Abstract
This study systematically presents the application of machine learning (ML) algorithms for constructing a constitutive model for soils. A genetic algorithm is integrated with ML algorithms to determine the global optimum model, and the k-fold cross-validation method is used to enhance the models’ robustness. Three typical ML algorithms with formulations explicitly expressed [i.e., back-propagation neural network (BPNN), extreme learning machine (ELM) and evolutionary polynomial regression (EPR)], and two modelling strategies (i.e. total or incremental stress–strain strategies) are used. A synthetic database is first generated based on a simple constitutive model to objectively evaluate the performance of three ML algorithms and two modelling strategies. Next, the optimum ML algorithm and the well evaluated modelling strategy are applied to experimental tests for examining its robustness. All results indicate that a BPNN-based constitutive model using the incremental stress–strain strategy performs best in modelling the mechanical behaviour of soils in terms of interpolation and extrapolation abilities, followed by ELM and then EPR.
Similar content being viewed by others
References
Badawy MF, Msekh MA, Hamdia KM, Steiner MK, Lahmer T, Rabczuk T (2017) Hybrid nonlinear surrogate models for fracture behavior of polymeric nanocomposites. Probabilist Eng Mech 50:64–75
Basheer IA (2000) Selection of methodology for neural network modeling of constitutive hystereses behavior of soils. Comput-Aided Civ Inf 15:440–458
Cabalar AF, Cevik A (2011) Triaxial behavior of sand–mica mixtures using genetic programming. Expert Syst Appl 38(8):10358–10367
Chang CS, Hicher PY (2005) An elasto-plastic model for granular materials with microstructural consideration. Int J Solids Struct 42(14):4258–4277
Chen RP, Zhang P, Kang X, Zhong ZQ, Liu Y, Wu HN (2019) Prediction of maximum surface settlement caused by EPB shield tunneling with ANN methods. Soils Found 59(2):284–295
Chen RP, Zhang P, Wu HN, Wang ZT, Zhong ZQ (2019) Prediction of shield tunneling-induced ground settlement using machine learning techniques. Front Struct Civ Eng 13(6):1363–1378
Ellis GW, Yao C, Zhao R, Penumadu D (1995) Stress-strain modeling of sands using artificial neural networks. J Geotech Eng 121(5):429–435
Faramarzi A, Javadi AA, Alani AM (2012) EPR-based material modelling of soils considering volume changes. Comput Geosci-UK 48:73–85
Feng XT, Chen BR, Yang CX, Zhou H, Ding X (2006) Identification of visco-elastic models for rocks using genetic programming coupled with the modified particle swarm optimization algorithm. Int J Rock Mech Min 43(5):789–801
Feng XT, Li SJ, Liao HJ, Yang CX (2002) Identification of non-linear stress-strain-time relationship of soils using genetic algorithm. Int J Numer Anal Met 26(8):815–830
Gajo A, Wood M (1999) Severn-Trent sand: a kinematic-hardening constitutive model: the q–p formulation. Geotechnique 49(5):595–614
Gao W, Ge M, Chen D, Wang X (2016) Back analysis for rock model surrounding underground roadways in coal mine based on black hole algorithm. Eng Comput-Germany 32(4):675–689
Gholamy A, Kreinovich V, Kosheleva O (2018) Why 70/30 or 80/20 relation between training and testing sets: a pedagogical explanation. Int J Intell Technol Appl Stat 11(2):105–111
Giustolisi O, Savic DA (2006) A symbolic data-driven technique based on evolutionary polynomial regression. J Hydroinform 8(4):235–237
Guo X, Dias D, Carvajal C, Peyras L, Breul P (2018) Reliability analysis of embankment dam sliding stability using the sparse polynomial chaos expansion. Eng Struct 174:295–307
Habibagahi G, Bamdad A (2003) A neural network framework for mechanical behavior of unsaturated soils. Can Geotech J 40(3):684–693
Hasanipanah M, Noorian-Bidgoli M, Jahed Armaghani D, Khamesi H (2016) Feasibility of PSO-ANN model for predicting surface settlement caused by tunneling. Eng Comput-Germany 32(4):705–715
Hattab M, Hicher PY (2004) Dilating behaviour of overconsolidated clay. Soils Found 44(2):27–40
He S, Li J (2009) Modeling nonlinear elastic behavior of reinforced soil using artificial neural networks. Appl Soft Comput 9(3):954–961
Holland JH. Adaptation in natural and artificial system: University of Michigan Press, 1975.
Hu X, Zhang Y, Guo L, Wang J, Cai Y, Fu H et al (2018) Cyclic behavior of saturated soft clay under stress path with bidirectional shear stresses. Soil Dyn Earthq Eng 104:319–328
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501
Iebeling K, Milton B (1996) Designing a neural network for forecasting financial and economic time series. Neurocomputing 10(3):215–236
Javadi AA, Rezania M (2009) Applications of artificial intelligence and data mining techniques in soil modeling. Geomech Eng 1(1):53–74
Jefferies M (1993) Nor-Sand: a simle critical state model for sand. Geotechnique 43(1):91–103
Jin Y-F, Wu Z-X, Yin Z-Y, Shen JS (2017) Estimation of critical state-related formula in advanced constitutive modeling of granular material. Acta Geotech 12(6):1329–1351
Jin Y-F, Yin Z-Y, Shen S-L, Hicher P-Y (2016) Investigation into MOGA for identifying parameters of a critical-state-based sand model and parameters correlation by factor analysis. Acta Geotech 11(5):1131–1145
Jin Y-F, Yin Z-Y, Shen S-L, Hicher P-Y (2016) Selection of sand models and identification of parameters using an enhanced genetic algorithm. Int J Numer Anal Met 40(8):1219–1240
Jin Y-F, Yin Z-Y, Wu Z-X, Daouadji A (2018) Numerical modeling of pile penetration in silica sands considering the effect of grain breakage. Finite Elem Anal Des 144:15–29
Jin Y-F, Yin Z-Y, Zhou W-H, Huang H-W (2019) Multi-objective optimization-based updating of predictions during excavation. Eng Appl Artif Intel 78:102–123
Jin YF, Yin ZY, Wu ZX, Zhou WH (2018) Identifying parameters of easily crushable sand and application to offshore pile driving. Ocean Eng 154:416–429
Johari A, Javadi AA, Habibagahi G (2011) Modelling the mechanical behaviour of unsaturated soils using a genetic algorithm-based neural network. Comput Geotech 38(1):2–13
Kim J, Hwang W, Kim Y (2018) Effects of hysteresis on hydro-mechanical behavior of unsaturated soil. Eng Geol 245:1–9
Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. International joint conference on artificial intelligence: Morgan Kaufmann Publishers Inc., 1995. p. 1137-1143
Kohestani VR, Hassanlourad M (2016) Modeling the mechanical behavior of carbonate sands using artificial neural networks and support vector machines. Int J Geomech 16(1):04015038
Kolymbas D. A generalized hypoelastic constitutive law. Proc XI Int Conf Soil Mechanics and Foundation Engineering. San Francisco: Balkema, Rotterdam, 1985. p. 2626.
Koopialipoor M, Jahed Armaghani D, Haghighi M, Ghaleini EN (2017) A neuro-genetic predictive model to approximate overbreak induced by drilling and blasting operation in tunnels. B Eng Geol Environ:1–10
Lefik M, Schrefler B (2003) Artificial neural network as an incremental non-linear constitutive model for a finite element code. Comput Methods Appl Mech Eng 192(28–30):3265–3283
Liu C, Jiang Z, Han X, Zhou W (2019) Slope displacement prediction using sequential intelligent computing algorithms. Measurement 134:634–648
Liu K, Liu B (2019) Intelligent information-based construction in tunnel engineering based on the GA and CCGPR coupled algorithm. Tunnell Undergr Space Technol 88:113–128
Liu WZ, Shi ML, Miao LC, Xu LR, Zhang DW (2013) Constitutive modeling of the destructuration and anisotropy of natural soft clay. Comput Geotech 51:24–41
Mašín D (2005) A hypoplastic constitutive model for clays. Int J Numer Anal Methods Geomech 29(4):311–336
Masters T (1994) Practical neural network recipes in C++. Academic Press
Müthing N, Zhao C, Hölter R, Schanz T (2018) Settlement prediction for an embankment on soft clay. Comput Geotech 93:87–103
Nassr A, Esmaeili-Falak M, Katebi H, Javadi A (2018) A new approach to modeling the behavior of frozen soils. Eng Geol 246:82–90
Ng CWW, Akinniyi DB, Zhou C, Chiu CF (2019) Comparisons of weathered lateritic, granitic and volcanic soils: Compressibility and shear strength. Eng Geol 249:235–240
Nielsen RH (1987) Kolmogorov’s mapping neural network existence theorem. In: Proceedings of the IEEE first international conference on neural networks, San Diego, CA, USA, pp 11–13
Paola JD (1994) Neural network classification of multispectral imagery. The University of Arizona
Penumadu D, Zhao RD (1999) Triaxial compression behavior of sand and gravel using artificial neural networks (ANN). Comput Geotech 24:207–230
Prechelt L (1998) Automatic early stopping using cross validation quantifying the criteria. Neural Netw 11:761–767
Rashidian V, Hassanlourad M (2014) Application of an artificial neural network for modeling the mechanical behavior of carbonate soils. Int J Geomech 14(1):142–150
Romo MP, García SR, Mendoza MJ, Taboada-Urtuzuástegui V (2001) Recurrent and constructive-algorithm networks for sand behavior modeling. Int J Geomech 1(4):371–387
Roscoe KH, Burland J. On the generalized stress-strain behaviour of wet clay. Engineering Plasticity. Cambridge, UK: Cambridge University Press, 1968. p. 535–609.
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(9):533–536
Stone M (1974) Cross-validatory choice and assessment of statistical predictions. J R Stat Soc C-appl 36(2):111–147
Su D, Yang ZX (2019) Drained analyses of cylindrical cavity expansion in sand incorporating a bounding-surface model with state-dependent dilatancy. Appl Math Model 68:1–20
Su L-J, Yin J-H, Zhou W-H (2010) Influences of overburden pressure and soil dilation on soil nail pull-out resistance. Comput Geotech 37(4):555–564
Taiebat M, Dafalias YF (2008) SANISAND: Simple anisotropic sand plasticity model. Int J Numer Anal Met 32(8):915–948
Tian Y, Yao YP (2017) Modelling the non-coaxiality of soils from the view of cross-anisotropy. Comput Geotech 86:219–229
Tran C, Srokosz P (2010) The idea of PGA stream computations for soil slope stability evaluation. Cr Mecanique 338(9):499–509
Turk G, Logar J, Majes B (2001) Modelling soil behaviour in uniaxial strain conditions by neural networks. Adv Eng Softw 32:805–812
Vermeer P (1978) A double hardening model for sand. Geotechnique 28(4):413–433
Wang C (1994) A theory of generalization in learning machines with neural application. The University of Pennsylvania
Wang S, Wu W, Yin Z-Y, Peng C, He X-Z (2018) Modelling time-dependent behaviour of granular material with hypoplasticity. Int J Numer Anal Methods Geomech 42(12):1331–1345
Wu W, Bauer E, Kolymbas D (1996) Hypoplastic constitutive model with critical state for granular materials. Mech Mater 23(1):45–69
Xie X, Qi S, Zhao F, Wang D (2018) Creep behavior and the microstructural evolution of loess-like soil from Xi’an area, China. Eng Geol 236:43–59
Xiong H, Nicot F, Yin Z (2017) A three-dimensional micromechanically based model. Int J Numer Anal Methods Geomech 41(17):1669–1686
Yao Y, Hou W, Zhou A (2009) UH model: three-dimensional unified hardening model for overconsolidated clays. Geotechnique 59(5):451–469
Yao Y, Sun D, Luo T (2004) A critical state model for sands dependent on stress and density. Int J Numer Anal Methods Geomech 28(4):323–337
Yao Y, Sun D, Matsuoka H (2008) A unified constitutive model for both clay and sand with hardening parameter independent on stress path. Comput Geotech 35(2):210–222
Yao YP, Hou W, Zhou AN (2009) UH model: three-dimensional unified hardening model for overconsolidated clays. Géotechnique 59(5):451–469
Yin Z-Y, Chang CS, Karstunen M, Hicher P-Y (2010) An anisotropic elastic–viscoplastic model for soft clays. Int J Solids Struct 47(5):665–677
Yin Z-Y, Jin Y-F, Shen S-L, Huang H-W (2016) An efficient optimization method for identifying parameters of soft structured clay by an enhanced genetic algorithm and elastic–viscoplastic model. Acta Geotech 12(4):849–867
Yin Z-Y, Karstunen M (2011) Modelling strain-rate-dependency of natural soft clays combined with anisotropy and destructuration. Acta Mech Solida Sin 24(3):216–230
Yin Z-Y, Karstunen M, Chang CS, Koskinen M, Lojander M (2011) Modeling time-dependent behavior of soft sensitive clay. J Geotech Geoenviron Eng 137(11):1103–1113
Yin Z-Y, Zhao J, Hicher P-Y (2014) A micromechanics-based model for sand-silt mixtures. Int J Solids Struct 51(6):1350–1363
Yin ZY, Chang CS (2009) Microstructural modelling of stress-dependent behaviour of clay. Int J Solids Struct 46(6):1373–1388
Yin ZY, Chang CS, Hicher PY (2010) Micromechanical modelling for effect of inherent anisotropy on cyclic behaviour of sand. Int J Solids Struct 47(14–15):1933–1951
Yin ZY, Chang CS, Hicher PY, Karstunen M (2009) Micromechanical analysis of kinematic hardening in natural clay. Int J Plast 25(8):1413–1435
Yin ZY, Chang CS, Karstunen M, Hicher PY (2010) An anisotropic elastic-viscoplastic model for soft clays. Int J Solids Struct 47(5):665–677
Yin ZY, Jin YF, S SJ, Hicher PY (2017) Optimization techniques for identifying soil parameters in geotechnical engineering: comparative study and enhancement. Int J Numer Anal Met 42(1):1-25
Yu H (1998) CASM: a unified state parameter model for clay and sand. Int J Numer Anal Methods Geomech 22(8):621–653
Zhang P, Wu H-N, Chen R-P, Chan THT (2020) Hybrid meta-heuristic and machine learning algorithms for tunneling-induced settlement prediction: a comparative study. Tunnell Undergr Space Technol 99:103383
Zhang P, Yin Z-Y, Jin Y-F, Chan THT (2020) A novel hybrid surrogate intelligent model for creep index prediction based on particle swarm optimization and random forest. Eng Geol 265:105328
Zhang P, Yin Z-Y, Zheng Y, Gao F-P (2020) A LSTM surrogate modelling approach for caisson foundations. Ocean Eng 204:107263
Zhang P, Yin ZY, Jin YF (2021) State-of-the-art review of machine learning applications in constitutive modeling of soils. Arch Comput Method Eng. https://doi.org/10.1007/s11831-020-09524-z
Zhang P, Yin ZY, Jin YF, Chan T, Gao FP (2021) Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms. Geosci Front 12(1):441–452
Zhang P, Yin ZY, Jin YF, Ye GL (2020) An AI-based model for describing cyclic characteristics of granular materials. Int J Numer Anal Met 44(9):1315–1335
Zhou YF, Tham LG, Yan WM, Dai FC, Xu L (2014) Laboratory study on soil behavior in loess slope subjected to infiltration. Eng Geol 183:31–38
Zhu JH, Zaman MM, Anderson SA (1998) Modelling of shearing behaviour of a residual soil with Recurrent Neural Network. Int J Numer Anal Met 22(8):671–687
Acknowledgements
This research was financially supported by the Research Grants Council (RGC) of Hong Kong Special Administrative Region Government (HKSARG) of China (Grant No.: 15209119, R5037-18F); Joint research project between SiChuan Province and National Universities funded by Science & Technology Department of Sichuan Province (No.2019YFSY0015), and Open research grant of MOE Key Laboratory of High-speed Railway Engineering.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A. Formulations of BPNN-based Kaolinite constitutive models
Appendix A. Formulations of BPNN-based Kaolinite constitutive models
where, X = [p, q, e, ε1, Δε1], matrix of input variables; H = matrix of the hidden layer output; O = [q, e], matrix of output variables; f = tansig formulation; g = purlin formulation. Herein,
Rights and permissions
About this article
Cite this article
Zhang, P., Yin, ZY., Jin, YF. et al. Modelling the mechanical behaviour of soils using machine learning algorithms with explicit formulations. Acta Geotech. 17, 1403–1422 (2022). https://doi.org/10.1007/s11440-021-01170-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11440-021-01170-4