Predicting Resilient Modulus of Cementitiously Stabilized Subgrade Soils Using Neural Network, Support Vector Machine, and Gaussian Process Regression
Publication: International Journal of Geomechanics
Volume 21, Issue 6
Abstract
Artificial neural network (ANN), support vector machine (SVM), and Gaussian process regression (GPR) were developed in this study for predicting resilient modulus (Mr) values of cementitously stabilized subgrade soils. A database was developed using laboratory test results on 160 specimens prepared by using four soils stabilized with three cementitious additives, namely, lime (3%, 6%, 9%), CFA (5%, 10%, 15%), and CKD (5%, 10%, 15%). Of these, 120 specimens (development dataset) prepared using three types of soils were used in development, and the remaining 40 specimens (validation dataset) were used in the validation of the developed models. A commercial software, MATLAB, was leveraged to develop three ANN models (radial basis function network/RBFN; a multilayer perceptrons network/MLPN with one hidden layer; and MLPN with two hidden layers); four SVM models (linear, quadratic, cubic, and radial basis function kernels); and three GPR models (rational quadratic, Matérn, and exponential kernels) by using codes written in MATLAB language. The strengths and weaknesses of the developed models were examined by comparing the predicted Mr values with the observed/experimental values with respect to the mean squared error (MSE) values and determination coefficient (R2) values. Through comprehensive comparison among these three types of models, an MLPN model with one hidden layer was determined as the best performing model developed in this study. It can be used to predict Mr of cementitiously stabilized subgrade soils for Level 2 pavement design applications. This model as well as the other models could be refined using an enriched database.
Get full access to this article
View all available purchase options and get full access to this article.
References
AASHTO. 1986. Standard specifications for transportation materials and methods of sampling and testing. Washington, DC: AASHTO.
AASHTO. 2003. Standard specifications for transportation materials and methods of sampling and testing. Washington, DC: AASHTO.
AASHTO. 2015. Mechanistic-empirical pavement design guide: A manual of practice. Washington, DC: AASHTO.
Abdessalem, A. B., N. Dervilis, D. J. Wang, and K. Worden. 2017. “Automatic kernel selection for gaussian processes regression with approximate Bayesian computation and sequential Monte Carlo.” Front. Built. Environ. 3: 52. https://doi.org/10.3389/fbuil.2017.00052.
Bengio, Y. 2013. “Practical recommendations for gradient-based training of deep architectures.” In Neural networks: Tricks of the trade, edited by G. Montavon, G. B. Orr, and K. R. Müller, 437–478. Berlin: Springer.
Cao, Z., and Y. Wang. 2014. “Bayesian model comparison and selection of spatial correlation functions for soil parameters.” Struct. Saf. 49: 10–17. https://doi.org/10.1016/j.strusafe.2013.06.003.
Cerato, A. B., and A. J. Lutenegger. 2002. “Determination of surface are of fine-grained soils by the ethylene glycol monoethyl ether (EGME) method.” ASTM Geotech. Testing J. 25 (3): 1–7. https://doi.org/10.1520/GTJ11087J.
Cheng, L., S. Ramchandran, T. Vatanen, N. Lietzén, R. Lahesmaa, A. Vehtari, and H. Lähdesmäki. 2019a. “An additive gaussian process regression model for interpretable non-parametric analysis of longitudinal data.” Nat. Commun. 10 (1): 1798. https://doi.org/10.1038/s41467-019-09785-8.
Cheng, M. Y., D. Prayogo, and Y. W. Wu. 2019b. “Prediction of permanent deformation in asphalt pavements using a novel symbiotic organisms search-least squares support vector regression.” Neural Comput. Appl. 31 (10): 6261–6273. https://doi.org/10.1007/s00521-018-3426-0.
Ding, S. F., W. K. Jia, C. Y. Su, X. L. Liu, and J. R. Chen. 2010. “An improved BP neural network algorithm based on factor analysis.” J. Converg. Inf. Technol. 5 (4): 103–108.
Dong, V. D., A. Hojjat, L. Hai-Bang, M. L. Lu, M. L. Vuong, L. Tien-Thinh, and T. P. Binh. 2020. “A sensitivity and robustness analysis of GPR and ANN for high-performance concrete compressive strength prediction using a Monte Carlo simulation.” Sustainability 12 (3): 830. https://doi.org/10.3390/su12030830.
Elfwing, S., E. Uchibe, and K. Doya. 2018. “Sigmoid-weighted linear units for neural network function approximation in reinforcement learning.” Neural Networks 107: 3–11. https://doi.org/10.1016/j.neunet.2017.12.012.
Elias, M. B., and H. H. Titi. 2006. “Evaluation of resilient modulus model parameter for mechanistic-empirical pavement design.” Transp. Res. Rec. 1967 (1): 89–100. https://doi.org/10.1177/0361198106196700110.
George, K. R. 1992. “Resilient testing of soils using gyratory testing machine.” Transp. Res. Rec. 1369: 63–72.
Gholami, R., and N. Fakhari. 2017. “Support vector machine: Principles, parameters, and applications.” Chap. 27 in Handbook of neural computation, 515–535. Amsterdam, Netherlands: Elsevier.
Ghosh, D., A. Singh, K. K. Shukla, and K. Manchanda. 2019. “Extended Karush-Kuhn-Tucker condition for constrained interval optimization problems and its application in support vector machines.” Inf. Sci. 504: 276–292. https://doi.org/10.1016/j.ins.2019.07.017.
Goh, A. T. C., and S. H. Goh. 2007. “Support vector machines: Their use in geotechnical engineering as illustrated using seismic liquefaction data.” Comput. Geotech. 34 (5): 410–421. https://doi.org/10.1016/j.compgeo.2007.06.001.
Golub, G. H., P. C. Hansen, and D. P. O’Leary. 1999. “Tikhonov regularization and total least squares.” SIAM J. Matrix Anal. Appl. 21 (1): 185–194. https://doi.org/10.1137/S0895479897326432.
Heidaripanah, A., M. Nazemi, and F. Soltani. 2017. “Prediction of resilient modulus of lime-treated subgrade soil using different kernels of support vector machine.” Int. J. Geomech. 17 (2): 06016020. https://doi.org/10.1061/(ASCE)GM.1943-5622.0000723.
Heo, Y., and V. M. Zavala. 2012. “Gaussian process modeling for measurement and verification of building energy savings.” Energy Build. 53: 7–18. https://doi.org/10.1016/j.enbuild.2012.06.024.
Hossain, M. S. 2009. “Estimation of subgrade resilient modulus for Virginia soil.” Transp. Res. Rec. 2101 (1): 98–109. https://doi.org/10.3141/2101-12.
Ji, R., N. Siddiki, T. Nantung, and D. Kim. 2014. “Evaluation of resilient modulus of subgrade and base materials in Indiana and its implementation in MEPDG.” Sci. World J. 2014: 372838. https://doi.org/10.1155/2014/372838.
Khoury, N., R. Brooks, S. Y. Boeni, and D. Yada. 2013. “Variation of resilient modulus, strength, and modulus of elasticity of stabilized soils with postcompaction moisture contents.” J. Mater. Civ. Eng. 25 (2): 160–166. https://doi.org/10.1061/(ASCE)MT.1943-5533.0000574.
Khoury, N., and M. Maalouf. 2018. “Prediction of resilient modulus from post-compaction moisture content and physical properties using support vector regression.” Geotech. Geol. Eng. 36 (5): 2881–2892. https://doi.org/10.1007/s10706-018-0510-2.
Kim, D.-S., G.-C. Kweon, and K.-H. Lee. 1997. “Alternative method of determining resilient modulus of compacted subgrade soils using free-free resonant column test.” Transp. Res. Rec. 1577 (1): 62–69. https://doi.org/10.3141/1577-08.
Kim, K., D. Lee, and I. Essa. 2011. “Gaussian process regression flow for analysis of motion trajectories.” In Proc., 2011 Int. Conf. on Computer Vision, 1164–1171. New York: IEEE.
Kumar, M., M. R. Bhatt, and P. Samui. 2014. “Modeling of elastic modulus of jointed rock mass: Gaussian process regression approach.” Int. J. Geomech. 14 (3): 06014001. https://doi.org/10.1061/(ASCE)GM.1943-5622.0000318.
Lázaro-Gredilla, M., and A. Figueiras-Vidal. 2009. “Inter-domain Gaussian processes for sparse inference using inducing features.” In Proc., 23rd Annual Conf. on Neural Information Processing Systems, edited by Y. Bemgio, 1087–1095. San Diego, CA: Neural Information Processing Systems Foundation, Inc.
Lee, W., N. C. Bohra, A. G. Altschaeffl, and T. D. White. 1997. “Resilient modulus of cohesive soils.” J. Geotech. Geoenviron. Eng. 123 (2): 131–136. https://doi.org/10.1061/(ASCE)1090-0241(1997)123:2(131).
Li, Q., D. X. Xiao, K. C. P. Wang, K. D. Hall, and Y. Qiu. 2011. “Mechanistic-empirical pavement design guide (MEPDG): A bird’s-eye view.” J. Mod. Transp. 19 (2): 114–133. https://doi.org/10.1007/BF03325749.
Liang, R. Y., S. Rabab’ah, and M. Khasawneh. 2008. “Predicting moisture-dependent resilient modulus of cohesive soils using soil suction concept.” J. Transp. Eng. 134 (1): 34–40. https://doi.org/10.1061/(ASCE)0733-947X(2008)134:1(34).
Linker, R., and I. Seginer. 2004. “Greenhouse temperature modeling: A comparison between sigmoid neural networks and hybrid models.” Math. Comput. Simul. 65 (1–2): 19–29. https://doi.org/10.1016/j.matcom.2003.09.004.
Maalouf, M., N. Khoury, and T. B. Trafalis. 2008. “Support vector regression to predict asphalt mix performance.” Int. J. Numer. Anal. Methods Geomech. 32 (16): 1989–1996. https://doi.org/10.1002/nag.718.
Mamatha, K. H., and S. V. Dinesh. 2017. “Resilient modulus of black cotton soil.” Int. J. Pavement Res. Technol. 10 (2): 171–184. https://doi.org/10.1016/j.ijprt.2017.01.008.
Mohammad, L. N., B. S. Huang, A. Puppala, and A. Allen. 1999. “Regression model for resilient modulus of subgrade soils.” Transp. Res. Rec. 1687 (1): 47–54. https://doi.org/10.3141/1687-06.
Mohammad, L. N., M. D. Nazzal, M. Y. Abu-Farsakh, and K. Alshibli. 2009. “Estimation of subgrade soils resilient modulus from in-situ devices test results.” J. Test Eval. 37 (3): 245–253. https://doi.org/10.1520/JTE101993.
Nhat-Duc, H., P. Anh-Duc, N. Quoc-Lam, and P. Quang-Nhat. 2016. “Estimating compressive strength of high-performance concrete with gaussian process regression model.” Adv. Civ. 2016: 2861380. https://doi.org/10.1155/2016/2861380.
Ooi, P. S. K., R. Archilla, and K. G. Sandefur. 2004. “Resilient modulus models for compacted cohesive soils.” Transp. Res. Rec. 1874 (1): 115–124. https://doi.org/10.3141/1874-13.
Pasolli, L., F. Melgani, and E. Blanzieri. 2010. “Gaussian process regression for estimating chlorophyll concentration in subsurface waters from remote sensing data.” IEEE Geosci. Remote Sens. Lett. 7 (3): 464–468. https://doi.org/10.1109/LGRS.2009.2039191.
Puppala, A., and L. N. Mohammad. 1997. “A regression model for better characterization of resilient properties of subgrade soils.” In Proc., 8th Int. Conf. on Asphalt Pavements, 859–866. Seattle: Univ. of Washington.
Que, Q., and M. Belkin. 2020. “Back to the future: Radial basis function network revisited.” IEEE Trans. Pattern Anal. Mach. Intell. 42 (8): 1856–1867. https://doi.org/10.1109/TPAMI.2019.2906594.
Rahim, A. M. 2005. “Subgrade soil index properties to estimate resilient modulus for pavement design.” Int. J. Pavement Eng. 6 (3): 163–169. https://doi.org/10.1080/10298430500140891.
Rashidi, M., R. S. Ashtiani, J. Si, R. P. Izzo, and M. McDaniel. 2018. “A practical approach for the estimation of strength and resilient properties of cementitious materials.” Transp. Res. Rec. 2672 (52): 152–163. https://doi.org/10.1177/0361198118769900.
Rasmussen, C. E., and C. K. Williams. 2006. Gaussian processes for machine learning. Cambridge, MA: MIT Press.
Rout, R., P. Ruttanapormakul, S. Valluru, and A. Puppala. 2012. “Resilient moduli behavior of lime-cement treated subgrade soils.” In GeoCongress 2012: State of the Art and Practice in Geotechnical Engineering, Geotechnical Special Publication 225, edited by R. D. Hryciw, A. Athanasopoulos-Zekkos, and N. Yesiller, 1428–1437. Reston, VA: ASCE.
Saini, I., and P. Chandramouli. 2013. “Prediction of elastic modulus of high strength concrete by gaussian process regression.” Int. J. Sci. Eng. Res. 4 (5): 197–198.
Salahudeen, A. B., T. S. Ijimdiya, A. O. Eberemu, and K. J. Osinubi. 2018. “Artificial neural networks prediction of compaction characteristics of black cotton soil stabilized with cement kiln dust.” J. Soft Comput. Civ. Eng. 2 (3): 50–71. https://doi.org/10.22115/SCCE.2018.128634.1059.
Schulz, E., M. Speekenbrink, and A. Krause. 2018. “A tutorial on gaussian process regression: Modelling, exploring, and exploiting functions.” J. Math. Psychol. 85: 1–16. https://doi.org/10.1016/j.jmp.2018.03.001.
Schwenker, F., H. A. Kestler, and G. Palm. 2001. “Three learning phases for radial-basis-function networks.” Neural Networks 14 (4–5): 439–458. https://doi.org/10.1016/S0893-6080(01)00027-2.
Smola, A. J., and B. Schölkopf. 2004. “A tutorial on support vector regression.” Stat. Comput. 14 (3): 199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88.
Solanki, P. 2010. “Characterization of cementitiously stabilized subgrades for mechanistic-empirical pavement design.” Ph.D. thesis, School of Civil Engineering and Environmental Sciences, Univ. of Oklahoma.
Twomey, J. M., and A. E. Smith. 1995. “Performance measures, consistency, and power for artificial neural network models.” Math. Comput. Modell. 21 (1–2): 243–258. https://doi.org/10.1016/0895-7177(94)00207-5.
Van der Vaart, A., and H. van Zanten. 2011. “Information rates of nonparametric gaussian process methods.” J. Mach. Learn. Res. 12 (2): 2095–2119.
Vapnik, V. N. 1995. The nature of statistical learning. New York: Springer-Verlag.
Williams, C. K. I., and D. Barber. 1998. “Bayesian classification with Gaussian processes.” IEEE Trans. Pattern Anal. Mach. Intell. 20 (12): 1342–1351. https://doi.org/10.1109/34.735807.
Wilson, A. G., and R. P. Adams. 2013. “Gaussian process kernels for pattern discovery and extrapolation.” In Proc., 30th Int. Conf. on Machine Learning, edited by S. Dasgupta, and D. McAllester, 1067–1075. Cambridge, MA: PMLR.
Yang, X., and J. Han. 2013. “Analytical model for resilient modulus and permanent deformation of geosynthetic-reinforced unbound granular material.” J. Geotech. Geoenviron. Eng. 139 (9): 1443–1453. https://doi.org/10.1061/(ASCE)GT.1943-5606.0000879.
Zaman, M., P. Solanki, A. Ebrahimi, and L. White. 2010. “Neural network modeling of resilient modulus using routine subgrade soil properties.” Int. J. Geomech. 10 (1): 1–12. https://doi.org/10.1061/(ASCE)1532-3641(2010)10:1(1).
Zapata, C., and C. Cary. 2009. “A new generation of resilient modulus characterization of unbound materials.” In Contemporary Topics in Ground Modification, Problem Soils, and Geo-Support, Geotechnical Special Publication 187, edited by M. Iskander, D. F. Laefer, and M. H. Hussein, 377–384. Reston, VA: ASCE.
Zeghal, M., and W. Khogali. 2005. “Predicting the resilient modulus of unbound granular materials by neural networks.” In Bearing Capacity of Roads and Airport Conf., 1–9. Trondheim, Norway: Norwegian University of Science and Technology.
Zhang, C. H., Y. J. Tian, and N. Y. Deng. 2010. “The new interpretation of support vector machines on statistical learning theory.” Sci. China Ser. A: Math. 53 (1): 151–164. https://doi.org/10.1007/s11425-010-0018-6.
Zhang, X., and Q. Song. 2015. “A multi-label learning based kernel automatic recommendation method for support vector machine.” PLoS One 10 (4): 0120455. https://doi.org/10.1371/journal.pone.0120455.
Information & Authors
Information
Published In
International Journal of Geomechanics
Volume 21 • Issue 6 • June 2021
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Jul 6, 2020
Accepted: Jan 8, 2021
Published online: Mar 24, 2021
Published in print: Jun 1, 2021
Discussion open until: Aug 24, 2021
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.