The unconfined compressive strength (Qu) is one of the most important criteria of stabilized soil to design in order to evaluate the effective of soft soil improvement. The unconfined compressive strength of stabilized soil is strongly affected by numerous factors such as the soil properties, the binder content, etc. Machine Learning (ML) approach can take into account these factors to predict the unconfined compressive strength (Qu) with high performance and reliability. The aim of this paper is to select a single ML model to design Qu of stabilized soil containing some chemical stabilizer agents such as lime, cement and bitumen. In order to build the single ML model, a database is created based on the literature investigation. The database contains 200 data samples, 12 input variables (Liquid limit, Plastic limit, Plasticity index, Linear shrinkage, Clay content, Sand content, Gravel content, Optimum water content, Density of stabilized soil, Lime content, Cement content, Bitumen content) and the output variable Qu. The performance and reliability of ML model are evaluated by the popular validation technique Monte Carlo simulation with aided of three criteria metrics including coefficient of determination R2, Root Mean Square Error (RMSE) and Mean Square Error (MAE). ML model based on Gradient Boosting algorithm is selected as highest performance and highest reliability ML model for designing Qu of stabilized soil. Explanation of feature effects on the unconfined compressive strength Qu of stabilized soil is carried out by Permutation importance, Partial Dependence Plot (PDP 2D) in two dimensions and SHapley Additive exPlanations (SHAP) local value. The ML model proposed in this investigation is single and useful for professional engineers with using the mapping Maximal dry density-Linear shrinkage created by PDP 2D.
TranV.Q., Hybrid gradient boosting with meta-heuristic algorithms prediction of unconfined compressive strength of stabilized soil based on initial soil properties, mix design and effective compaction, J. Clean. Prod. (2022), 131683. doi: 10.1016/j.jclepro.2022.131683.
2.
SaitohS., TechnicalT., SuzukiY., TechnicalT., ShiraiK. and TechnicalT., Durcissement des sols améliorés par la méthode du mélange en profondeur, pp. 1745–1748.
3.
MolaAbasiH., SaberianM. and LiJ., Prediction of compressive and tensile strengths of zeolite-cemented sand using porosity and composition, Constr. Build. Mater. 202 (2019), 784–795, doi: 10.1016/j.conbuildmat.2019.01.065.
TranV.Q., MaiH.-V.T., NguyenT.-A. and LyH.-B., Investigation of ANN architecture for predicting the compressive strength of concrete containing GGBFS, PloS One16(12) (2021), e0260847, doi: 10.1371/journal.pone.0260847.
6.
TranV.Q. and NguyenL.Q., Using machine learning technique for designing reinforced lightweight soil, J. Intell. Fuzzy Syst.Preprint(Preprint) (2022), 1–18, doi: 10.3233/JIFS-212621.
7.
TranV.Q. and NguyenL.Q., Using machine learning technique for designing reinforced lightweight soil, J. Intell. Fuzzy Syst. 43(1) (2022), 1633–1650, doi: 10.3233/JIFS-212621.
8.
TranV.Q., Compressive strength prediction of stabilized dredged sediments using artificial neural network, Adv. Civ. Eng. 2021 (2021), e6656084, doi: 10.1155/2021/6656084.
9.
PhamT.A., TranV.Q., VuH.-L.T. and LyH.-B., Design deep neural network architecture using a genetic algorithm for estimation of pile bearing capacity, PLoS One15(12) (2020), e0243030.
10.
TranV.Q., DangV.Q. and HoL.S., Evaluating compressive strength of concrete made with recycled concrete aggregates using machine learning approach, Constr. Build. Mater. 323 (2022), 126578.
11.
Tran, Quan V., Machine learning approach for investigating chloride diffusion coefficient of concrete containing supplementary cementitious materials, Constr. Build. Mater. 328 (2022), 127103, doi: 10.1016/j.conbuildmat.2022.127103.
12.
AhmadiM., NaderpourH. and KheyroddinA., Utilization of artificial neural networks to prediction of the capacity of CCFT short columns subject to short term axial load, Arch. Civ. Mech. Eng. 14(3) (2014), 510–517.
13.
MolaAbasiH. and ShooshpashaI., Polynomial models controlling strength of zeolite-cement-sand mixtures, Sci. Iran. 24(2) (2017), 526–536, doi: 10.24200/sci.2017.2415.
14.
KalantaryF., ArdalanH. and Nariman-ZadehN., An investigation on the Su–NSPT correlation using GMDH type neural networks and genetic algorithms, Eng. Geol. 104(1) (2009), 144–155, doi: 10.1016/j.enggeo.2008.09.006.
15.
KordnaeijA., KalantaryF., KordtabarB. and Mola-AbasiH., Prediction of recompression index using GMDH-type neural network based on geotechnical soil properties, Soils Found. 55(6) (2015), 1335–1345, doi: 10.1016/j.sandf.2015.10.001.
16.
DasS.K., SamuiP. and SabatA.K., Application of artificial intelligence to maximum dry density and unconfined compressive strength of cement stabilized soil, Geotech. Geol. Eng. 29(3) (2011), 329–342, doi: 10.1007/s10706-010-9379-4.
17.
SumanS., MahamayaM. and DasS.K., Prediction of maximum dry density and unconfined compressive strength of cement stabilised soil using artificial intelligence techniques, Int. J. Geosynth. Ground Eng. 2(2) (2016), 11, doi: 10.1007/s40891-016-0051-9.
18.
PedregosaF., et al., Scikit-learn: machine learning in python, J. Mach. Learn. Res. 12 (2011), 2825–2830.
19.
BurroughsV.S., Quantitative criteria for the selection and stabilisation of soils for rammed earth wall construction, University of New South Wales, England, 2001.
20.
AS 1160-1996 Bituminous emulsions for the construction and mainte, Stand. Aust.1996.
21.
Guide to Pavement Technology Part 4D: Stabilised Materials, Austroads Ltd, 2019.
22.
U. C. for H. Settlements (Habitat), Earth construction technology. Part 2, Low-cost technology for production of adobe, rammed earth and compressed blocks. 1987, Accessed: Feb. 11, 2022. [Online]. Available: https://digitallibrary.un.org/record/42574.
23.
HellwigZ., 1 - REGRESSION AND CORRELATION,” in, Linear Regression and its Application to Economics Z. Hellwig, Ed. Pergamon 1963, pp. 1–51. doi: 10.1016/B978-1-4832-0073-6.50004-4.
24.
TibshiraniR., Regression Shrinkage and Selection via the Lasso, J. R. Stat. Soc. Ser. B Methodol. 58(1) (1996), 267–288.
25.
PiryonesiS.M. and El-DirabyT.E., Role of data analytics in infrastructure asset management: overcoming data size and quality problems, J. Transp. Eng. Part B Pavements146(2) (2020), 04020022, doi: 10.1061/JPEODX.0000175.
26.
HastieT., TibshiraniR., FriedmanJ.The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition, 2nd ed. New York: Springer-Verlag, 2009. doi: 10.1007/978-0-387-84858-7.
27.
VapnikV., The Nature of Statistical Learning Theory, 2nd ed. New York: Springer-Verlag, 2000. doi: 10.1007/978-1-4757-3264-1
.
28.
TranV.Q. and PrakashI., Prediction of soil loss due to erosion using support vector machine model, Vietnam J. Earth Sci. 42(3) (2020), 247–254.
29.
HoL.S. and TranV.Q., Machine learning approach for predicting and evaluating California bearing ratio of stabilized soil containing industrial waste, J. Clean. Prod. 370, (2022), 133587, doi: 10.1016/j.jclepro.2022.133587.
30.
PradhanB., A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS, Comput. Geosci. 51 (2013), 350–365.
31.
TinocoJ., CorreiaA.G. and CortezP., Support vector machines applied to uniaxial compressive strength prediction of jet grouting columns, Comput. Geotech. 55 (2014), 132–140.
32.
SamuiP., Support vector machine applied to settlement of shallow foundations on cohesionless soils, (3), Comput. Geotech. 35 (2008), 419–427.
33.
BreimanL., Random forests, Mach. Learn. 45(1) (2001), 5–32, doi: 10.1023/A:1010933404324.
34.
TellaA., BalogunA.-L., AdebisiN. and AbdullahS., Spatialassessment of PM10 hotspots using Random Forest, K-Nearest Neighbourand Naïve Bayes, Atmospheric Pollut. Res. 12(10) (2021), 101202, doi: 10.1016/j.apr.2021.101202.
35.
FriedmanJ.H., Greedy function approximation: a gradient boosting machine, Ann. Stat. 29(5) (2001), 1189–1232.
ChenT. and GuestrinC., XGBoost: A Scalable Tree Boosting System, Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. (2016), 785–794, doi: 10.1145/2939672.2939785.
38.
TranV.Q., MaiH.-V.T., ToQ.T. and NguyenM.H., Machine learning approach in investigating carbonation depth of concrete containing Fly ash, Struct. Concr., vol. n/a, no. n/a, doi: 10.1002/suco.202200269.
39.
MordechaiS., Applications of Monte Carlo Method in Science and Engineering2011. doi: 10.5772/1954.
40.
FengD.-C., WangW.-J., MangalathuS. and TacirogluE., Interpretable XGBoost-SHAP Machine-Learning Model for Shear Strength Prediction of Squat RC Walls, J. Struct. Eng. 147(11) (2021), 04021173, doi: 10.1061/(ASCE)ST.1943-541X.0003115.
