Dimensionality reduction and prediction of soil consolidation coefficient using random forest coupling with Relief algorithm

Abstract

The consolidation coefficient of soil (C_v) is a crucial parameter used for the design of structures leaned on soft soi. In general, the C_v is determined experimentally in the laboratory. However, the experimental tests are time-consuming as well as expensive. Therefore, researchers tried several ways to determine C_v via other simple soil parameters. In this study, we developed a hybrid model of Random Forest coupling with a Relief algorithm (RF-RL) to predict the C_v of soil. To conduct this study, a database of soil parameters collected from a case study region in Vietnam was used for modeling. The performance of the proposed models was assessed via statistical indicators, namely Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The proposal models were constructed with four sets of soil variables, including 6, 7, 8, and 13 inputs. The results revealed that all models performed well with a high performance (R² > 0.980). Although the RF-RL model with 13 variables has the highest prediction accuracy ( R² = 0.9869), the difference compared with other models was negligible (i.e., R² = 0.9824, 0.9850, 0.9825 for the cases with 6, 7, 8 inputs, respectively). Thus, it can be concluded that the hybrid model of RF-RL can be employed to predict C_v based on the basic soil parameters.

Graphical abstract

Keywords

soil consolidation coefficient / machine learning / random forest / Relief

References

[1] CasagrandeA, FadumR E. Notes on Soil Testing for Engineering Purposes. Cambridge, MA: Harvard University, 1940

[2] YangP, ZhangJ, HuH, WuX, CaoX, ChangY, LiuY, XuJ. Coefficient analysis of soft soil consolidation based on measurement of stratified settlement. Geotechnical and Geological Engineering, 2016, 34( 1): 383– 390

[3] TaylorD W. Research on Consolidation of Clays. Cambridge, MA: Massachusetts Institute of Technology, 1942

[4] CaiG, LiuS, PuppalaA J. Predictions of coefficient of consolidation from CPTU dissipation tests in quaternary clays. Bulletin of Engineering Geology and the Environment, 2012, 71( 2): 337– 350

[5] CaiG, LiuS, PuppalaA J. Consolidation parameters interpretation of CPTU dissipation data based on strain path theory for soft Jiangsu quaternary clays. Marine Georesources and Geotechnology, 2015, 33( 4): 310– 319

[6] RajuP N, PandianN S, NagarajT S. Analysis and estimation of the coefficient of consolidation. Geotechnical Testing Journal, 1995, 18( 2): 252– 258

[7] PistorC M, YardimciM A, GüçeriS I. On-line consolidation of thermoplastic composites using laser scanning. Composites. Part A: Applied Science and Manufacturing, 1999, 30( 10): 1149– 1157

[8] SridharanA, NagarajH B. Coefficient of consolidation and its correlation with index properties of remolded soils. Geotechnical Testing Journal, 2004, 27 : 469– 474

[9] KanayamaM, RoheA, van PaassenL A. Using and improving neural network models for ground settlement prediction. Geotechnical and Geological Engineering, 2014, 32 : 687– 697

[10] PsyllakiP, StamatiouK, IliadisI, MourlasA, AsterisP, VaxevanidisN. Surface treatment of tool steels against galling failure. In: Proceedings of the MATEC Web of Conferences. Les Ulis: EDP Sciences, 2018

[11] SamaniegoE, AnitescuC, GoswamiS, Nguyen-ThanhV M, GuoH, HamdiaK, ZhuangX, RabczukT. An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications. Computer Methods in Applied Mechanics and Engineering, 2020, 362 : 112790

[12] AnitescuC, AtroshchenkoE, AlajlanN, RabczukT. Artificial neural network methods for the solution of second order boundary value problems. Computers, Materials & Continua, 2019, 59( 1): 345– 359

[13] Nguyen-ThanhV M, AnitescuC, AlajlanN, RabczukT, ZhuangX. Parametric deep energy approach for elasticity accounting for strain gradient effects. Computer Methods in Applied Mechanics and Engineering, 2021, 386 : 114096

[14] PhamB T, NguyenM D, Al-AnsariN, TranQ A, HoL S, LeH V, PrakashI. A comparative study of soft computing models for prediction of permeability coefficient of soil. Mathematical Problems in Engineering, 2021, 2021 : 1– 11

[15] PhamB T, LyH B, Al-AnsariN, HoL S. A comparison of Gaussian process and M5P for prediction of soil permeability coefficient. Scientific Programming, 2021, 1– 13

[16] KanungoD P, SharmaS, PainA. Artificial Neural Network (ANN) and Regression Tree (CART) applications for the indirect estimation of unsaturated soil shear strength parameters. Frontiers of Earth Science, 2014, 8( 3): 439– 456

[17] KhanS Z, SumanS, PavaniM, DasS K. Prediction of the residual strength of clay using functional networks. Geoscience Frontiers, 2016, 7( 1): 67– 74

[18] ZhangW, WuC, ZhongH, LiY, WangL. Prediction of undrained shear strength using extreme gradient boosting and random forest based on bayesian optimization. Geoscience Frontiers, 2021, 12( 1): 469– 477

[19] MamudurK, KattamuriM R. Application of boosting-based ensemble learning method for the prediction of compression index. Journal of The Institution of Engineers (India): Series A, 2020, 101 : 409– 419

[20] PhamB T, NguyenM D, DaoD V, PrakashI, LyH B, LeT T, HoL S, NguyenK T, NgoT Q, HoangV, SonL H, NgoH T T, TranH T, DoN M, Van LeH, HoH L, Tien BuiD. Development of artificial intelligence models for the prediction of compression coefficient of soil: An application of Monte Carlo sensitivity analysis. Science of the Total Environment, 2019, 679 : 172– 184

[21] BuiD T, NhuV H, HoangN D. Prediction of soil compression coefficient for urban housing project using novel integration machine learning approach of swarm intelligence and multi-layer perceptron neural network. Advanced Engineering Informatics, 2018, 38 : 593– 604

[22] MoayediH, GörM, LyuZ, BuiD T. Herding behaviors of grasshopper and Harris Hawk for hybridizing the neural network in predicting the soil compression coefficient. Measurement, 2020, 152 : 107389

[23] PhamB T, NguyenM D, BuiK T T, PrakashI, ChapiK, BuiD T. A novel artificial intelligence approach based on multi-layer perceptron neural network and biogeography-based optimization for predicting coefficient of consolidation of soil. Catena, 2019, 173 : 302– 311

[24] NguyenM D, PhamB T, HoL S, LyH B, LeT T, QiC, LeV M, LeL M, PrakashI, BuiD T. Soft-computing techniques for prediction of soils consolidation coefficient. Catena, 2020, 195 : 104802

[25] NguyenM D, PhamB T, TuyenT T, Hai YenH P, PrakashI, VuT T, ChapiK, ShirzadiA, ShahabiH, DouJ, QuocN K, BuiD T. Development of an artificial intelligence approach for prediction of consolidation coefficient of soft soil: A sensitivity analysis. Open Construction & Building Technology Journal, 2019, 13( 1): 178– 188

[26] Rodriguez-GalianoV, Sanchez-CastilloM, Chica-OlmoM, Chica-RivasM. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geology Reviews, 2015, 71 : 804– 818

[27] TrigilaA, IadanzaC, EspositoC, Scarascia-MugnozzaG. Comparison of logistic regression and random forests techniques for shallow landslide susceptibility assessment in Giampilieri (NE Sicily, Italy). Geomorphology, 2015, 249 : 119– 136

[28] VeronesiF, HurniL. Random forest with semantic tie points for classifying landforms and creating rigorous shaded relief representations. Geomorphology, 2014, 224 : 152– 160

[29] PhamB T, QiC, HoL S, Nguyen-ThoiT, Al-AnsariN, NguyenM D, NguyenH D, LyH B, LeH V, PrakashI. A novel hybrid soft computing model using random forest and particle swarm optimization for estimation of undrained shear strength of soil. Sustainability, 2020, 12( 6): 2218–

[30] WindleM. Statistical Approaches to Gene X Environment Interactions for Complex Phenotypes. Cambridge, MA: MIT Press, 2016

[31] KononenkoI, SˇikonjaM R. Non-Myopic Feature Quality Evaluation with (R) ReliefF. Oxford: Chapman and Hall/CRC, 2007

[32] KiraK, RendellL A. A practical approach to feature selection. In: Machine learning Proceedings 1992. Amsterdam: Elsevier, 1992, 249– 256

[33] BreimanL. Random forests. Machine Learning, 2001, 45( 1): 5– 32

[34] ZhangP, YinZ Y, JinY F, ChanT H. A novel hybrid surrogate intelligent model for creep index prediction based on particle swarm optimization and random forest. Engineering Geology, 2020, 265 : 105328

[35] LyH B, Thai PhamB. Soil unconfined compressive strength prediction using random forest (RF) machine learning model. Open Construction & Building Technology Journal, 2020, 14(Suppl 2): 278– 285

[36] PhamT D, BuiN D, NguyenT T, PhanH C. Predicting the reduction of embankment pressure on the surface of the soft ground reinforced by sand drain with random forest regression. In: Proceedings of the IOP Conference Series: Materials Science and Engineering. Bristol: IOP Publishing, 2020, 072027

[37] DurgabaiR P L, YRB. Feature selection using ReliefF Algorithm. International Journal of Advanced Research in Computer and Communication Engineering, 2014, 8215– 8218

[38] KiraK, RendellL A. The feature selection problem: Traditional methods and a new algorithm. AAAI, 1992, 2 : 129– 134

[39] DitterrichT G. Machine learning research: Four current directions. Artificial Intelligence Magazine, 1997, 18( 4): 97– 136

[40] SunY. Iterative RELIEF for feature weighting: Algorithms, theories, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29( 6): 1035– 1051

[41] NagelkerkeN J. A note on a general definition of the coefficient of determination. Biometrika, 1991, 78( 3): 691– 692

[42] PiephoH P. A coefficient of determination (R²) for generalized linear mixed models. Biometrical Journal. Biometrische Zeitschrift, 2019, 61( 4): 860– 872

[43] WangW, LuY. Analysis of the mean absolute error (MAE) and the root mean square error (RMSE) in assessing rounding model. Materials Science and Engineering, 2018, 324 : 012049

[44] LyH B, LeT T, VuH L T, TranV Q, LeL M, PhamB T. Computational hybrid machine learning based prediction of shear capacity for steel fiber reinforced concrete beams. Sustainability, 2020, 12( 7): 2709

[45] WillmottC J, MatsuuraK. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 2005, 30 : 79– 82

[46] ChaiT, Draxler R R. Root mean square error ( RMSE) or mean absolute error (MAE)?—Arguments against avoiding RMSE in the literature. Geoscientific Model Development , 2014, 7(3): 1525–1534

[47] LeT T, PhamB T, LyH B, ShirzadiA, LeL M. Development of 48-hour precipitation forecasting model using nonlinear autoregressive neural network. In: CIGOS 2019, Innovation for Sustainable Infrastructure. Hanoi: Springer, 2020, 1191– 1196

[48] PhamB T, NguyenM D, LyH B, PhamT A, HoangV, Van LeH, LeT T, NguyenH Q, BuiG L. Development of artificial neural networks for prediction of compression coefficient of soft soil. In: CIGOS 2019, Innovation for Sustainable Infrastructure. Hanoi: Springer, 2020, 1167– 1172

[49] AbualigahL M, KhaderA T, HanandehE S. A new feature selection method to improve the document clustering using particle swarm optimization algorithm. Journal of Computational Science, 2018, 25 : 456– 466

[50] WuY L, TangC Y, HorM K, WuP F. Feature selection using genetic algorithm and cluster validation. Expert Systems with Applications, 2011, 38( 3): 2727– 2732

[51] ZhouQ, ZhouH, LiT. Cost-sensitive feature selection using random forest: Selecting low-cost subsets of informative features. Knowledge-Based Systems, 2016, 95 : 1– 11

[52] LyH B, NguyenM H, PhamB T. Metaheuristic optimization of Levenberg–Marquardt-based artificial neural network using particle swarm optimization for prediction of foamed concrete compressive strength. Neural Computing & Applications, 2021, 33( 24): 1– 21

[53] QiC, LyH B, LeL M, YangX, GuoL, PhamB T. Improved strength prediction of cemented paste backfill using a novel model based on adaptive neuro fuzzy inference system and artificial bee colony. Construction & Building Materials, 2021, 284 : 122857

[54] LyH B, NguyenT A, TranV Q. Development of deep neural network model to predict the compressive strength of rubber concrete. Construction & Building Materials, 2021, 301 : 124081

RIGHTS & PERMISSIONS

Higher Education Press 2022