Data-Drive Site Characterization for Benchmark Examples: Sparse Bayesian Learning versus Gaussian Process Regression
Publication: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 9, Issue 1
Abstract
In this paper, two data-drive site characterization methods, the sparse Bayesian learning (SBL) method and the Gaussian process regression (GPR) method, are benchmarked by a set of virtual ground examples and a real ground example of cone penetration test (CPT) data. The two methods both assume a zero-mean prior Gaussian random field model for the spatial trend, but the strategies of maintaining model simplicity are different. The SBL method produces a simple trend model by adopting sparse basis functions, whereas the GPR method produces a simple trend model by adopting a kernel function governed by few hyperparameters. The accuracy of the two methods in predicting the cone tip resistance () of CPT was quantified by the root-mean square prediction error (RMSE), whereas the accuracy in identifying soil layers was quantified by the identification rate (IR). It was found that the GPR method in general outperforms the SBL method. Further accuracy improvement for the GPR method can be obtained if a clustering analysis based on the Robertson’s soil behavior index () is conducted.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Computer codes used in this study are available from the corresponding author on reasonable request.
Acknowledgments
The idea of the clustering analysis presented in this paper was inspired by a discussion between the first author and Mr. Antonis Mavritsakis (Deltares). The first author would like to express his gratitude.
References
Betz, W., I. Papaioannou, and D. Straub. 2016. “Transitional Markov chain Monte Carlo: Observations and improvements.” ASCE J. Eng. Mech. 142 (5): 04016016. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001066.
Bishop, C. M., and N. M. Nasrabadi. 2006. Pattern recognition and machine learning. New York: Springer.
Ching, J., and Y. C. Chen. 2007. “Transitional Markov chain Monte Carlo method for Bayesian model updating, model class selection and model averaging.” ASCE J. Eng. Mech. 133 (7): 816–832. https://doi.org/10.1061/(ASCE)0733-9399(2007)133:7(816).
Ching, J., W. H. Huang, and K. K. Phoon. 2020. “3D Probabilistic site characterization by sparse Bayesian learning.” ASCE J. Eng. Mech. 146 (12): 04020134. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001859.
Ching, J., and K. K. Phoon. 2017. “Characterizing uncertain site-specific trend function by sparse Bayesian learning.” ASCE J. Eng. Mech. 143 (7): 04017028. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001240.
Ching, J., and K. K. Phoon. 2019. “Impact of auto-correlation function model on the probability of failure.” ASCE J. Eng. Mech. 145 (1): 04018123. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001549.
Ching, J., M. Uzielli, K. K. Phoon, and X. J. Xu. 2022a. “Characterizing spatially variable cone tip resistance soundings from a global CPT database.” ASCE J. Geotech. Geoenviron. Eng.
Ching, J., Z. Y. Yang, and K. K. Phoon. 2021. “Dealing with non-lattice data in three-dimensional probabilistic site characterization.” ASCE J. Eng. Mech. 147 (5): 06021003. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001907.
Ching, J., I. Yoshida, and K. K. Phoon. 2022b. “Comparison of trend models for geotechnical spatial variability: Sparse Bayesian Learning vs. Gaussian Process Regression.” Gondwana Res. https://doi.org/10.1016/j.gr.2022.07.011.
Guttorp, P., and T. Gneiting. 2006. “Studies in the history of probability and statistics XLIX on the Matérn correlation family.” Biometrika 93 (4): 989–995. https://doi.org/10.1093/biomet/93.4.989.
Hegazy, Y. A., and P. W. Mayne. 2002. “Objective site characterization using clustering of piezocone data.” ASCE J. Geotech. Geoenviron. Eng. 128 (12): 986–996. https://doi.org/10.1061/(ASCE)1090-0241(2002)128:12(986).
Jaksa, M. 1995. “The influence of spatial variability on the geotechnical design properties of a stiff, overconsolidated clay.” Ph.D. dissertation, Dept. of Civil and Environmental Engineering, Univ. of Adelaide.
Jaksa, M. B., W. S. Kaggwa, and P. I. Brooker. 1999. “Experimental evaluation of the scale of fluctuation of a stiff clay.” In Proc., 8th Int. Conf. on Application of Statistics and Probability, 415–422. Rotterdam, Netherlands: A. A. Balkema.
Liao, T., and P. W. Mayne. 2007. “Stratigraphic delineation by three-dimensional clustering of piezocone data.” Georisk: Assess. Manage. Risk Eng. Syst. Geohazards 1 (2): 102–119. https://doi.org/10.1080/17499510701345175.
Liu, W. F., Y. F. Leung, and M. K. Lo. 2017. “Integrated framework for characterization of spatial variability of geological profiles.” Can. Geotech. J. 54 (1): 47–58. https://doi.org/10.1139/cgj-2016-0189.
Phoon, K. K., J. Ching, and T. Shuku. 2021. “Challenges in data-driven site characterization.” Georisk: Assess. Manage. Risk Eng. Syst. Geohazards 16 (1): 114–126. https://doi.org/10.1080/17499518.2021.1896005.
Phoon, K. K., T. Shuku, J. Ching, and I. Yoshida. 2022. “Benchmark examples for data-driven site characterization.” Georisk: Assess. Manage. Risk Eng. Syst. Geohazards 1–23. https://doi.org/10.1080/17499518.2022.2025541.
Robertson, P. K. 2016. “Cone penetration test (CPT)-based soil behaviour type (SBT) classification system—An update.” Can. Geotech. J. 53 (12): 1910–1927. https://doi.org/10.1139/cgj-2016-0044.
Thorndike, R. L. 1953. “Who belongs in the family?” Psychometrika 18 (4): 267–276. https://doi.org/10.1007/BF02289263.
Tipping, M. E. 2001. “Sparse Bayesian learning and the relevance vector machine.” J. Mach. Learn. Res. 1 (Dec): 211–244. https://doi.org/10.1162/15324430152748236.
Wang, H., X. Wang, J. F. Wellmann, and R. Y. Liang. 2018. “Bayesian stochastic soil modeling framework using Gaussian Markov random fields.” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part A: Civ. Eng. 4 (2): 04018014. https://doi.org/10.1061/AJRUA6.0000965.
Yoshida, I., Y. Tomizawa, and Y. Otake. 2021. “Estimation of trend and random components of conditional random field using Gaussian process regression.” Comput. Geotech. 136 (Aug): 104179. https://doi.org/10.1016/j.compgeo.2021.104179.
Information & Authors
Information
Published In
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Aug 17, 2022
Accepted: Oct 14, 2022
Published online: Nov 28, 2022
Published in print: Mar 1, 2023
Discussion open until: Apr 28, 2023
ASCE Technical Topics:
- Analysis (by type)
- Bayesian analysis
- Benchmark
- Business management
- Communication systems
- Engineering fundamentals
- Gaussian process
- Geomechanics
- Geotechnical engineering
- Geotechnical investigation
- Infrastructure
- Lifeline systems
- Management methods
- Mathematics
- Penetration tests
- Practice and Profession
- Probability
- Regression analysis
- Soil analysis
- Soil mechanics
- Soil properties
- Statistical analysis (by type)
- Stochastic processes
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Takayuki Shuku, Kok Kwang Phoon, Comparison of Data-Driven Site Characterization Methods through Benchmarking: Methodological and Application Aspects, ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 10.1061/AJRUA6.RUENG-977, 9, 2, (2023).
- Kok-Kwang Phoon, Takayuki Shuku, Jianye Ching, Ikumasa Yoshida, Benchmarking Data-Driven Site Characterization, ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 10.1061/AJRUA6.RUENG-1058, 9, 2, (2023).