CatBoost–Bayesian Hybrid Model Adaptively Coupled with Modified Theoretical Equations for Estimating the Undrained Shear Strength of Clay
Source abstract
Abstract
The undrained shear strength of clay is an important index for the calculation of the bearing capacity of the foundation soil, the calculation of the soil pressure of the foundation pit, and the analysis of the slope stability. Therefore, the purpose of this paper is to conduct a comprehensive study of the combined use of machine learning with clay theoretical equations to estimate it. Under the Bayesian framework, the CatBoost algorithm (CatBoost–Bayesian) based on Bayesian optimization algorithm was developed to obtain the feature importance level of soil parameters affecting the undrained shear strength of clay, so as to adaptively couple the theoretical equation of undrained shear strength of K0 consolidated clay, which was derived from the modified Cambridge model. Then, the theoretical equation of undrained shear strength of the isotropically consolidated clay was established from the critical state of the clay parameters. Finally, it was illustrated and verified using the experimental samples of Finnish clay. The results indicate that the theoretical equation established by the overconsolidation ratio and effective overburden pressure parameters can well estimate the undrained shear strength of isotropically consolidated clays, and the parameter uncertainty can be considered explicitly and rigorously.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geotechnical Engineering and Analysis · Dam Engineering and Safety · Landslides and related hazards
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Civil Engineering and Architecture, Guilin University of Technology, Guilin 541004, China
Funding
National Natural Science Foundation of China · Guangxi Key Laboratory of Geomechanics and Geotechnical Engineering · Foundation Project of South China Mine Geological Environment Technology Innovation Center
References (58)
Show source-provided references
1. Analytical Approach for Determination of Soil Shear Strength Parameters from CPT and CPTu Data10.1007/s13369-014-1022-x ↗
2. New Design Procedure for Stability of Soft Clays10.1061/AJGEB6.0000066 ↗
3. Discussion of “New design procedure for stability of soft clays”10.1061/AJGEB6.0005026 ↗
4. Slope Reliability Analysis by Simulation of Non-Stationary Random Field of Undrained Shear Strength
5. Marchetti, S., Monaco, P., Totani, G., and Calabrese, M. (2001). The Flat Dilatometer Test (DMT) in Soil Investigation, ISSMGE. ISSMGE TC 16 Report.
6. Robertson, P.K. (2015, January 14–16). Soil Behavior Type Using the DMT. Proceedings of the 3rd International Flat Dilatometer Conference, Roma, Italy. Available online: https://www.cpt-robertson.com/PublicationsPDF/Robertson%20DMT15%202015.pdf.
7. A New Soft Computing Model for Estimating and Controlling Blast-Produced Ground Vibration Based on Hierarchical K-Means Clustering and Cubist Algorithms10.1016/j.asoc.2019.01.042 ↗
8. Xu, H., Zhou, J., Asteris, P.G., Armaghani, D.J., and Tahir, M.M. (2019). Supervised Machine Learning Techniques to the Prediction of Tunnel Boring Machine Penetration Rate. Appl. Sci., 9.10.3390/app9183715 ↗
9. Slope Stability Prediction for Circular Mode Failure Using Gradient Boosting Machine Approach Based on an Updated Database of Case Histories10.1016/j.ssci.2019.05.046 ↗
10. Artificial Intelligence in Seismology: Advent, Performance and Future Trends10.1016/j.gsf.2019.10.004 ↗
11. Research on Prediction Model of Geotechnical Parameters Based on BP Neural Network10.1007/s00521-018-3902-6 ↗
12. Estimation of the Undrained Shear Strength of Sensitive Clays Using Optimized Inference Intelligence System10.1007/s00521-022-06891-5 ↗
13. State-of-the-Art Review of Geotechnical-Driven Artificial Intelligence Techniques in Underground Soil-Structure Interaction10.1016/j.tust.2021.103946 ↗
14. Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient Boosting with Categorical Features Support. arXiv.
15. Evaluating the Predictive Power of Different Machine Learning Algorithms for Groundwater Salinity Prediction of Multi-Layer Coastal Aquifers in the Mekong Delta, Vietnam10.1016/j.ecolind.2021.107790 ↗
16. Seismic Performance Assessment of Corroded RC Columns Based on Data-Driven Machine-Learning Approach10.1016/j.engstruct.2022.113936 ↗
17. Evaluation of CatBoost Method for Prediction of Reference Evapotranspiration in Humid Regions10.1016/j.jhydrol.2019.04.085 ↗
18. CatBoost: A New Approach for Estimating Daily Reference Crop Evapotranspiration in Arid and Semi-Arid Regions of Northern China10.1016/j.jhydrol.2020.125087 ↗
19. Prediction of Undrained Shear Strength Using Extreme Gradient Boosting and Random Forest Based on Bayesian Optimization10.1016/j.gsf.2020.03.007 ↗
20. Oh, H.-J., Syifa, M., Lee, C.-W., and Lee, S. (2019). Land Subsidence Susceptibility Mapping Using Bayesian, Functional, and Meta-Ensemble Machine Learning Models. Appl. Sci., 9.10.3390/app9061248 ↗
21. Roscoe, K.H., and Burland, J.B. (1968). On the Generalised Stress-Strain Behaviour of “wet” Clay. Eng. Plast., 535–609. Available online: https://trid.trb.org/view/124868.
22. Undrained Shear Strength of K0 Consolidated Soft Clays
23. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A. (2018). Advances in Neural Information Processing Systems, Curran Associates, Inc.
24. The Application of Bayesian Methods for Seeking the Extremum
25. Bayesian Hyperparameter Estimation Using Gaussian Process and Bayesian Optimization10.7566/JPSJ.88.074001 ↗
26. SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
27. Hutter, F., Hoos, H.H., and Leyton-Brown, K. (2011, January 17–21). Sequential Model-Based Optimization for General Algorithm Configuration. Proceedings of the Learning and Intelligent Optimization: 5th International Conference, LION 5, Rome, Italy.
28. Random Forests10.1023/A:1010933404324 ↗
29. The Predictive Sample Reuse Method with Applications10.1080/01621459.1975.10479865 ↗
30. Cross-Validatory Choice and Assessment of Statistical Predictions (with Discussion)10.1111/j.2517-6161.1976.tb01573.x ↗
31. Multiple Predicting K-Fold Cross-Validation for Model Selection10.1080/10485252.2017.1404598 ↗
32. Pham, B.T., Qi, C., Ho, L.S., Nguyen-Thoi, T., Al-Ansari, N., Nguyen, M.D., Nguyen, H.D., Ly, H.-B., Le, H.V., and Prakash, I. (2020). A Novel Hybrid Soft Computing Model Using Random Forest and Particle Swarm Optimization for Estimation of Undrained Shear Strength of Soil. Sustainability, 12.10.3390/su12062218 ↗
33. Anisotropy of Undrained Shear Strength of Clays under Axi-Symmetric Loading Conditions10.3208/sandf1972.25.2_73 ↗
34. Karube, D. (2022, May 20). Nonstandard Triaxial Testing Method and Its Problems. Available online: https://cir.nii.ac.jp/crid/1572261549455735296.
35. Empirical Correlations of Compression Index and Swelling Index for Shanghai Clay
36. Regression Analysis of Soil Compressibility10.3208/sandf1972.16.2_19 ↗
37. Stability Evaluation during Staged Construction10.1061/(ASCE)0733-9410(1991)117:4(540) ↗
38. Zhang, J. (2016). Bayesian Method: A Natural Tool for Processing Geotechnical Information, ISSMGE. TC205/TC304 Discussion Groups.
39. Stochastic Mechanics-Based Bayesian Method Calibrating the Constitutive Parameters of the Unified Model for Clay and Sand with CPTU Data10.1007/s11440-022-01524-6 ↗
40. Bayesian Model Comparison and Characterization of Undrained Shear Strength10.1061/(ASCE)GT.1943-5606.0001108 ↗
41. CPT-Based Fully Probabilistic Seismic Liquefaction Potential Assessment to Reduce Uncertainty: Integrating XGBoost Algorithm with Bayesian Theorem10.1016/j.compgeo.2022.104868 ↗
42. Juang, C.H., and Zhang, J. (2017). Bayesian Methods for Geotechnical Applications—A Practical Guide, ASCE.10.1061/9780784480731.019 ↗
43. SPT-Based Probabilistic Evaluation of Soil Liquefaction Potential Considering Design Life of Civil Infrastructures10.1016/j.compgeo.2022.104807 ↗
44. CPT-Based Probabilistic Liquefaction Assessment Considering Soil Spatial Variability, Interpolation Uncertainty and Model Uncertainty10.1016/j.compgeo.2021.104504 ↗
45. Unified CPTu-Based Probabilistic Model for Assessing Probability of Liquefaction of Sand and Clay10.1680/geot.9.P.025 ↗
46. Probabilistic Version of the Robertson and Wride Method for Liquefaction Evaluation: Development and Application10.1139/t11-085 ↗
47. Draper, N.R., and Smith, H. (1998). Applied Regression Analysis, John Wiley & Sons.10.1002/9781118625590 ↗
48. Application and Comparison of Several Machine Learning Algorithms and Their Integration Models in Regression Problems10.1007/s00521-019-04644-5 ↗
49. Analysis of Ground Surface Settlement in Anisotropic Clays Using Extreme Gradient Boosting and Random Forest Regression Models10.1016/j.jrmge.2021.08.001 ↗
50. (2022, June 15). FI-CLAY/14/856 Finland Clays. Available online: http://140.112.12.21/issmge/tc304.htm.
51. Transformation Models for the Compressibility Properties of Finnish Clays Using a Multivariate Database
52. Rutledge, P.C. (2022, May 20). Cooperative Triaxial Shear Research Program of the Corps of Engineers. Available online: https://trid.trb.org/view/119101.
53. Jamiolkowski, M., Ladd, C.C., Germaine, J.T., and Lancellotta, R. (1985, January 12–16). New developments in field and laboratory testing of soils. Proceedings of the XI the International Conference on Soil Mechanics & Foundation Engineering, San Francisco, CA, USA.
54. A Comparison of Simplified Calculation Methods of Undrained Shear Strength of Soft Clays after Consolidation
55. Simplified calculation method for lateral pressure at rest in the under-consolidation stratum
56. Spatial Variability of the Undrained Strength of Clays10.1061/AJGEB6.0001292 ↗
57. Others Experimental Study of Undrained Shear Strength and Cyclic Degradation Behaviors of Marine Clay in Pearl River Estuary
58. Ching, J., Arroyo, M., Chen, J., Jorge, C., Lansivaara, T., Li, D., Mayne, P., Phoon, K., Prakoso, W., and Uzielli, M. (2017). Final Report of Joint TC205/TC304 Working Group on “Discussion of Statistical/Reliability Methods for Eurocodes”, International Society for Soil Mechanics and Geotechnical Engineering (ISSMGE).