Use of Deep Learning to Study Modeling Deterioration of Pavements a Case Study in Iowa
Abstract
:1. Introduction
- Classification: Supervised learning in neural networks can be used to deal with unknown inputs. Neural network models have been used to investigate the classification of pavement distresses from digital images [23]. Another research study by [24] reported using a neural network to detect pavement cracks.
- Performance Prediction: Neural networks have been used in various studies as powerful and versatile computational tools for both determining the performance of existing pavement systems and predicting future conditions. The Pavement Distress Index (PDI), based on surface thickness, pavement age, and traffic level, was predicted using an NN model that outperformed other multiple-linear regressions [25]. A back-propagation neural network model was developed by [26] for predicting IRI based on pavement distress.
- Optimization and maintenance strategies: Neural networks have been used as computational tools to determine which maintenance and rehabilitation actions should be performed on deteriorated pavement sections, using a hybrid NN and genetic algorithm method developed for optimizing the maintenance strategy of flexible pavements [27].
- Distress Prediction: Neural networks can help pavement engineers predict future distresses, and a multi-layer perceptron back-propagation NN with one hidden layer has been used to predict future roughness distress in flexible pavements [28]. NNs could be a powerful alternative to traditional techniques that are always limited by normality, linearity, and collinearity assumptions. Two major advantages of using NNs are their ability to model complex and nonlinear large amounts of data and detect all possible interactions between predictor variables.
2. Methods
2.1. Data Collection
2.2. Preprocessing
- Riding index;
- Rutting index (AC and COM Only);
- Cracking index;
- Faulting index (PCC Only).
2.3. Developing LSTM Model
2.4. Training
2.5. Validation
2.6. Comparison
3. Results and Discussion
4. Conclusions
- The comparison between the developed model and the individual regression models used by the Iowa DOT from the three different pavement types indicates that the prediction accuracy in the LSTM model is higher than individual regression models.
- The LSTM achieved a higher PCI prediction accuracy than the individual regression models in all three pavement types.
- A hypothesis analysis of the mean was conducted for the PCI residual in both techniques and the results exhibited less LSTM bias than that of the individual regression models.
- Each of these two methods has its own advantages and disadvantages. The equation of the individual regression models requires an annual update, and each section will exhibit a new year-by-year behavior, making the prediction process more complex. The LSTM is only one more consistent model compatible for all sections using a training process. The LSTM approach was sensitive to the data fluctuation resulting from unrecorded maintenance activities.
- While the evaluation of the regression models was restricted to residuals between the fitted functions and the actual readings, the evaluation for the LSTM was based on its ability to predict full performance curves not included during the training stage.
Author Contributions
Funding
Conflicts of Interest
References
- AASHTO. Pavement Management Guide, 2nd ed.; AASHTO: Washington, DC, USA, 2012. [Google Scholar]
- Vasquez, C.A. Pavement Management Systems on a Local Level. Master’s Thesis, Utah State University, Logan, UT, USA, 2011. [Google Scholar]
- Hassan, R.; Lin, O.; Thananjeyan, A. A comparison between three approaches for modelling deterioration of five pavement surfaces. Int. J. Pavement Eng. 2015, 18, 26–35. [Google Scholar] [CrossRef]
- Saha, P.; Ksaibati, K.; Atadero, R. Developing pavement distress deterioration models for pavement management system using markovian probabilistic process. Adv. Civ. Eng. 2017, 2017, 1–9. [Google Scholar] [CrossRef] [Green Version]
- Ragnoli, A.; De Blasiis, M.R.; Di Benedetto, A. Pavement distress detection methods: A review. Infrastructures 2018, 3, 58. [Google Scholar] [CrossRef] [Green Version]
- Shahnazari, H.; Tutunchian, M.A.; Mashayekhi, M.; Amini, A.A. Application of soft computing for prediction of pavement condition index. J. Transp. Eng. 2012, 138, 1495–1506. [Google Scholar] [CrossRef]
- Ceylan, H.; Birkan Bayrak, M.; Gopalakrishnan, K. Neural networks applications in pavement engineering: A recent survey. Int. J. Pavement Res. Technol. 2014, 7, 434–444. [Google Scholar] [CrossRef]
- Bektas, F.; Smadi, O.G.; Al-Zoubi, M. Pavement Management Performance Modeling: Evaluating the Existing PCI Equations Institute for Transportation at Iowa State University Project Reports. 2014. Available online: https://lib.dr.iastate.edu/intransreports/100/ (accessed on 6 November 2014).
- Pantuso, A.; Flintsch, G.W.; Katicha, S.W.; Loprencipe, G. Development of network-level pavement deterioration curves using the linear empirical Bayes approach. Int. J. Pavement Eng. 2019, 1–14. [Google Scholar] [CrossRef] [Green Version]
- Lytton, R.L. Concepts of pavement performance prediction and modeling. In Proceedings of the 2nd North American Conference on Managing Pavements, Toronto, ON, Canada, 2–6 November 1987; Volume 2, pp. 27–33. [Google Scholar]
- Wolters, A.S.; Zimmerman, K.A. Research of Current Practices in Pavement Performance Modeling (No. FHWA-PA-2010-007-080307). 2010. Available online: https://trid.trb.org/view/919191 (accessed on 6 November 2019).
- Li, N.; Xie, W.C.; Haas, R. Reliability-based processing of Markov chains for modeling pavement network deterioration. Transp. Res. Rec. 1996, 1524, 203–213. Available online: https://journals.sagepub.com/doi/abs/10.1177/0361198196152400124?journalCode=trra (accessed on 6 November 2019). [CrossRef]
- Silva, F.D.M.E.; Van Dam, T.J.; Bulleit, W.M.; Ylitalo, R. Proposed pavement performance models for local government agencies in michigan. Transp. Res. Rec. J. Transp. Res. Board 2000, 1699, 81–86. [Google Scholar] [CrossRef]
- Mills, L.N.O.; Attoh-Okine, N.O.; McNeil, S. Developing pavement performance models for delaware. Transp. Res. Rec. J. Transp. Res. Board 2012, 2304, 97–103. [Google Scholar] [CrossRef]
- Haas, R.; Hudson, W.; Zaniewski, J. Modern Pavement Management; Krieger Publishing Company: Malabar, FL, USA, 1994; Volume 102, p. 583. [Google Scholar]
- Shabanpour, R. Pavement Performance Modeling: Literature Review and Research Agenda, Illinois Asphalt Pavement Association. 2017. Available online: https://ilasphalt.org/files/7315/1803/1691/Ramin_Shabanpour_2017_UICg.pdf (accessed on 17 June 2020).
- Golroo, A.; Tighe, S.L. Development of pervious concrete pavement performance models using expert opinions. J. Transp. Eng. 2012, 138, 634–648. [Google Scholar] [CrossRef]
- Adeli, H. Neural networks in civil engineering: 1989–2000. Comput. Civ. Infrastruct. Eng. 2001, 16, 126–142. [Google Scholar] [CrossRef]
- Dougherty, M. A review of neural networks applied to transport. Transp. Res. Part. C Emerg. Technol. 1995, 3, 247–260. [Google Scholar] [CrossRef]
- Flood, I. Towards the next generation of artificial neural networks for civil engineering. Adv. Eng. Inform. 2008, 22, 4–14. [Google Scholar] [CrossRef]
- Flood, I.; Kartam, N. Neural networks in civil engineering. I: Principles and understanding. J. Comput. Civ. Eng. 1994, 8, 131–148. [Google Scholar] [CrossRef]
- Basheer, I.; Hajmeer, M. Artificial neural networks: Fundamentals, computing, design, and application. J. Microbiol. Methods 2000, 43, 3–31. [Google Scholar] [CrossRef]
- Nallamothu, S.; Wang, K.C. Experimenting with recognition accelerator for pavement distress identification. Transp. Res. Rec. 1996, 1536, 130–135. [Google Scholar] [CrossRef]
- Cheng, H.D.; Wang, J.; Hu, Y.G.; Glazier, C.; Shi, X.J.; Chen, X.W. Novel approach to pavement cracking detection based on neural network. Transp. Res. Rec. J. Transp. Res. Board 2001, 1764, 119–127. [Google Scholar] [CrossRef]
- Owusu-Ababio, S. Effect of neural network topology on flexible pavement cracking prediction. Comput. Civ. Infrastruct. Eng. 1998, 13, 349–355. [Google Scholar] [CrossRef]
- Lin, J.; Yau, J.-T.; Hsiao, L.-H. Correlation analysis between international roughness index (iri) and pavement distress by neural network. In Proceedings of the 82nd Transportation Research Board Annual Meeting, Washington, DC, USA, 12–16 January 2003. [Google Scholar]
- Evolutionary Neural Network Model for the Selection of Pavement Maintenance Strategy. Available online: http://onlinepubs.trb.org/Onlinepubs/trr/1995/1497/1497-009.pdf (accessed on 18 June 2019).
- Huang, Y.; Moore, R.K. Roughness level probability prediction using artificial neural networks. Transp. Res. Rec. J. Transp. Res. Board 1997, 1592, 89–97. [Google Scholar] [CrossRef]
- Laptev, N.; Yosinski, J.; Li, L.E.; Smyl, S. Time-series extreme event forecasting with neural networks at uber. In Proceedings of the International Conference on Machine Learning, Sydney, Australia, 6–11 August 2017; Volume 34, pp. 1–5. Available online: http://roseyu.com/time-series-workshop/submissions/TSW2017_paper_3.pdf (accessed on 14 July 2019).
- Hosseini, S.A. Data-Driven Framework for Modeling Deterioration of Pavements in the State of Iowa. Ph.D. Thesis, Iowa State University, Ames, IA, USA, 2020. [Google Scholar]
- Hosseini, S.A.; Smadi, O. How Prediction Accuracy Can Affect the Decision-making Process in Pavement Management System. engrXiv 2020. Available online: https://engrxiv.org/t28ue/ (accessed on 17 June 2020).
- Horne, J.; Manzenreiter, W. Accounting for mega-events. Int. Rev. Sociol. Sport 2004, 39, 187–203. [Google Scholar] [CrossRef]
- Graves, A. Supervised Sequence Labelling with Recurrent Neural Networks; Springer: Berlin, Germany, 2012; pp. 5–13. [Google Scholar]
- Lecun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef]
- Training Recurrent Neural Networks. Available online: https://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf (accessed on 1 October 2019).
- Busseti, E.; Osband, I.; Wong, S. Deep Learning for Time Series Modeling, Final Project Report. 2012. Available online: https://pdfs.semanticscholar.org/a241/a7e26d6baf2c068601813216d3cc09e845ff.pdf (accessed on 14 October 2019).
- Chung, J.; Gulcehre, C.; Cho, K.H.; Bengio, Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv 2014, arXiv:1412.3555. [Google Scholar]
- Bursanescu, L.; Blais, F. Automated pavement distress data collection and analysis: A 3-D approach. In Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134), Ottawa, ON, Canada, 12–15 May 1997; pp. 311–317. [Google Scholar] [CrossRef] [Green Version]
- Iowa Department of Transportation Transportation Asset Management Plan. 2018. Available online: https://iowadot.gov/systems_planning/fpmam/IowaDOT-TAMP-2018.pdf (accessed on 18 October 2019).
- Chris Olah. Understanding LSTM Networks-Colah’s Blog. 2015. Available online: https://colah.github.io/posts/2015-08-Understanding-LSTMs/ (accessed on 14 October 2019).
Pavement Types | Average Length (Miles) | Minimum Length (Miles) | Maximum Length (Miles) |
---|---|---|---|
AC | 3.88 | 0.16 | 18.61 |
PCC | 2.71 | 0.05 | 18.91 |
COM | 2.69 | 0.05 | 18.14 |
Sub-Index | AC and COM | PCC |
---|---|---|
Transverse Cracking (count/km) | 300 | 300 |
Longitudinal Cracking (m/km) | 500 | 500 |
Wheel-path Cracking (m/km) | 500 | - |
Alligator Cracking (m2/km) | 360 | - |
Sub-Index | PCC | AC and COM |
---|---|---|
Transvers | 60% | 20% |
Longitudinal | 40% | 10% |
Wheel-path | - | 30% |
Alligator | - | 40% |
Actual Mean | Predicted Mean | Actual Standard Deviation | Predicted Standard Deviation | R-Square | |||
---|---|---|---|---|---|---|---|
PCC | DOT | PCI | 58.06 | 68.63 | 23.18 | 19.14 | 0.44 |
Crack | 79.62 | 83.02 | 23.83 | 17.56 | 0.26 | ||
Fault | 61.27 | 99.74 | 20.04 | 0.21 | −3.68 | ||
Ride | 34.89 | 38.69 | 39.55 | 37.82 | 0.66 | ||
LSTM | PCI | 58.06 | 54.13 | 23.18 | 21.12 | 0.70 | |
Crack | 79.62 | 67.67 | 23.83 | 20.95 | −0.26 | ||
Fault | 61.27 | 62.78 | 20.04 | 14.30 | 0.62 | ||
Ride | 34.89 | 36.27 | 39.55 | 40.48 | 0.86 | ||
COM | DOT | PCI | 68.71 | 78.66 | 19.61 | 17.9 | 0.11 |
Crack | 62.91 | 78.08 | 19.74 | 15.75 | −0.05 | ||
Rut | 60.44 | 98.36 | 17.35 | 0.57 | −4.7 | ||
Ride | 78.64 | 74.51 | 32.41 | 34.35 | −0.02 | ||
LSTM | PCI | 68.71 | 72.48 | 19.61 | 17.55 | 0.50 | |
Crack | 62.91 | 66.01 | 19.74 | 16.88 | 0.39 | ||
Rut | 60.44 | 61.92 | 17.35 | 15.35 | 0.19 | ||
Ride | 78.64 | 84.23 | 32.41 | 29.03 | 0.43 | ||
AC | DOT | PCI | 71.02 | 82.95 | 19.58 | 17.73 | 0.31 |
Crack | 64.11 | 80.88 | 24.52 | 16.02 | 0.15 | ||
Rut | 64.05 | 98.42 | 15.14 | 0.47 | −5.11 | ||
Ride | 81.51 | 77.29 | 29.83 | 33.73 | 0.55 | ||
LSTM | PCI | 71.02 | 72.89 | 19.58 | 17.36 | 0.61 | |
Crack | 64.11 | 67.08 | 24.52 | 21.78 | 0.35 | ||
Rut | 64.05 | 63.74 | 15.14 | 12.33 | 0.19 | ||
Ride | 81.51 | 83.28 | 29.83 | 27.65 | 0.61 |
Pavement Types | DOT vs. Actual | LSTM vs. Actual |
PCC | −10.57 | 3.93 |
AC | −11.93 | −1.87 |
COM | −9.94 | −3.77 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Hosseini, S.A.; Alhasan, A.; Smadi, O. Use of Deep Learning to Study Modeling Deterioration of Pavements a Case Study in Iowa. Infrastructures 2020, 5, 95. https://doi.org/10.3390/infrastructures5110095
Hosseini SA, Alhasan A, Smadi O. Use of Deep Learning to Study Modeling Deterioration of Pavements a Case Study in Iowa. Infrastructures. 2020; 5(11):95. https://doi.org/10.3390/infrastructures5110095
Chicago/Turabian StyleHosseini, Seyed Amirhossein, Ahmad Alhasan, and Omar Smadi. 2020. "Use of Deep Learning to Study Modeling Deterioration of Pavements a Case Study in Iowa" Infrastructures 5, no. 11: 95. https://doi.org/10.3390/infrastructures5110095
APA StyleHosseini, S. A., Alhasan, A., & Smadi, O. (2020). Use of Deep Learning to Study Modeling Deterioration of Pavements a Case Study in Iowa. Infrastructures, 5(11), 95. https://doi.org/10.3390/infrastructures5110095