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

doi:10.1007/s11709-022-0812-6

Front. Struct. Civ. Eng.

2022, Vol. 16

Issue (2) : 224-238 https://doi.org/10.1007/s11709-022-0812-6

RESEARCH ARTICLE

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

Hai-Bang LY¹, Huong-Lan Thi VU¹, Lanh Si HO^1,²(

), Binh Thai PHAM³

¹. Department of Civil Engineering, University of Transport Technology, Hanoi 100000, Vietnam
². Civil and Environmental Engineering Program, Hiroshima University, Hiroshima 739-8527, Japan
³. Department of Science, Technology and International Cooperation, University of Transport Technology, Hanoi 100000, Vietnam

Download: PDF(9149 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

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.

Keywords soil consolidation coefficient machine learning random forest Relief

Corresponding Author(s): Lanh Si HO

Just Accepted Date: 17 January 2022 Online First Date: 22 March 2022 Issue Date: 20 April 2022

Cite this article:

Hai-Bang LY,Huong-Lan Thi VU,Lanh Si HO, et al. Dimensionality reduction and prediction of soil consolidation coefficient using random forest coupling with Relief algorithm[J]. Front. Struct. Civ. Eng., 2022, 16(2): 224-238.

URL:

https://academic.hep.com.cn/fsce/EN/10.1007/s11709-022-0812-6
https://academic.hep.com.cn/fsce/EN/Y2022/V16/I2/224

Tab.1 Statistical analysis of the inputs and output in this study

Fig.1 Multi-correlation graph of input and output parameters employed in this study.

Fig.2 RF algorithm.

Fig.3 Relief algorithm.

Fig.4 Methodology flow chart.

Fig.5 Weights of input variables in the function of different nearest neighbors for: (a) from 5 to 35 nearest neighbors; (b) from 40 to 85 nearest neighbors; (c) more than 90 nearest neighbors.

Fig.6 Analysing of the convergence of prediction results with respect to statistical criteria of different datasets over 50 simulations: (a) R² of RF-RL13; (b) RMSE of RF-RL13; (c) R² of RF-RL6; (d) RMSE of RF-RL6; (e) R² of RF-RL7; (f) RMSE of RF-RL7; (g) R² of RF-RL8; (h) RMSE of RF-RL8.

Tab.2 Summary of different datasets selected using Relief algorithm

Tab.3 Summary of different quality assessment criteria over 50 simulations in different cases

Fig.7 Comparisons of the prediction accuracy over 50 simulations in different cases with respect to (a) R², (b) RMSE, and (c) MAE.

Fig.8 Target and output values plots for training and testing datasets for the best predictor in different cases: (a) RF-RL13; (b) RF-RL6; (c) RF-RL7; and (d) RF-RL8.

Fig.9 Regression graphs for all data for the best predictor in different cases: (a) RF-RL13; (b) RF-RL6; (c) RF-RL7; (d) RF-RL8.

Tab.4 Summary of different quality assessment criteria for the best predictor in different cases

Tab.5 Summary of different parameters for the algorithms used in this study

Fig.10 Results of 10-fold cross-validation for the training part using LightGBM, CatBoost, Deep NN, and RF algorithms in this study: (a) R²; (b) RMSE.

Tab.6 Summary of different quality assessment criteria for the best predictor in different cases

Fig.11 Regression graphs for all data for different cases: (a) Deep NN; (b) CatBoost; (c) LightGBM.

Fig.12 Feature importance analysis conducted with 13 inputs using RF.

1	A Casagrande, R E Fadum. Notes on Soil Testing for Engineering Purposes. Cambridge, MA: Harvard University, 1940
2	P Yang, J Zhang, H Hu, X Wu, X Cao, Y Chang, Y Liu, J Xu. Coefficient analysis of soft soil consolidation based on measurement of stratified settlement. Geotechnical and Geological Engineering, 2016, 34( 1): 383– 390 https://doi.org/10.1007/s10706-015-9952-y
3	D W Taylor. Research on Consolidation of Clays. Cambridge, MA: Massachusetts Institute of Technology, 1942
4	G Cai, S Liu, A J Puppala. Predictions of coefficient of consolidation from CPTU dissipation tests in quaternary clays. Bulletin of Engineering Geology and the Environment, 2012, 71( 2): 337– 350 https://doi.org/10.1007/s10064-011-0385-4
5	G Cai, S Liu, A J Puppala. 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 https://doi.org/10.1080/1064119X.2013.872742
6	P N Raju, N S Pandian, T S Nagaraj. Analysis and estimation of the coefficient of consolidation. Geotechnical Testing Journal, 1995, 18( 2): 252– 258 https://doi.org/10.1520/GTJ10325J
7	C M Pistor, M A Yardimci, S I Güçeri. On-line consolidation of thermoplastic composites using laser scanning. Composites. Part A: Applied Science and Manufacturing, 1999, 30( 10): 1149– 1157 https://doi.org/10.1016/S1359-835X(99)00030-5
8	A Sridharan, H B Nagaraj. Coefficient of consolidation and its correlation with index properties of remolded soils. Geotechnical Testing Journal, 2004, 27 : 469– 474
9	M Kanayama, A Rohe, L A van Paassen. Using and improving neural network models for ground settlement prediction. Geotechnical and Geological Engineering, 2014, 32 : 687– 697 https://doi.org/10.1007/s10706-014-9745-8
10	P Psyllaki, K Stamatiou, I Iliadis, A Mourlas, P Asteris, N Vaxevanidis. Surface treatment of tool steels against galling failure. In: Proceedings of the MATEC Web of Conferences. Les Ulis: EDP Sciences, 2018
11	E Samaniego, C Anitescu, S Goswami, V M Nguyen-Thanh, H Guo, K Hamdia, X Zhuang, T Rabczuk. 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 https://doi.org/10.1016/j.cma.2019.112790
12	C Anitescu, E Atroshchenko, N Alajlan, T Rabczuk. Artificial neural network methods for the solution of second order boundary value problems. Computers, Materials & Continua, 2019, 59( 1): 345– 359 https://doi.org/10.32604/cmc.2019.06641
13	V M Nguyen-Thanh, C Anitescu, N Alajlan, T Rabczuk, X Zhuang. Parametric deep energy approach for elasticity accounting for strain gradient effects. Computer Methods in Applied Mechanics and Engineering, 2021, 386 : 114096 https://doi.org/10.1016/j.cma.2021.114096
14	B T Pham, M D Nguyen, N Al-Ansari, Q A Tran, L S Ho, H V Le, I Prakash. A comparative study of soft computing models for prediction of permeability coefficient of soil. Mathematical Problems in Engineering, 2021, 2021 : 1– 11
15	B T Pham, H B Ly, N Al-Ansari, L S Ho. A comparison of Gaussian process and M5P for prediction of soil permeability coefficient. Scientific Programming, 2021, 1– 13
16	D P Kanungo, S Sharma, A Pain. 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 https://doi.org/10.1007/s11707-014-0416-0
17	S Z Khan, S Suman, M Pavani, S K Das. Prediction of the residual strength of clay using functional networks. Geoscience Frontiers, 2016, 7( 1): 67– 74 https://doi.org/10.1016/j.gsf.2014.12.008
18	W Zhang, C Wu, H Zhong, Y Li, L Wang. Prediction of undrained shear strength using extreme gradient boosting and random forest based on bayesian optimization. Geoscience Frontiers, 2021, 12( 1): 469– 477 https://doi.org/10.1016/j.gsf.2020.03.007
19	K Mamudur, M R Kattamuri. 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	B T Pham, M D Nguyen, D V Dao, I Prakash, H B Ly, T T Le, L S Ho, K T Nguyen, T Q Ngo, V Hoang, L H Son, H T T Ngo, H T Tran, N M Do, H Van Le, H L Ho, D Tien Bui. 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 https://doi.org/10.1016/j.scitotenv.2019.05.061
21	D T Bui, V H Nhu, N D Hoang. 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 https://doi.org/10.1016/j.aei.2018.09.005
22	H Moayedi, M Gör, Z Lyu, D T Bui. Herding behaviors of grasshopper and Harris Hawk for hybridizing the neural network in predicting the soil compression coefficient. Measurement, 2020, 152 : 107389 https://doi.org/10.1016/j.measurement.2019.107389
23	B T Pham, M D Nguyen, K T T Bui, I Prakash, K Chapi, D T Bui. 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 https://doi.org/10.1016/j.catena.2018.10.004
24	M D Nguyen, B T Pham, L S Ho, H B Ly, T T Le, C Qi, V M Le, L M Le, I Prakash, D T Bui. Soft-computing techniques for prediction of soils consolidation coefficient. Catena, 2020, 195 : 104802 https://doi.org/10.1016/j.catena.2020.104802
25	M D Nguyen, B T Pham, T T Tuyen, H P Hai Yen, I Prakash, T T Vu, K Chapi, A Shirzadi, H Shahabi, J Dou, N K Quoc, D T Bui. 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 https://doi.org/10.2174/1874836801913010178
26	V Rodriguez-Galiano, M Sanchez-Castillo, M Chica-Olmo, M Chica-Rivas. 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 https://doi.org/10.1016/j.oregeorev.2015.01.001
27	A Trigila, C Iadanza, C Esposito, G Scarascia-Mugnozza. Comparison of logistic regression and random forests techniques for shallow landslide susceptibility assessment in Giampilieri (NE Sicily, Italy). Geomorphology, 2015, 249 : 119– 136 https://doi.org/10.1016/j.geomorph.2015.06.001
28	F Veronesi, L Hurni. Random forest with semantic tie points for classifying landforms and creating rigorous shaded relief representations. Geomorphology, 2014, 224 : 152– 160 https://doi.org/10.1016/j.geomorph.2014.07.020
29	B T Pham, C Qi, L S Ho, T Nguyen-Thoi, N Al-Ansari, M D Nguyen, H D Nguyen, H B Ly, H V Le, I Prakash. 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– https://doi.org/10.3390/su12062218
30	M Windle. Statistical Approaches to Gene X Environment Interactions for Complex Phenotypes. Cambridge, MA: MIT Press, 2016
31	I Kononenko, M R. Sˇikonja Non-Myopic Feature Quality Evaluation with (R) ReliefF. Oxford: Chapman and Hall/CRC, 2007
32	K Kira, L A Rendell. A practical approach to feature selection. In: Machine learning Proceedings 1992. Amsterdam: Elsevier, 1992, 249– 256
33	L Breiman. Random forests. Machine Learning, 2001, 45( 1): 5– 32 https://doi.org/10.1023/A:1010933404324
34	P Zhang, Z Y Yin, Y F Jin, T H Chan. A novel hybrid surrogate intelligent model for creep index prediction based on particle swarm optimization and random forest. Engineering Geology, 2020, 265 : 105328 https://doi.org/10.1016/j.enggeo.2019.105328
35	H B Ly, B Thai Pham. Soil unconfined compressive strength prediction using random forest (RF) machine learning model. Open Construction & Building Technology Journal, 2020, 14(Suppl 2): 278– 285
36	T D Pham, N D Bui, T T Nguyen, H C Phan. 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	R P L Durgabai, B YR. Feature selection using ReliefF Algorithm. International Journal of Advanced Research in Computer and Communication Engineering, 2014, 8215– 8218 https://doi.org/10.17148/IJARCCE.2014.31031
38	K Kira, L A Rendell. The feature selection problem: Traditional methods and a new algorithm. AAAI, 1992, 2 : 129– 134
39	T G Ditterrich. Machine learning research: Four current directions. Artificial Intelligence Magazine, 1997, 18( 4): 97– 136
40	Y Sun. Iterative RELIEF for feature weighting: Algorithms, theories, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29( 6): 1035– 1051 https://doi.org/10.1109/TPAMI.2007.1093
41	N J Nagelkerke. A note on a general definition of the coefficient of determination. Biometrika, 1991, 78( 3): 691– 692 https://doi.org/10.1093/biomet/78.3.691
42	H P Piepho. A coefficient of determination (R2) for generalized linear mixed models. Biometrical Journal. Biometrische Zeitschrift, 2019, 61( 4): 860– 872 https://doi.org/10.1002/bimj.201800270
43	W Wang, Y Lu. 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	H B Ly, T T Le, H L T Vu, V Q Tran, L M Le, B T Pham. Computational hybrid machine learning based prediction of shear capacity for steel fiber reinforced concrete beams. Sustainability, 2020, 12( 7): 2709 https://doi.org/10.3390/su12072709
45	C J Willmott, K Matsuura. 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 https://doi.org/10.3354/cr030079
46	T Chai, R R Draxler. 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	T T Le, B T Pham, H B Ly, A Shirzadi, L M Le. 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	B T Pham, M D Nguyen, H B Ly, T A Pham, V Hoang, H Van Le, T T Le, H Q Nguyen, G L Bui. 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	L M Abualigah, A T Khader, E S Hanandeh. A new feature selection method to improve the document clustering using particle swarm optimization algorithm. Journal of Computational Science, 2018, 25 : 456– 466 https://doi.org/10.1016/j.jocs.2017.07.018
50	Y L Wu, C Y Tang, M K Hor, P F Wu. Feature selection using genetic algorithm and cluster validation. Expert Systems with Applications, 2011, 38( 3): 2727– 2732 https://doi.org/10.1016/j.eswa.2010.08.062
51	Q Zhou, H Zhou, T Li. Cost-sensitive feature selection using random forest: Selecting low-cost subsets of informative features. Knowledge-Based Systems, 2016, 95 : 1– 11 https://doi.org/10.1016/j.knosys.2015.11.010
52	H B Ly, M H Nguyen, B T Pham. 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 https://doi.org/10.1007/s00521-021-06321-y
53	C Qi, H B Ly, L M Le, X Yang, L Guo, B T Pham. 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 https://doi.org/10.1016/j.conbuildmat.2021.122857
54	H B Ly, T A Nguyen, V Q Tran. Development of deep neural network model to predict the compressive strength of rubber concrete. Construction & Building Materials, 2021, 301 : 124081 https://doi.org/10.1016/j.conbuildmat.2021.124081

[1]	Gebrail BEKDAŞ, Melda YÜCEL, Sinan Melih NIGDELI. Estimation of optimum design of structural systems via machine learning[J]. Front. Struct. Civ. Eng., 2021, 15(6): 1441-1452.
[2]	Shan LIN, Hong ZHENG, Chao HAN, Bei HAN, Wei LI. Evaluation and prediction of slope stability using machine learning approaches[J]. Front. Struct. Civ. Eng., 2021, 15(4): 821-833.
[3]	Amin MAHDAVI-MEYMAND, Mohammad ZOUNEMAT-KERMANI, Kourosh QADERI. Prediction of hydro-suction dredging depth using data-driven methods[J]. Front. Struct. Civ. Eng., 2021, 15(3): 652-664.
[4]	Nader KARBALLAEEZADEH, Hosein GHASEMZADEH TEHRANI, Danial MOHAMMADZADEH SHADMEHRI, Shahaboddin SHAMSHIRBAND. Estimation of flexible pavement structural capacity using machine learning techniques[J]. Front. Struct. Civ. Eng., 2020, 14(5): 1083-1096.
[5]	Zohreh SHEIKH KHOZANI, Khabat KHOSRAVI, Mohammadamin TORABI, Amir MOSAVI, Bahram REZAEI, Timon RABCZUK. Shear stress distribution prediction in symmetric compound channels using data mining and machine learning models[J]. Front. Struct. Civ. Eng., 2020, 14(5): 1097-1109.
[6]	Walid Khalid MBARAK, Esma Nur CINICIOGLU, Ozer CINICIOGLU. SPT based determination of undrained shear strength: Regression models and machine learning[J]. Front. Struct. Civ. Eng., 2020, 14(1): 185-198.
[7]	Renpeng CHEN, Pin ZHANG, Huaina WU, Zhiteng WANG, Zhiquan ZHONG. Prediction of shield tunneling-induced ground settlement using machine learning techniques[J]. Front. Struct. Civ. Eng., 2019, 13(6): 1363-1378.
[8]	Tanvi SINGH, Mahesh PAL, V. K. ARORA. Modeling oblique load carrying capacity of batter pile groups using neural network, random forest regression and M5 model tree[J]. Front. Struct. Civ. Eng., 2019, 13(3): 674-685.

Viewed

Full text

Abstract

Cited

Shared

Discussed