Bayesian Analysis of Benchmark Examples for Data-Driven Site Characterization
Publication: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 9, Issue 2
Abstract
Data-driven site characterization (DDSC) aids geotechnical engineering by inferring and mapping soil parameters of the subsurface domain. In practice, the limited availability of site investigation data may hinder the performance of traditional machine learning methods and implies significant uncertainty in the predictions, which is typically not quantified. In this study, a framework for Bayesian site characterization (BaySiC) is applied on a benchmark example. Adopting Bayesian statistics enables the framework to deal with small training data sets and allows for coherent quantification of uncertainty, which is valuable to engineering practice for assessing the reliability and the determining characteristic values. BaySiC uses site investigation data to infer statistical estimators of cone penetration test (CPT) parameters and their dependence, as well as to learn spatial correlations. Consecutively, it generates a three-dimensional (3D) map of the subsurface by predicting the CPT parameter values and classifying the material type over the soil domain. For the benchmark example, the study formulated two models within the BaySiC framework and demonstrated their conduct in several cases of varying complexity. Eventually, the performance of the models was evaluated and compared in both deterministic and probabilistic terms. One of the models proved highly effective in predicting the material type at new locations of the subsurface domain, whereas the other provided accurate mapping of the CPT parameters even in complex stratigraphic cases. Also, investigating and comparing the results of the models led to insights regarding the effectiveness of their formulation. Moreover, the paper used hypothesis testing as a means of assessing the predictive power of the model independently from the validation data set. Stemming from the benchmark example, the paper draws conclusions that are meaningful to geotechnical engineering and decision-making.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All models and/or code that support the findings of this study are available from the corresponding author upon reasonable request. All data used during the study were provided by a third party. Direct requests for these materials may be made to the provider, as indicated in the Acknowledgments.
Acknowledgments
The authors would like to thank Kok-Kwang Phoon, Takayuki Shuku, Jianye Ching, and Ikumasa Yoshida for creating the benchmark example and driving developments in ML and statistical methods for DDSC. The data supporting the findings of this study is presented in the work of Phoon et al. (2022b), whose authors can be contacted to provide the benchmark data. The authors offer their special thanks to Jianye Ching for the fruitful discussions that have improved the quality of the paper.
References
Baecher, G. B. 2017. “Bayesian thinking in geotechnics.” In Geo-Risk 2017, 1–18. Reston, VA: ASCE.
Betancourt, M. 2017. “A conceptual introduction to Hamiltonian Monte Carlo.” Preprint, submitted January 10, 2017. https://doi.org/10.48550/arXiv.1701.02434.
Ching, J., and K.-K. Phoon. 2019. “Constructing site-specific multivariate probability distribution model using Bayesian machine learning.” J. Eng. Mech. 145 (1): 04018126. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001537.
Dutilleul, P. 1999. “The MLE algorithm for the matrix normal distribution.” J. Stat. Comput. Simul. 64 (2): 105–123. https://doi.org/10.1080/00949659908811970.
Gelman, A., J. B. Carlin, H. S. Stern, D. B. Dunson, A. Vehtari, and D. B. Rubin. 2013. Bayesian data analysis. Boca Raton, FL: Chapman and Hall/CRC.
Geyer, S., I. Papaioannou, and D. Straub. 2021. “Bayesian analysis of hierarchical random fields for material modeling.” Probab. Eng. Mech. 66 (Oct): 103167. https://doi.org/10.1016/j.probengmech.2021.103167.
Gupta, A. K., and D. K. Nagar. 1999. Matrix variate distributions. Boca Raton, FL: Chapman & Hall.
Gut, A. 2009. An intermediate course in probability. New York: Springer.
Helterbrand, J. D., and N. Cressie. 1994. “Universal cokriging under intrinsic coregionalization.” Math. Geol. 26 (2): 205–226. https://doi.org/10.1007/BF02082764.
Hoffman, M. D., and A. Gelman. 2014. “The No-U-Turn sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo.” J. Mach. Learn. Res. 15 (1): 1593–1623. https://doi.org/10.5555/2627435.2638586.
Krüger, F., S. Lerch, T. L. Thorarinsdottir, and T. Gneiting. 2016. “Predictive inference based on Markov chain Monte Carlo output.” Int. Stat. Rev. 89 (2): 274–301. https://doi.org/10.1111/insr.12405.
Kruschke, J. K. 2013. “Bayesian estimation supersedes the t test.” J. Exp. Psychol. Gen. 142 (2): 573–603. https://doi.org/10.1037/a0029146.
Kruschke, J. K. 2018. “Rejecting or accepting parameter values in Bayesian estimation.” Adv. Methods Pract. Psychol. Sci. 1 (2): 270–280. https://doi.org/10.1177/2515245918771304.
Lehmann, E. L., and G. Casella. 1998. Theory of point estimation. New York: Springer.
Mariethoz, G., and J. Caers. 2014. Multiple-point geostatistics. New York: Wiley.
Marriott, F. H. C., and M. L. Eaton. 1984. “Multivariate statistics: A vector space approach.” Appl. Stat. 33 (3): 319. https://doi.org/10.2307/2347710.
Mavritsakis, A., T. Schweckendiek, A. Teixeira, and E. Smyrniou. 2022. “Bayesian subsurface mapping using CPT data.” In Proc., 8th Int. Symp. for Geotechnical Safety & Risk, ISGSR 2022. Adelaide, Australia: Engineers Australia.
Meyn, S. P., and R. L. Tweedie. 1993. Markov chains and stochastic stability. London: Springer.
Murphy, K. P. 2022. Probabilistic machine learning: An introduction. Cambridge, MA: MIT Press.
Neal, R. M. 2011. MCMC using Hamiltonian dynamics. Boca Raton, FL: Chapman and Hall/CRC.
Phoon, K.-K., J. Ching, and T. Shuku. 2022a. “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. 2022b. “Benchmark examples for data-driven site characterization.” Georisk: Assess. Manage. Risk Eng. Syst. Geohazards 16 (4): 1–23. https://doi.org/10.1080/17499518.2022.2025541.
Rall, L. B. 1981. Vol. 120 of Automatic differentiation: Techniques and applications. Berlin: Springer.
Rasmussen, C. E., and C. K. I. Williams. 2006. Gaussian processes for machine learning. Cambridge, UK: MIT Press.
Robertson, P. 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.
Salvatier, J., T. V. Wiecki, and C. Fonnesbeck. 2016. “Probabilistic programming in Python using pymc3.” PeerJ Comput. Sci. 2: e55. https://doi.org/10.7717/peerj-cs.55.
van de Meent, J.-W., B. Paige, H. Yang, and F. Wood. 2018. “An introduction to probabilistic programming.” Found. Trends Mach. Learn. Preprint, submitted September 27, 2018. https://arxiv.org/abs/1809.10756.
Vanmarcke, E. 2010. Random fields: Analysis and synthesis. Singapore: World Scientific.
Wang, Z., M. Broccardo, and J. Song. 2019. “Hamiltonian Monte Carlo methods for subset simulation in reliability analysis.” Struct. Saf. 76 (Jan): 51–67. https://doi.org/10.1016/j.strusafe.2018.05.005.
Wasserman, L. 2004. All of statistics. New York: Springer.
Zhu, H., L. Zhang, T. Xiao, and X. Li. 2017. “Generation of multivariate cross-correlated geotechnical random fields.” Comput. Geotech. 86 (Jun): 95–107. https://doi.org/10.1016/j.compgeo.2017.01.006.
Information & Authors
Information
Published In
ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 9 • Issue 2 • June 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Jul 31, 2022
Accepted: Nov 17, 2022
Published online: Feb 6, 2023
Published in print: Jun 1, 2023
Discussion open until: Jul 6, 2023
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
- 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).