Short-Term Predictions of Asphalt Pavement Rutting Using Deep-Learning Models
Publication: Journal of Transportation Engineering, Part B: Pavements
Volume 150, Issue 2
Abstract
Pavement maintenance causes an instant change in the pavement’s material or structural properties and affects the subsequent development of pavement distresses and performance. The occurrence of maintenance action significantly limits the applicability of predictive models that rely heavily on the continuity of time and pavement exposure conditions. Using rutting of asphalt pavement as an example, this study treated the partitioned rutting development as short-term time series. The proposed average cosine similarity of pavement rutting development effectively integrated the data collected within a characteristic length in the longitudinal direction of the pavement. Integration of the raw data effectively mitigated the data inconsistency caused by measuring errors and simplified the model construction. We employed convolutional neural network (CNN) and long short-term memory (LSTM) as two typical deep-learning (DL) models to capture the characteristics of rutting development from limited data and make corresponding predictions. The effects of model hyperparameters and input type on the model performance (e.g., accuracy and stability) were investigated to identify the optimal setting for various modeling data. The comparisons with two statistical models—exponential smoothing (ES) model and autoregressive integrated moving average (ARIMA) model—indicated the potential of applied DL models in accurately predicting rutting development in field pavement. Finally, three strategies of improving model performance were explored and discussed for future applications, i.e., increasing the input length, input dimensionality, and model complexity.
Practical Applications
This study stands in the position of transportation engineers to solve a practical problem with computer-aided tools, which is the prediction of asphalt pavement performance with deep-learning (DL) models. The data utilized in this study were collected from the field, resulting in inherently challenging characteristics such as being short-term and noisy. This study investigated corresponding strategies to allow DL models to provide accurate and stable predictions. Besides, this study makes DL models more accessible to practicing engineers. A significant amount of model information obtained in this study can be extended to various types of performance indices. Finally, DL models constructed in this study were compared with classic and currently applied models using the same data. The results reveal that DL models can serve as reliable and promising tools for predicting asphalt pavement performance in the natural deterioration stage of the pavement.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
The rutting and OCI data that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This work was financially supported by the Idaho Transportation Department (ITD Project No. 293) and National Center for Transportation Infrastructure Durability & Life-Extension (TriDurLE, Grant No. 69A3551947137). We would also like to thank the technical support from the ITD, especially that from project managers Ned Parrish and Amanda Lamb and from project champions Jim Poorbaugh, Riley Bender, and Mir Tamim.
Disclaimer
The authors declare that they have no conflict of interest. The article reflects the views of the authors, who are responsible for the facts and accuracy of the data presented herein. The contents do not necessarily reflect the official views or policies of ITD or the Federal Highway Administration (FHWA). This article does not constitute a standard, specification, or regulation.
References
Abaza, K. A. 2004. “Deterministic performance prediction model for rehabilitation and management of flexible pavement.” Int. J. Pavement Eng. 5 (2): 111–121. https://doi.org/10.1080/10298430412331286977.
Abaza, K. A. 2016. “Simplified staged-homogenous Markov model for flexible pavement performance prediction.” Road Mater. Pavement Des. 17 (2): 365–381. https://doi.org/10.1080/14680629.2015.1083464.
ARA-ERES (ARA, Inc., ERES Consultants Division). 2004. “Guide for mechanistic–empirical design of new and rehabilitated pavement structures.” Accessed May 31, 2019. http://onlinepubs.trb.org/onlinepubs/archive/mepdg/guide.htm.
Archilla, A. R., and S. Madanat. 2000. “Development of a pavement rutting model from experimental data.” J. Transp. Eng. 126 (4): 291–299. https://doi.org/10.1061/(ASCE)0733-947X(2000)126:4(291).
Box, G. E., and G. M. Jenkins. 1970. Time series analysis: Forecasting and control. San Francisco: Holden-Day.
Brown, R. G., and R. F. Meyer. 1961. “The fundamental theorem of exponential smoothing.” Oper. Res. 9 (5): 673–685. https://doi.org/10.1287/opre.9.5.673.
Brownlee, J. 2018. Deep learning for time series forecasting: Predict the future with MLPs, CNNs and LSTMs in Python. San Francisco: Machine Learning Mastery.
Bukharin, A. W., Z. Yang, and Y. Tsai. 2021. “Five-year project-level statewide pavement performance forecasting using a two-stage machine learning approach based on long short-term memory.” Transp. Res. Rec. 2675 (11): 280–290. https://doi.org/10.1177/03611981211017132.
Chandra, R., S. Goyal, and R. Gupta. 2021. “Evaluation of deep learning models for multi-step ahead time series prediction.” IEEE Access 9 (May): 83105–83123. https://doi.org/10.1109/ACCESS.2021.3085085.
Chen, C., Y. Deng, M. Li, and X. Shi. 2023. “Investigation of key climatic factors affecting asphalt pavement roughness in different climate regions.” Transp. Res. Part D Transp. Environ. 122 (Jun): 103877. https://doi.org/10.1016/j.trd.2023.103877.
Choi, S., and M. Do. 2020. “Development of the road pavement deterioration model based on the deep learning method.” Electronics 9 (1): 3. https://doi.org/10.3390/electronics9010003.
Deng, Y., C. Chen, and X. Shi. 2022a. “Prediction of traffic mobility based on historical data and machine learning approaches (CAMMSE-UNCC-2022-UTC-Project-15).” Accessed August 1, 2022. https://rosap.ntl.bts.gov/view/dot/64522.
Deng, Y., X. Luo, F. Gu, Y. Zhang, and R. L. Lytton. 2019. “3D simulation of deflection basin of pavements under high-speed moving loads.” Constr. Build. Mater. 226 (Apr): 868–878. https://doi.org/10.1016/j.conbuildmat.2019.07.228.
Deng, Y., X. Luo, and H. Wang. 2022b. “Backcalculation of damage density of in-service asphalt pavements using artificial intelligence-based finite element model updating.” Fatigue Fract. Eng. Mater. Struct. 45 (3): 671–686. https://doi.org/10.1111/ffe.13624.
Deng, Y., X. Luo, Y. Zhang, and R. L. Lytton. 2021. “Evaluation of flexible pavement deterioration conditions using deflection profiles under moving loads.” Transp. Geotech. 26 (Feb): 100434. https://doi.org/10.1016/j.trgeo.2020.100434.
Deng, Y., and X. Shi. 2022a. “An accurate, reproducible and robust model to predict the rutting of asphalt pavement: Neural networks coupled with particle swarm optimization.” IEEE Intell. Transp. Syst. Trans. 23 (11): 22063–22072. https://doi.org/10.1109/TITS.2022.3149268.
Deng, Y., and X. Shi. 2022b. “Development of predictive models of asphalt pavement distresses in Idaho through gene expression programming.” Neural Comput. Appl. 34 (17): 14913–14927. https://doi.org/10.1007/s00521-022-07305-2.
Deng, Y., and X. Shi. 2023. “Modeling the rutting performance of asphalt pavements: A review.” J. Infrastruct. Preserv. Resilience 4 (1): 17. https://doi.org/10.1186/s43065-023-00082-9.
Deng, Y., X. Shi, Y. Kou, J. Chen, and Q. Shi. 2022c. “Optimized design of asphalt concrete pavement containing phase change materials based on rutting performance.” J. Cleaner Prod. 380 (Mar): 134787. https://doi.org/10.1016/j.jclepro.2022.134787.
Deng, Y., X. Shi, Y. Zhang, and J. Chen. 2021. “Numerical modelling of rutting performance of asphalt concrete pavement containing phase change material.” Eng. Comput. 13 (Sep): 1167–1182. https://doi.org/10.1007/s00366-021-01507-3.
Deng, Y., Y. Zhang, X. Shi, S. Hou, and R. L. Lytton. 2022d. “Stress–strain dependent rutting prediction models for multi-layer structures of asphalt mixtures.” Int. J. Pavement Eng. 23 (8): 2728–2745. https://doi.org/10.1080/10298436.2020.1869974.
Dong, Y., Y. Shao, X. Li, S. Li, L. Quan, W. Zhang, and J. Du. 2019. “Forecasting pavement performance with a feature fusion LSTM-BPNN model.” In Proc., 28th ACM Int. Conf. on Information and Knowledge Management. New York: Association for Computing Machinery.
Fukushima, K. 1969. “Visual feature extraction by a multilayered network of analog threshold elements.” IEEE Transact. Syst. Sci. Cybern. 5 (4): 322–333. https://doi.org/10.1109/TSSC.1969.300225.
George, S., and A. K. Santra. 2020. “Traffic prediction using multifaceted techniques: A survey.” Wireless Pers. Commun. 115 (2): 1047–1106. https://doi.org/10.1007/s11277-020-07612-8.
Géron, A. 2019. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. 2nd ed. Sebastopol, CA: O’Reilly Media.
Gong, H., Y. Sun, Z. Mei, and B. Huang. 2018. “Improving accuracy of rutting prediction for mechanistic-empirical pavement design guide with deep neural networks.” Constr. Build. Mater. 190 (Jun): 710–718. https://doi.org/10.1016/j.conbuildmat.2018.09.087.
Hall, C. A., and W. W. Meyer. 1976. “Optimal error bounds for cubic spline interpolation.” J. Approximation Theory 16 (2): 105–122. https://doi.org/10.1016/0021-9045(76)90040-X.
Han, Z., J. Zhao, H. Leung, K. F. Ma, and W. Wang. 2019. “A review of deep learning models for time series prediction.” IEEE Sens. J. 21 (6): 7833–7848. https://doi.org/10.1109/JSEN.2019.2923982.
Hewamalage, H., C. Bergmeir, and K. Bandara. 2021. “Recurrent neural networks for time series forecasting: Current status and future directions.” Int. J. Forecasting 37 (1): 388–427. https://doi.org/10.1016/j.ijforecast.2020.06.008.
Hochreiter, S., and J. Schmidhuber. 1997. “Long short-term memory.” Neural Comput. 9 (8): 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735.
Holt, C. C. 2004. “Forecasting seasonals and trends by exponentially weighted moving averages.” Int. J. Forecasting 20 (1): 5–10. https://doi.org/10.1016/j.ijforecast.2003.09.015.
Hyndman, R. J., and G. Athanasopoulos. 2018. Forecasting: Principles and practice. 2nd ed. Melbourne, Australia: OTexts.
Justo-Silva, R., A. Ferreira, and G. Flintsch. 2021. “Review on machine learning techniques for developing pavement performance prediction models.” Sustainability 13 (9): 5248. https://doi.org/10.3390/su13095248.
Kingma, D. P., and J. Ba. 2014. “Adam: A method for stochastic optimization.” Preprint, submitted December 22, 2014. http://arxiv.org/abs/1412.6980.
Kiranyaz, S., O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj, and D. J. Inman. 2021. “1D convolutional neural networks and applications: A survey.” Mech. Syst. Signal Process. 151 (Mar): 107398. https://doi.org/10.1016/j.ymssp.2020.107398.
Kotu, V., and B. Deshpande. 2018. Data science: Concepts and practice. 2nd ed. Burlington, MA: Morgan Kaufmann.
LeCun, Y., and Y. Bengio. 1995. “Convolutional networks for images, speech, and time series.” In The handbook of brain theory and neural networks. Cambridge, MA: MIT Press.
Luo, X., H. Wang, Y. Deng, and H. Li. 2022. “Automatic inverse analysis of asphalt pavement field aging based on system identification.” IEEE Trans. Intell. Transp. Syst. 23 (11): 22106–22115. https://doi.org/10.1109/TITS.2022.3172518.
Makridakis, S., E. Spiliotis, and V. Assimakopoulos. 2018. “Statistical and machine learning forecasting methods: Concerns and ways forward.” PLoS One 13 (3): e0194889. https://doi.org/10.1371/journal.pone.0194889.
Marcelino, P., M. de Lurdes Antunes, E. Fortunato, and M. C. Gomes. 2021. “Machine learning approach for pavement performance prediction.” Int. J. Pavement Eng. 22 (3): 341–354. https://doi.org/10.1080/10298436.2019.1609673.
Murphy, K. P. 2012. Machine learning: A probabilistic perspective. Cambridge, MA: MIT press.
Okuda, T., K. Suzuki, and N. Kohtake. 2018. “Non-parametric prediction interval estimate for uncertainty quantification of the prediction of road pavement deterioration.” In Proc., 21st Int. Conf. on Intelligent Transportation Systems (ITSC). New York: IEEE.
Pu, Z., C. Liu, X. Shi, Z. Cui, and Y. Wang. 2020. “Road surface friction prediction using long short-term memory neural network based on historical data.” J. Intell. Transp. Syst. 26 (1): 34–45. https://doi.org/10.1080/15472450.2020.1780922.
Rogoza, W. 2019. “Method for the prediction of time series using small sets of experimental samples.” Appl. Math. Comput. 355 (Apr): 108–122. https://doi.org/10.1016/j.amc.2019.02.062.
Shi, X., Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W.-C. Woo. 2015. “Convolutional LSTM network: A machine learning approach for precipitation nowcasting.” Accessed March 31, 2022. https://proceedings.neurips.cc/paper/2015/file/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf.
Tutumluer, E., and T. Pan. 2008. “Aggregate morphology affecting strength and permanent deformation behavior of unbound aggregate materials.” J. Mater. Civ. Eng. 20 (9): 617–627. https://doi.org/10.1061/(ASCE)0899-1561(2008)20:9(617).
Wang, F., C.-C. B. Lee, and N. G. Gharaibeh. 2022. “Network-level bridge deterioration prediction models that consider the effect of maintenance and rehabilitation.” J. Infrastruct. Syst. 28 (1): 05021009. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000662.
Winters, P. R. 1960. “Forecasting sales by exponentially weighted moving averages.” Manage. Sci. 6 (3): 324–342. https://doi.org/10.1287/mnsc.6.3.324.
Xin, J., M. Akiyama, D. M. Frangopol, and M. Zhang. 2022. “Multi-objective optimisation of in-service asphalt pavement maintenance schedule considering system reliability estimated via LSTM neural networks.” Struct. Infrastruct. Eng. 18 (7): 1002–1019. https://doi.org/10.1080/15732479.2022.2038641.
Yao, L., Q. Dong, J. Jiang, and F. Ni. 2020. “Deep reinforcement learning for long-term pavement maintenance planning.” Comput.-Aided Civ. Infrastruct. Eng. 35 (11): 1230–1245. https://doi.org/10.1111/mice.12558.
Zhang, Y., H. Chen, P. Xiao, Y. Deng, and A.-H. Kang. 2022. “Investigation of average asphalt film thickness of dense graded asphalt mixtures with compaction effects.” Constr. Build. Mater. 326 (Mar): 126696. https://doi.org/10.1016/j.conbuildmat.2022.126696.
Zhou, Q., E. Okte, and I. L. Al-Qadi. 2021. “Predicting pavement roughness using deep learning algorithms.” Transp. Res. Rec. 2675 (11): 1062–1072. https://doi.org/10.1177/03611981211023765.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part B: Pavements
Volume 150 • Issue 2 • June 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Mar 10, 2023
Accepted: Oct 24, 2023
Published online: Jan 25, 2024
Published in print: Jun 1, 2024
Discussion open until: Jun 25, 2024
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.