Machine learning-based prediction of soil compression modulus with application of 1D settlement

基于机器学习的土体压缩模量预测及一维基础沉 降应用

Abstract

The compression modulus (Es) is one of the most significant soil parameters that affects the compressive deformation of geotechnical systems, such as foundations. However, it is difficult and sometime costly to obtain this parameter in engineering practice. In this study, we aimed to develop a non-parametric ensemble artificial intelligence (AI) approach to calculate the Es of soft clay in contrast to the traditional regression models proposed in previous studies. A gradient boosted regression tree (GBRT) algorithm was used to discern the non-linear pattern between input variables and the target response, while a genetic algorithm (GA) was adopted for tuning the GBRT model’s hyper-parameters. The model was tested through 10-fold cross validation. A dataset of 221 samples from 65 engineering survey reports from Shanghai infrastructure projects was constructed to evaluate the accuracy of the new model’s predictions. The mean squared error and correlation coefficient of the optimum GBRT model applied to the testing set were 0.13 and 0.91, respectively, indicating that the proposed machine learning (ML) model has great potential to improve the prediction of Es for soft clay. A comparison of the performance of empirical formulas and the proposed ML method for predicting foundation settlement indicated the rationality of the proposed ML model and its applicability to the compressive deformation of geotechnical systems. This model, however, cannot be directly applied to the prediction of Es in other sites due to its site specificity. This problem can be solved by retraining the model using local data. This study provides a useful reference for future multi-parameter prediction of soil behavior.

概要

目的

土体压缩模量是影响岩土体结构变形的重要参数 之一。本文旨在通过机器学习的方法实现对压缩 模量的预测, 并通过构建一个机器学习模型,得 到塑限、液限、塑性指数、液性指数、比贯入阻 力以及埋深这6 个输入参数与压缩模量预测值之 间的关系。

创新点

1. 构建一个机器学习算法框架以实现对土体压缩 模量的预测; 2. 此框架包括梯度提升回归树 (GBRT) 和遗传算法 (GA) 并采用 GA 对GBRT 超参数进行获取。

方法

1. 通过收集整理工程报告获取本次预测的数据集 (样本211 个);输入参数有6 个,分别为塑限、 液限、塑性指数、液性指数、比贯入阻力以及埋 深;输出参数为压缩模量。2. 采用GBRT 算法识 别输入变量与目标响应之间的非线性规律,并采 用GA 调整GBRT 模型的超参数。 3. 模型训练完 成后,对压缩模量进行预测。4. 将测试集上的预 测结果和传统方法进行对比分析并应用到一维 基础沉降中。

结论

1. 本文提出的GA-GBRT 模型可以较好地实现对 土体压缩模量的预测;GA 可以对GBRT 算法的 超参数进行有效标定。2. 训练后的GA-GBRT 模 型在训练集和测试集上都表现良好; 在训练集和 测试集上的相关系数 R 值分别为0.82 和0.91,说 明模型可以对压缩模量进行准确预测。3. 对输入 变量相对重要性的研究发现,液性指标是本研究 中最重要的变量, 其重要性得分为0.313(总数 为1); 其他指标的重要性排序依次为: :液限、塑 限、塑性指数、比贯入阻力和埋深。 4. 对于地基 沉降的预测 本文提出的模型在相关系数 R 值和 Mann-Whitney 检验结果上均优于经验公式。 5. 本 文提出的GA-GBRT 模型可以更经济、更快速地 预测土壤压缩模量。

References

  1. Arditi D, Pulket T, 2005. Predicting the outcome of construction litigation using boosted decision trees. Journal of Computing in Civil Engineering, 19(4):387–393. https://doi.org/10.1061/(asce)0887-3801(2005)19:4(387)

    Article  Google Scholar 

  2. Arditi D, Pulket T, 2010. Predicting the outcome of construction litigation using an integrated artificial intelligence model. Journal of Computing in Civil Engineering, 24(1): 73–80. https://doi.org/10.1061/(asce)0887-3801(2010)24:1(73)

    Article  Google Scholar 

  3. Brabie D, Andersson E, 2008. An overview of some highspeed train derailments: means of minimizing consequences based on empirical observations. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 222(4):441–463. https://doi.org/10.1243/09544097jrrt149

    Article  Google Scholar 

  4. Braga-Neto U, Hashimoto R, Dougherty ER, et al., 2004. Is cross-validation better than resubstitution for ranking genes? Bioinformatics, 20(2):253–258. https://doi.org/10.1093/bioinformatics/btg399

    Article  Google Scholar 

  5. Ching J, Phoon KK, 2014. Correlations among some clay parameters—the multivariate distribution. Canadian Geotechnical Journal, 51(6):686–704. https://doi.org/10.1139/cgj-2013-0353

    Article  Google Scholar 

  6. Clayton CRI, Steinhagen M, Steinhagen HM, et al., 1995. Terzaghi’s theory of consolidation, and the discovery of effective stress (compiled from the work of K. Terzaghi and A.W. Skempton). Proceedings of the Institution of Civil Engineers-Geotechnical Engineering, 113(4):191–205. https://doi.org/10.1680/igeng.1995.28015

    Article  Google Scholar 

  7. Fan HH, Wu PT, Gao JE, et al., 2006. Influence of density and water content on unconfined compression strength of solidified soil. Science of Soil and Water Conservation, 4(3):54–58 (in Chinese). https://doi.org/10.3969/j.issn.1672-3007.2006.03.011

    Google Scholar 

  8. Fenton GA, Griffiths DV, 2008. Risk Assessment in Geotechnical Engineering. Wiley, New York, USA, p.78–101. https://doi.org/10.1002/9780470284704.ch5

    Google Scholar 

  9. Goldberg DE, 1989. Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Longman Publishing, New York, USA.

    Google Scholar 

  10. Gong Y, Luo XQ, Wang DH, et al., 2018. Urban travel time prediction based on gradient boosting regression tress. Journal of Zhejiang University (Engineering Science), 52(3):453–460 (in Chinese). https://doi.org/10.3785/j.issn.1008-973X.2018.03.006

    Google Scholar 

  11. Huang HW, Zhang DM, 2016. Resilience analysis of shield tunnel lining under extreme surcharge: characterization and field application. Tunnelling and Underground Space Technology, 51:301–312. https://doi.org/10.1016/j.tust.2015.10.044

    Article  Google Scholar 

  12. Huang HW, Gong WP, Khoshnevisan S, et al., 2015. Simplified procedure for finite element analysis of the longitudinal performance of shield tunnels considering spatial soil variability in longitudinal direction. Computers and Geotechnics, 64:132–145. https://doi.org/10.1016/j.compgeo.2014.11.010

    Article  Google Scholar 

  13. Huang HW, Xiao L, Zhang DM, et al., 2017. Influence of spatial variability of soil Young’s modulus on tunnel convergence in soft soils. Engineering Geology, 228:357–370. https://doi.org/10.1016/j.enggeo.2017.09.011

    Article  Google Scholar 

  14. Jalabert SSM, Martin MP, Renaud JP, et al., 2010. Estimating forest soil bulk density using boosted regression modelling. Soil Use and Management, 26(4):516–528. https://doi.org/10.1111/j.1475-2743.2010.00305.x

    Article  Google Scholar 

  15. Johari A, Javadi AA, Habibagahi G, 2011. Modelling the mechanical behaviour of unsaturated soils using a genetic algorithm-based neural network. Computers and Geotechnics, 38(1):2–13. https://doi.org/10.1016/j.compgeo.2010.08.011

    Article  Google Scholar 

  16. Juang CH, Wang L, 2013. Reliability-based robust geotechnical design of spread foundations using multi-objective genetic algorithm. Computers and Geotechnics, 48(4):96–106. https://doi.org/10.1016/j.compgeo.2012.10.003

    Article  Google Scholar 

  17. Khanlari GR, Heidari M, Momeni AA, et al., 2012. Prediction of shear strength parameters of soils using artificial neural networks and multivariate regression methods. Engineering Geology, 137–138:11–18. https://doi.org/10.1016/j.enggeo.2011.12.006

    Article  Google Scholar 

  18. Koo TK, Li MY, 2016. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. Journal of Chiropractic Medicine, 15(2):155–163. https://doi.org/10.1016/j.jcm.2016.02.012

    Article  Google Scholar 

  19. Kulhawy FH, Mayne PW, 1990. Manual on Estimating Soil Properties for Foundation Design. Electric Power Research Institute, Palo Alto, USA.

    Google Scholar 

  20. Lee MJ, Hong SJ, Choi YM, et al., 2010. Evaluation of deformation modulus of cemented sand using CPT and DMT. Engineering Geology, 115(1–2):28–35. https://doi.org/10.1016/j.enggeo.2010.06.016

    Article  Google Scholar 

  21. Lee SJ, Lee SR, Kim YS, 2003. An approach to estimate unsaturated shear strength using artificial neural network and hyperbolic formulation. Computers and Geotechnics, 30(6):489–503. https://doi.org/10.1016/s0266-352x(03)00058-2

    Article  Google Scholar 

  22. Nejad FP, Jaksa MB, Kakhi M, et al., 2009. Prediction of pile settlement using artificial neural networks based on standard penetration test data. Computers and Geotechnics, 36(7):1125–1133. https://doi.org/10.1016/j.compgeo.2009.04.003

    Article  Google Scholar 

  23. Persson C, Bacher P, Shiga T, et al., 2017. Multi-site solar power forecasting using gradient boosted regression trees. Solar Energy, 150:423–436. https://doi.org/10.1016/j.solener.2017.04.066

    Article  Google Scholar 

  24. Qi CC, Tang XL, 2018. Slope stability prediction using integrated metaheuristic and machine learning approaches: a comparative study. Computers & Industrial Engineering, 118:112–122. https://doi.org/10.1016/j.cie.2018.02.028

    Article  Google Scholar 

  25. Qi CC, Fourie A, Ma GW, et al., 2018a. Comparative study of hybrid artificial intelligence approaches for predicting hangingwall stability. Journal of Computing in Civil Engineering, 32(2):04017086. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000737

    Article  Google Scholar 

  26. Qi CC, Fourie A, Chen QS, et al., 2018b. A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill. Journal of Cleaner Production, 183:566–578, https://doi.org/10.1016/j.jclepro.2018.02.154

    Article  Google Scholar 

  27. Rodriguez JD, Perez A, Lozano JA, 2010. Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(3):569–575. https://doi.org/10.1109/TPAMI.2009.187

    Article  Google Scholar 

  28. Roe BP, Yang HJ, Ji Z, et al., 2005. Boosted decision trees as an alternative to artificial neural networks for particle identification. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 543(2–3):577–584. https://doi.org/10.1016/j.nima.2004.12.018

    Article  Google Scholar 

  29. Roy PP, Roy K, 2008. On some aspects of variable selection for partial least squares regression models. QSAR & Combinatorial Science, 27(3):302–313. https://doi.org/10.1002/qsar.200710043

    Article  Google Scholar 

  30. Shahin MA, 2016. State-of-the-art review of some artificial intelligence applications in pile foundations. Geoscience Frontiers, 7(1):33–44. https://doi.org/10.1016/j.gsf.2014.10.002

    Article  Google Scholar 

  31. Shahin MA, Maier HR, Jaksa MB, 2004. Data division for developing neural networks applied to geotechnical engineering. Journal of Computing in Civil Engineering, 18(2):105–114. https://doi.org/10.1061/(asce)0887-3801(2004)18:2(105)

    Article  Google Scholar 

  32. Sridharan A, Nagaraj HB, 2000. Compressibility behaviour of remoulded, fine-grained soils and correlation with index properties. Canadian Geotechnical Journal, 37(3):712–722. https://doi.org/10.1139/t99-128

    Article  Google Scholar 

  33. Tarawneh B, 2017. Predicting standard penetration test N-value from cone penetration test data using artificial neural networks. Geoscience Frontiers, 8(1):199–204. https://doi.org/10.1016/j.gsf.2016.02.003

    MathSciNet  Article  Google Scholar 

  34. Tong LY, Tu QZ, Du GY, et al., 2013. Determination of confined compression modulus of soft clay using piezocone penetration tests. Chinese Journal of Geotechnical Engineering, 35(S2):569–572 (in Chinese).

    Google Scholar 

  35. Touzani S, Granderson J, Fernandes S, 2018. Gradient boosting machine for modeling the energy consumption of commercial buildings. Energy and Buildings, 158:1533–1543. https://doi.org/10.1016/j.enbuild.2017.11.039

    Article  Google Scholar 

  36. Tun YW, Pedroso DM, Scheuermann A, et al., 2016. Probabilistic reliability analysis of multiple slopes with genetic algorithms. Computers and Geotechnics, 77:68–76. https://doi.org/10.1016/j.compgeo.2016.04.006

    Article  Google Scholar 

  37. Viswanathan R, Samui P, 2016. Determination of rock depth using artificial intelligence techniques. Geoscience Frontiers, 7(1):61–66. https://doi.org/10.1016/j.gsf.2015.04.002

    Article  Google Scholar 

  38. Yin ZY, Jin YF, Huang HW, et al., 2016. Evolutionary polynomial regression based modelling of clay compressibility using an enhanced hybrid real-coded genetic algorithm. Engineering Geology, 210:158–167. https://doi.org/10.1016/j.enggeo.2016.06.016

    Article  Google Scholar 

  39. Zhang DM, Hu QF, Huang HW, et al., 2018. Nonlinear subgrade reaction solution for circular tunnel lining design based on mobilized strength of undrained clay. Canadian Geotechnical Journal, 55(2):155–170. https://doi.org/10.1139/cgj-2017-0006

    Article  Google Scholar 

  40. Zhou J, Li XB, Mitri HS, 2016. Classification of rockburst in underground projects: comparison of ten supervised learning methods. Journal of Computing in Civil Engineering, 30(5):04016003. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000553

    Article  Google Scholar 

Download references

Acknowledgement

The authors thank Li XIAO and Ye-lu ZHOU from Tongji University, China for their help in collecting the original data for this study.

Author information

Affiliations

Authors

Contributions

Dong-ming ZHANG, Jin-zhang ZHANG, Hong-wei HUANG, Chong-chong QI, and Chen-yu CHANG declare that they have no conflict of interest.

Corresponding authors

Correspondence to Hong-wei Huang or Chong-chong Qi.

Additional information

Project supported by the National Natural Science Foundation of China (Nos. 51608380 and 51538009), the Key Innovation Team Program of the Innovation Talents Promotion Plan by Ministry of Science and Technology of China (No. 2016RA4059), and the Specific Consultant Research Project of Shanghai Tunnel Engineering Company Ltd. (No. SLEC/KJB/XMGL/0130), China

Contributors

Hong-wei HUANG and Jin-zhang ZHANG designed the research. Dong-ming ZHANG and Chong-chong QI processed the corresponding data. Jin-zhang ZHANG wrote the first draft of the manuscript. Dong-ming ZHANG and Chong-chong QI helped to organize the manuscript. Hong-wei HUANG and Chen-yu CHANG revised and edited the final version.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhang, D., Zhang, J., Huang, H. et al. Machine learning-based prediction of soil compression modulus with application of 1D settlement. J. Zhejiang Univ. Sci. A 21, 430–444 (2020). https://doi.org/10.1631/jzus.A1900515

Download citation

Key words

  • Compression modulus prediction
  • Machine learning (ML)
  • Gradient boosted regression tree (GBRT)
  • Genetic algorithm (GA)
  • Foundation settlement

CLC number

  • TU433

关键词

  • 压缩模量预测
  • 机器学习
  • 梯度提升回归算法
  • 遗传算法(GA)
  • 基础沉降