Abstract
The soil resilient modulus (MR) is essential to pavement design. This parameter is determined through a costly and time-consuming repeated load triaxial test. Accordingly, prior research focused on implementing complex and interpretable machine learning (ML) models to predict MR directly from soil parameters. However, existing models rely on either black-box machine learning, sacrificing interpretability, or traditional genetic programming (GP) approaches with underfitting issues. This study introduces an innovative approach using the Adaptive Layered Population Structure Genetic Algorithm (ALPS-GA) to develop accurate and fully interpretable MR prediction models for cohesive soils. For this purpose, a soil dataset was adopted from the literature with 891 data points for the A-4, A-6, and A-7-6 soil classes. Three MR prediction equations were developed for each soil class, and the performance of each equation was evaluated using the coefficient of determination (R2), the root mean squared error (RMSE), and the mean absolute error (MAE). The R2 for the developed models ranged from 0.91 to 0.93 for the testing set; the RMSE ranged from 7.10 to 8.63 MPa, and the MAE ranged from 5.10 to 7.2 MPa, reflecting high-accuracy models. A comparative bias-variance analysis was done for the proposed models, and it was concluded that they do not tend to overfit or underfit the data, unlike previous models. Finally, a sensitivity analysis was implemented to investigate the impact of each soil parameter on MR for each soil type.
Similar content being viewed by others
Data Availability
The data utilized in this research has been adopted from previous studies (Hanittinan (2007) and is accessible for reference and analysis via the following link https://books.google.com/books/about/Resilient_Modulus_Prediction_Using_Neura.html?id=5POZnQAACAAJ.
Abbreviations
- AASHTO :
-
American Association of State Highway and Transportation Officials
- ALPS-GA :
-
Adaptive Layered Population Structure Genetic Algorithm
- ANFS-ANN :
-
Adaptive Neuro-Fuzzy Inference Systems Artificial Neural Network
- ANN :
-
Artificial Neural Network
- BP-ANN :
-
Back-Propagation Artificial Neural Network
- CG-ANN :
-
Conjugate Gradient Artificial Neural Network
- EA :
-
evolutionary algorithms
- GP :
-
genetic programming
- GWO :
-
grey wolf optimizer
- HHO :
-
Harris hawks optimization
- KELM :
-
polynomial kernel-based extreme learning machine
- LL :
-
liquid limit
- LSSVM :
-
least square support vector machine
- LTPP :
-
long-term pavement performance
- MAE :
-
mean absolute error
- MEPDG :
-
Mechanistic-Empirical Pavement Design Guide
- MLR :
-
multiple linear regression
- M R :
-
soil resilient modulus
- NCHRP :
-
National Cooperative Highway Research Program
- OMC :
-
optimum moisture content
- PI :
-
plasticity index
- PSO :
-
particle swarm optimization
- qu :
-
unconfined compressive strength
- RBF-SVM :
-
radial bases function kernel-based support vector machine
- RMSE :
-
root mean squared error
- S :
-
degree of soil saturation
- SELM :
-
simple extreme learning machine
- SMA :
-
slime mold algorithm
- SOS :
-
symbiotic organisms search
- SSA :
-
salp swarm algorithm
- wc :
-
water content
References
AASHTO: Guide for mechanistic-empirical design of new and rehabilitated pavement structure. AASHTO, Washington, DC (2004)
AASHTO MEPDG-2: Mechanistic-empirical pavement design guide: a manual of practice. AASHTO, Washington, DC (2015)
AASHTO MEPDG-3: Mechanistic-empirical pavement design guide: a manual of practice. AASHTO, Washington, DC (2020)
AASHTO T307: Determining the resilient modulus of soils and aggregate materials. AASHTO, Washington, D.C. (1999)
ARA (Applied Research Associates) Inc.: Guide for mechanistic empirical pavement design of new and rehabilitated pavement structures. Federal Highway Administration, Washington, DC (2004)
A. Azam, A. Bardhan, . M. R. Kaloop, . P. Samui, F. Alanazi, M. Alzara and A. M. Yosri , "Modeling resilient modulus of subgrade soils using LSSVM optimized with swarm intelligence algorithms." Scientific Reports, 2022
Dong-Gyou, M.S.K.: Development of a constitutive model for resilient modulus of cohesive soils. The Ohio State University (2004)
Elias, M., Titi, H.: Evaluation of resilient modulus model parameters for mechanistic–empirical pavement design. Transp. Res. Rec. 1967(1), 89–100 (2006). https://doi.org/10.1177/0361198106196700110
George, K.P.: Prediction of resilient modulus from soil index properties. The University Of Mississippi, Mississippi (2004)
Goulet, J.A.: Probabilistic machine learning for civil engineers. The MIT Press (2020)
Hanittinan, W.: Resilient modulus prediction using neural network algorithms. The Ohio State University, Ohio (2007)
Hornby, G.S.: "ALPS: the age-layered population structure for reducing the problem of premature convergence," in 8th annual conference on Genetic and evolutionary computation. USA, New York (2006)
Ikeagwuani, C.C., Nwonua, D.C., Nwekeb, C.C.: Resilient modulus descriptive analysis and estimation for fine-grained soils using multivariate and machine learning methods. Int. J. Pavement. Eng. 23(10), 3409–3424 (2022). https://doi.org/10.1080/10298436.2021.1895993
James, G., Witten, D., Hastie, T., Tibshirani, R.: An introduction to statistical learning. Springer (2013)
Ji, R., Siddiki, N., Nantung, T., Kim, D.: Evaluation of resilient modulus of subgrade and base materials in Indiana and its implementation in MEPDG. The Scientific World Journal (2014)
Khasawneh, M.A., Al-jamal, N.F.: Modeling resilient modulus of fine-grained materials using different statistical techniques. Transportation Geotechnics (2019)
Khoury, N.N., Zaman, M.M.: Correlation between resilient modulus, moisture variation, and soil suction for subgrade soils. Transp. Res. Rec. 1874(1), 99–107 (2004)
Kim, D., Siddiki, N.Z.: Simplification of resilient modulus testing for subgrades. Federal Highway Administration, Indiana (2005)
Langdon, W.B., Poli, R., McPhee, N.F., Koza, J.R.: "Genetic programming: an introduction and tutorial, with a survey of techniques and applications," Studies in Computational Intelligence. Springer (2008)
Lee, W., Bohra, N., Altschaeffl, A., White, T.: Resilient modulus of cohesive soils and the effect of freeze–thaw. Can. Geotech. J. 32(4), 559–568 (1995). https://doi.org/10.1139/t95-059
Lee, W., Bohra, N.C., White, T.D., Altschaeffl, A.G.: Resilient modulus of cohesive soils. J. Geotech. Geoenviron. Eng. 132(2), 131–136 (1997)
Li, D., Selig, E.T.: Resilient modulus for fine-grained subgrade soils. J. Geotech. Eng. 120(6), 939–957 (1994). https://doi.org/10.1061/(ASCE)0733-9410
Malik, S., Wadhwa, S.: Preventing premature convergence in genetic algorithm using DGCA and elitist technique. International Journal of Advanced Research in Computer Science and Software Engineering (2014)
Malla, R.B., Joshi, S.: Subgrade resilient modulus prediction models for coarse and fine-grained soils based on long-term pavement performance data. Int. J. Pavement. Eng. 9(6), 431–444 (2008). https://doi.org/10.1080/10298430802279835
Müller, A.C., Guido, S.: Introduction to machine learning with python. O'Reilly Media (2016)
Nazzal, M.D., Mohammad, L.N.: Estimation of resilient modulus of subgrade soils for design of pavement structures. J. Mater. Civ. Eng. 22(7), 726–734 (2010). https://doi.org/10.1061/(ASCE)MT.1943-5533.0000073
Pal, M., Deswal, S.: Extreme learning machine based modeling of resilient modulus of subgrade soils. Geotech. Geol. Eng. 32, 287–296 (2014). https://doi.org/10.1007/s10706-013-9710-y
Poli, R., Langdon, W.B., McPhee, N.F.: A field guide to genetic programming. Lulu Enterprises Ltd., UK (2008)
Rahman, M.M., Gassman, S.L., Islam, K.M.: Effect of moisture content on subgrade soils resilient modulus for predicting pavement rutting. Geosciences (2023)
Sadik, L., Khoshnevisan, S.: "Simplicity vs complexity in machine learning models – focusing on soil resilient modulus prediction," in Geo-Congress 2024, Vancouver, BC (2024)
Sadrossadat, E., Heidaripanah A., Osouli, S.: "Prediction of the resilient modulus of flexible pavement subgrade soils using adaptive neuro-fuzzy inference systems". Constr. Build. Mater. 123, 235–247 (2016a). https://doi.org/10.1016/j.conbuildmat.2016.07.008
Sadrossadat, E., Heidaripanah, A., Ghorbani, B.: Towards application of linear genetic programming for indirect estimation of the resilient modulus of pavements subgrade soils, pp. 139–153. Road Materials and Pavement Design (2016b)
Su, Y., Cui, Y.-J., Dupla, J.-C., Canou, J.: Effect of water content on resilient modulus and damping ratio of fine/coarse soil mixtures with varying coarse grain contents. Transportation Geotechnics (2021)
Thi Hoang, H.-G., Nguyen, T.-A.: "An artificial intelligence approach to predict the resilient modulus of subgrade pavement or unbound material," in 6th International Conference on Geotechnics. Civil Engineering and Structures (2021)
Tokar, A., Johnson, P.: Rainfall-runoff modeling using artificial neural networks. J. Hydrol. Eng. 4(3), 232–239 (1999). https://doi.org/10.1061/(ASCE)1084-0699
Turney, S.: 2023 "Coefficient of determination (R2) | calculation & interpretation". 3 July 2023. [Online]. Available: https://www.scribbr.com/statistics/coefficient-of-determination/. Accessed 7 Oct 2023
Willis, M.J., Hiden, H., Marenbach, P., McKay, B., Montague, G.: Genetic programming: an introduction and survey of applications. Genetic ALgorithms in Engineering Systems : Innovations And Applications, Glasgow (1997)
Zwan, J.V.D.: Machine learning techniques. Bookdown Publishing (2021)
Acknowledgements
I am grateful to all of my professors, colleagues, and researchers with whom I have had the pleasure to work on this and other related projects.
Author information
Authors and Affiliations
Contributions
LS: conceptualization, data analysis, visualization, ALPS-GA model implementation, validation, and sensitivity analysis
Corresponding author
Ethics declarations
Ethics Approval and Consent to Participate
The research described in this manuscript has been conducted in accordance with the ethical guidelines. Informed consent was obtained from the author involved in the study.
Consent for Publication
The author has given his consent for the publication of this manuscript.
Competing Interests
The author declares no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
ESM 1
(CSV 44 kb)
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sadik, L. Developing Prediction Equations for Soil Resilient Modulus Using Evolutionary Machine Learning. Transp. Infrastruct. Geotech. (2023). https://doi.org/10.1007/s40515-023-00342-x
Accepted:
Published:
DOI: https://doi.org/10.1007/s40515-023-00342-x