Thermo-Mechanical Pavement Deformation Prediction Using Monte Carlo Simulation and Regularized Neural Networks: A Comparative Study of FFNN and LSTM Models

International Journal of Civil Engineering

© 2025 by SSRG - IJCE Journal

Volume 12 Issue 11

Year of Publication : 2025

Authors : Oumaima EL ABIDI, Mouna EL MKHALET, Nouzha LAMDOUAR

10.14445/23488352/IJCE-V12I11P106

How to Cite?

Oumaima EL ABIDI, Mouna EL MKHALET, Nouzha LAMDOUAR, "Thermo-Mechanical Pavement Deformation Prediction Using Monte Carlo Simulation and Regularized Neural Networks: A Comparative Study of FFNN and LSTM Models," SSRG International Journal of Civil Engineering, vol. 12,  no. 11, pp. 68-88, 2025. Crossref, https://doi.org/10.14445/23488352/IJCE-V12I11P106

Abstract:

This study addresses the challenge of predicting pavement performance under the combined influence of traffic
induced mechanical loads and daily thermal variations, a critical issue for road infrastructure in Morocco, where harsh climatic conditions and increasing traffic intensities exacerbate pavement deterioration. Traditional monitoring methods, such as visual inspections or simplified mechanical models, remain limited in their ability to capture the complexity and uncertainty inherent to thermo mechanical interactions. In contrast, artificial intelligence methods, particularly neural networks, have shown strong potential for modeling nonlinear phenomena and improving predictive accuracy in pavement engineering. Building on this perspective, the present research develops a predictive framework that integrates two constitutive equations reflecting thermo mechanical interactions, solved through deep learning architectures including feed forward neural networks and long short term memory networks, with and without dropout regularization. The study pursues a dual objective: to compare the predictive performance and robustness of these models, and to assess the reliability of their associated uncertainties, ultimately aiming to provide actionable insights for predictive pavement management and maintenance planning.

Keywords:

Artificial Intelligence, Artificial Neural Network, FFNN, LSTM, Pavement Deformation, Pavement Performance Prevision.

References:

[1] T.A. Cruse, Reliability Based Mechanical Design, CRC Press, pp. 1 341, 1997.
[Google Scholar] [Publisher Link]
[2] Sameh S. Abd elfattah, Ahmed I. Abu Elmaat, and Ibrahim H. Hashim, “Reliability Analysis of Flexible Pavement Using Crude Monte Carlo Simulation,” ERJ. Engineering Research Journal, vol. 45, no. 3, pp. 447 456, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Nawras Shatnawi, Mohammed Taleb Obaidat, and Amjad Al Sharideah, “Modeling Road Pavement Rutting Using Artificial Neural Network and Conventional Measurements,” Transportation Research Record: Journal of the Transportation Research Board, vol. 2677, no. 2, pp. 973 984, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Chunru Cheng et al., “Predicting Rutting Development of Pavement with Flexible Overlay Using Artificial Neural Network,” Applied Science, vol. 13, no. 12, pp. 1 15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Claude Nadeau, and Yoshua Bengio, “Inference for the Generalization Error,” Machine Learning, vol. 52, pp. 239 281, 2003.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Mingyang Gong, Yiren Sun, and Jingyun Chen, “Analysis of Coupled Thermo Mechanical Response and Damage Behaviour of Curved Ramp Bridge Deck Pavement using a 3D Multiscale Method,” Road Materials and Pavement Design, vol. 25, no. 11, pp. 2335 2357, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Xu Li et al., “Analysis of Asphalt Pavement Response to Long Longitudinal Slope Considering the Influence of Temperature Fields,” Materials, vol. 18, no. 15, pp. 1 18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Rouba Joumblat et al., “State of the Art Review on Permanent Deformation Characterization of Asphalt Concrete Pavements,” Sustainability, vol. 15, no. 2, pp. 1 34, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Maureen Caudill, “Neural Networks Primer, Part I,” AI Expert, vol. 2, no. 12, pp. 46‑52, 1987.
[Google Scholar] [Publisher Link]
[10] Jidong Yang, “Road Crack Condition Performance Modeling using Recurrent Markov Chains and Artificial Neural Networks,” Digital Commans, University of South Florida, pp. 1 111, 2024.
[Google Scholar] [Publisher Link]
[11] Yingjie Tian, and Yuqi Zhang, “A Comprehensive Survey on Regularization Strategies in Machine Learning,” Informatioin Fusion, vol. 80, pp. 146 166, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, pp. 1 775, 2016.
[Google Scholar] [Publisher Link]
[13] Nitish Srivastava, “Improving Neural Networks with Dropout,” Master’s Thesis, University of Toronto, pp. 1 26, 2013.
[Google Scholar] [Publisher Link]
[14] Sepp Hochreiter, and Jürgen Schmidhuber, “Long Short Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735‑1780, 1997.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Klaus Greff et al., “LSTM: A Search Space Odyssey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 10, pp. 2222‑2232, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Tianjie Zhang et al., “LSTM+MA: A Time Series Model for Predicting Pavement IRI,” Infrastructures, vol. 10, no. 1, pp. 1 16, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Micah Mers et al., “Recurrent Neural Networks for Pavement Performance Forecasting: Review and Model Performance Comparison,” Transportation Research Record: Journal of the Transportation Research Board, vol. 2677, no 1, pp. 610‑624, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Samik Raychaudhuri, “Introduction to Monte Carlo Simulation,” 2008 Winter Simulation Conference, Miami, FL, USA, pp. 91
100, 2008.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Deep Learning: Theory, Algorithms, and Implications, dl2025. [Online]. Available: https://dl2025.fbk.eu/
[20] Andrew. Y. Ng, “Feature Selection, L1 vs. L2 Regularization, and Rotational Invariance,” Twenty First International Conference on Machine Learning ICML ’04, Banff, Alberta, Canada, pp. 1 78, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Nithish Srivastava et al., “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929 1958, 2014.
[Google Scholar] [Publisher Link]
[22] Yarin Gal, and Zoubin Ghahramani, “Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning,” Proceedings of the 33rd International Conference on International Conference on Machine Learning, vol. 48, pp. 1050 1059, 2016.
[Google Scholar] [Publisher Link]
[23] Lutz Prechelt, “Automatic Early Stopping Using Cross Validation: Quantifying the Criteria,” Neural Networks, vol. 11, no. 4, pp. 761 767, 1998.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Connor Shorten, and Taghi M. Khoshgoftaar, “A Survey on Image Data Augmentation for Deep Learning,” Journal of Big Data, vol. 6, pp. 1 48, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Sergey Ioffe, and Christian Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” Arxiv Preprint, pp. 1 11, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Rafael Müller, Simon Kornblith, and Geoffrey E. Hinton, “When Does Label Smoothing Help?,” Advances in Neural Information Processing Systems, pp. 1 10, 2019.
[Google Scholar] [Publisher Link]
[27] Chris M. Bishop, “Training with Noise is Equivalent to Tikhonov Regularization,” Neural Compution, vol. 7, no. 1, pp. 108‑116, 1995.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Hongyi Zhang et al., “Mixup: Beyond Empirical Risk Minimization,” Arxiv Preprint, pp. 1 13, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Song Han, Huizi Mao, and William J. Dally, “Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding,” Arxiv Preprint, pp. 1 14, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Pamela Carreno, Dana Kulic, and Michael Burke, “Adapting Neural Models with Sequential Monte Carlo Dropout,” Proceedings of The 6th Conference on Robot Learning, PMLR, pp. 1542‑1552, 2023.
[Google Scholar] [Publisher Link]
[31] Stephan Thaler et al., “Active Learning Graph Neural Networks for Partial Charge Prediction of Metal Organic Frameworks via Dropout Monte Carlo,” NPJ Computational Materials, vol. 10, pp. 1 10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Hongchen Liu et al., “Multi Fidelity Deep Neural Network with Monte Carlo Dropout Technique for Uncertainty Aware Risk Recognition of Backward Erosion Piping in Dikes,” Applied Soft Computing, vol. 166, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Alex Kendall, and Yarin Gal, “What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?,” Advances in Neural Information Processing Systems, pp. 1 11, 2017.
[Google Scholar] [Publisher Link]
[34] Yarin Gal, “Uncertainty in Deep Learning,” University of Cambridge, pp. 1 174, 2016.
[Google Scholar] [Publisher Link]
[35] Ian Osband et al., “Deep Exploration via Bootstrapped DQN,” Advances in Neural Information Processing Systems, pp. 1 9, 2016.
[Google Scholar] [Publisher Link]
[36] Yaniv Ovadia et al., “Can you Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift,” Advances in Neural Information Processing Systems, pp. 1 12, 2019.
[Google Scholar] [Publisher Link]
[37] Meire Fortunato, Charles Blundell, and Oriol Vinyals, “Bayesian Recurrent Neural Networks,” Arxiv Preprint, pp. 1 14, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Menglan Zeng, and Donald H. Shields, “Nonlinear Thermal Expansion and Contraction of Asphalt Concrete,” Canadian Journal of Civil Engineering, vol. 26, no. 1, pp. 26‑34, 1999.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Rosie Shier, Statistics: 1.1 Paired T Tests, mathematics Learing Support Centre, 2004. [Online]. Available: https://www.statstutor.ac.uk/resources/uploaded/paired t test.pdf
[40] Yushun Dong et al., “Forecasting Pavement Performance with a Feature Fusion LSTM BPNN Model,” Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, China, pp. 1953 1962, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[41] Nima Amini, and Qinqin Zhu, “Fault Detection and Diagnosis with a Novel Source Aware Autoencoder and Deep Residual Neural Network,” Neurocomputing, vol. 488, pp. 618‑633, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[42] Sepideh Emami Tabrizi et al., “Hourly Road Pavement Surface Temperature Forecasting Using Deep Learning Models,” Journal of Hydrology, vol. 603, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[43] Meng Zhang et al., “A Deep Learning Approach for Enhanced Real Time Prediction of Winter Road Surface Temperatures in High
Altitude Mountain Areas,” Promet Traffic Transportation, vol. 36, no. 5, pp. 958‑972, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[44] Mouncif Sarroukh et al., “Effect of Global Warming and New Equivalent Temperature Zoning Maps for Asphalt Pavement Design in Morocco,” Energy and Buildings, vol. 303, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[45] Bishal Karki et al., “Neural Network Approach for Fatigue Crack Prediction in Asphalt Pavements Using Falling Weight Deflectometer Data,” Applied Science, vol. 15, no. 7, pp. 1 17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]