging Technologies, 111, 245–254.
   Web of Science ®Google Scholar
• Zeiada, W., et al., 2019. Investigation and modelling of asphalt pavement performance in cold regions. International Journal of Pavement Engineering, 20 (8), 986–997.
   Web of Science ®Google Scholar
• Zeiada, W., et al., 2020. Machine learning for pavement performance modelling in warm climate regions. Arabian Journal for Science and Engineering, 45, 4091–4109.
   Web of Science ®Google Scholar
• Zhou, L., Ni, F., and Zhao, Y, 2010. Evaluation method for transverse cracking in asphalt pavements on freeways. Transportation Research Record, 2153 (1), 97–105.
   Google Scholar