Utilizing Gaussian Process Regression Model Enhanced by Metaheuristic Algorithms to Forecast Undrained Shear Strength

Jian  Zhang

doi:10.6180/jase.202504_28(4).0008

Utilizing Gaussian Process Regression Model Enhanced by Metaheuristic Algorithms to Forecast Undrained Shear Strength

Civil Engineering

Jian ZhangThis email address is being protected from spambots. You need JavaScript enabled to view it.

College of Civil Engineering, Nanyang Normal University, Nanyang 473061, Henan, China

Received: December 23, 2023
Accepted: April 24, 2024
Publication Date: June 10, 2024

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202504_28(4).0008

Undrained shear strength is a fundamental property of soil that characterizes its ability to resist deformation under load without allowing water drainage time. This property is crucial in geotechnical engineering, as it influences the stability of structures and the behavior of foundations. Traditional and laboratory methods for calculating undrained shear strength involve direct shear tests, unconfined compression tests, and vane shear tests. These methods are time-consuming and labor-intensive, limiting their practicality, especially when dealing with large datasets or complex soil compositions. Machine learning (ML)-based models offer a promising alternative by predicting undrained shear strength with greater efficiency and accuracy. In this investigation, Gaussian Process Regression is employed as a core technique to address the challenges of developing an ML model. Additionally, the study incorporates two different meta-heuristic optimization methods, specifically Artificial Rabbits Optimization and Runge-Kutta optimization, to achieve the best possible results. The evaluations undeniably validate the GPRK model’s unmistakable superiority. It achieves an impressive maximum R² value of 99.3% in the training phase of prediction, showcasing exceptional explanatory capability and exhibiting notably low MSE and RMSE values of 65.727 and 95.242, respectively. This model indicates minimal prediction deviation when contrasted with the GPR and GPAR models.

Keywords: Undrained Shear Strength; Gaussian Process Regression; Artificial Rabbits Optimization; Runge-Kutta optimization

[1] R. J. Chandler, (1988) “The in-situ measurement of the undrained shear strength of clays using the field vane" Vane shear strength testing in soils: field and labo ratory studies 1014: 13–44.
[2] K. N. Prasad, S. Triveni, T. Schanz, and L. T. S. Na garaj, (2007) “Sample disturbance in soft and sensitive clays: analysis and assessment" Marine Georesources and Geotechnology 25: 181–197.
[3] B. D. Buò, J. Selänpää, T. T. Länsivaara, and M. D’Ignazio, (2019) “Evaluation of sample quality from dif ferent sampling methods in Finnish soft sensitive clays" Canadian Geotechnical Journal 56: 1154–1168.
[4] Q.-A. Tran, W. Solowski, M. Karstunen, and L. Korkiala-Tanttu, (2017) “Modelling of fall-cone tests with strain-rate effects" Procedia Engineering 175: 293–301.
[5] Q.-A. Tran and W. Sołowski, (2019) “Generalized Inter polation Material Point Method modelling of large defor mation problems including strain-rate effects–Application to penetration and progressive failure problems" Com puters and Geotechnics 106: 249–265.
[6] F. Masoumi, S. Najjar-Ghabel, A. Safarzadeh, and B. Sadaghat, (2020) “Automatic calibration of the ground water simulation model with high parameter dimensional ity using sequential uncertainty fitting approach" Water Supply 20: 3487–3501.
[7] M. M. E. Zumrawi, (2012) “Prediction of CBR value from index properties of cohesive soils":
[8] S. Hansbo. New approach to the determination of the shear strength of clay by the fall-cone test. Statens geotekniska institut, 1957.
[9] R.Larsson,(1980) “Undrained shear strength in stability calculation of embankments and foundations on soft clays" Canadian Geotechnical Journal 17: 591–602.
[10] B. Sadaghat, G. G. Tejani, and S. Kumar, (2023) “Pre dict the maximum dry density of soil based on individual and hybrid methods of machine learning" Advances in Engineering and Intelligence Systems 2:
[11] P. Samui, (2008) “Prediction of friction capacity of driven piles in clay using the support vector machine" Canadian Geotechnical Journal 45: 288–295.
[12] R. Sarkhani Benemaran, M. Esmaeili-Falak, and H. Katebi, (2022) “Physical and numerical modelling of pile stabilised saturated layered slopes" Proceedings of the Institution of Civil Engineers-Geotechnical Engi neering 175(5): 523–538.
[13] R. Sarkhani Benemaran, M. Esmaeili-Falak, and H. Katebi, (2022) “Physical and numerical modelling of pile stabilised saturated layered slopes" Proceedings of the Institution of Civil Engineers-Geotechnical Engi neering 175(5): 523–538.
[14] H.-B. Ly and B. T. Pham, (2020) “Prediction of shear strength of soil using direct shear test and support vector machine model" The Open Construction Building Technology Journal 14:
[15] D. P. Kanungo, S. Sharma, and A. Pain, (2014) “Artifi cial Neural Network (ANN) and Regression Tree (CART) applications for the indirect estimation of unsaturated soil shear strength parameters" Frontiers of earth science 8: 439–456.
[16] D.Padmini, K. Ilamparuthi, and K. P. Sudheer, (2008) “Ultimate bearing capacity prediction of shallow foun dations on cohesionless soils using neurofuzzy models" Computers and Geotechnics 35: 33–46.
[17] R. S. Benemaran and M. Esmaeili-Falak, (2020) “Op timization of cost and mechanical properties of concrete with admixtures using MARS and PSO" Computers and Concrete, An International Journal 26(4): 309–316.
[18] S.K.DasandP.K.Basudhar,(2006)“Undrained lateral load capacity of piles in clay using artificial neural net work" Computers and Geotechnics 33(8): 454–459.
[19] M. Esmaeili-Falak, H. Katebi, M. Vadiati, and J. Adamowski, (2019) “Predicting triaxial compressive strength and Young’s modulus of frozen sand using arti f icial intelligence methods" Journal of Cold Regions Engineering 33(3): 04019007.
[20] S. B. Ikizler, M. Aytekin, M. Vekli, and F. Kocaba¸s, (2010) “Prediction of swelling pressures of expansive soils using artificial neural networks" Advances in Engineer ing Software 41(4): 647–655.
[21] F. P. Nejad and M. B. Jaksa, (2017) “Load-settlement behavior modeling of single piles using artificial neural networks and CPT data" Computers and Geotechnics 89: 9–21.
[22] J. Yuan, M. Zhao, and M. Esmaeili-Falak. A compara tive study on predicting the rapid chloride permeability of self-compacting concrete using meta-heuristic algorithm and artificial intelligence techniques (Retraction of Vol 23, Pg 753, 2022). 2024.
[23] P. Samui and P. Kurup, (2012) “Multivariate adaptive regression spline and least square support vector machine for prediction of undrained shear strength of clay" Inter national Journal of Applied Metaheuristic Comput ing (IJAMC) 3(2): 33–42.
[24] M. Y. Abu-Farsakh and M. A. H. Mojumder, (2020) “Exploring artificial neural network to evaluate the undrained shear strength of soil from cone penetration test data" Transportation Research Record 2674(4): 11–22.
[25] D. Tien Bui, N.-D. Hoang, and V.-H. Nhu, (2019) “A swarm intelligence-based machine learning approach for predicting soil shear strength for road construction: a case study at Trung Luong National Expressway Project (Viet nam)" Engineering with Computers 35(3): 955–965.
[26] H.Moayedi, M. Gör, M. Khari, L. K. Foong, M. Bahi raei, and D.T.Bui,(2020) “Hybridizing four wise neural metaheuristic paradigms in predicting soil shear strength" Measurement 156: 107576.
[27] M. R. Akbarzadeh, H. Ghafourian, A. Anvari, R. Pourhanasa, and M. L. Nehdi, (2023) “Estimating com pressive strength of concrete using neural electromagnetic f ield optimization" Materials 16(11): 4200.
[28] B. A. Omran, Q. Chen, and R. Jin, (2016) “Compari son of data mining techniques for predicting compressive strength of environmentally friendly concrete" Journal of Computing in Civil Engineering 30(6): 04016029.
[29] R. Gupta, M. A. Kewalramani, and A. Goel, (2006) “Prediction of concrete strength using neural-expert sys tem" Journal of materials in civil engineering 18(3): 462–466.
[30] C. K. Williams and C. E. Rasmussen. Gaussian pro cesses for machine learning. 2. 3. MIT press Cambridge, MA,2006.
[31] S. Chithra, S. S. Kumar, K. Chinnaraju, and F. A. Ash mita, (2016) “A comparative study on the compressive strength prediction models for High Performance Concrete containing nano silica and copper slag using regression analysis and Artificial Neural Networks" Construction and Building Materials 114: 528–535.
[32] H.I. Erdal, O. Karakurt, and E. Namli, (2013) “High performance concrete compressive strength forecasting us ing ensemble models based on discrete wavelet transform" Engineering Applications of Artificial Intelligence 26(4): 1246–1254.
[33] M.Ebden,(2015) “Gaussian processes: A quick introduc tion" arXiv preprint arXiv:1505.02965:
[34] M.-Y. Cheng, C.-C. Huang, and A. F. V. Roy, (2013) “Predicting project success in construction using an evo lutionary Gaussian process inference model" Journal of Civil Engineering and Management 19(sup1): S202 S211.
[35] L. Wang, Q. Cao, Z. Zhang, S. Mirjalili, and W. Zhao, (2022) “Artificial rabbits optimization: A new bio-inspired meta-heuristic algorithm for solving engineering optimiza tion problems" Engineering Applications of Artificial Intelligence 114: 105082.
[36] I. Ahmadianfar, A. A. Heidari, A. H. Gandomi, X. Chu, and H. Chen, (2021) “RUN beyond the metaphor: An efficient optimization algorithm based on Runge Kutta method" Expert Systems with Applications 181: 115079.