Stochastic Simulation of Soil Stratigraphic Profile Using Image Warping
Publication: Geo-Risk 2023
ABSTRACT
Interpreting stratigraphic condition is an essential task in geotechnical projects. However, algorithmically delineating and simulating stratigraphic profiles of non-stationary field, defined as heterogeneous stratum such as tectonically distorted or irregularly deposited strata, is still an open question and a challenging task in engineering practices. In this study, a novel approach that applies the image warping technique in computer vision to a non-stationary random field is developed, and it is further combined with an advanced stratigraphic stochastic simulation model. The image warping technique is effective for transforming non-stationary field into stationary field. Subsequently, an in-house developed stratigraphic stochastic simulation model integrates the Markov random field (MRF) model and the discriminant adaptive nearest neighbor-based k-harmonic mean distance (DANN-KHMD) classifier into a Bayesian framework and is applied to the transferred stationary field to efficiently estimate the stratigraphic uncertainty given sparse site exploration results. To demonstrate the effectiveness of the developed approach, a synthetic case is studied. We envision this approach can be further promoted in industry practices for an improved risk control in geotechnical engineering.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Besag, J. (1986). On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society: Series B (Methodological), 48(3), 259–279.
Bookstein, F. L. (1989). Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Transactions on pattern analysis and machine intelligence, 11(6), 567–585.
Cross, G. R., and Jain, A. K. (1983). Markov random field texture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25–39.
Donato, G., and Belongie, S. (2003). Approximation methods for thin plate spline mappings and principal warps.
Geman, S., and Geman, D. (1984). Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 721–741.
Gong, W., Tang, H., Wang, H., Wang, X., and Juang, C. H. (2019). Probabilistic analysis and design of stabilizing piles in slope considering stratigraphic uncertainty. Engineering Geology, 259, 105162.
Hastie, T., and Tibshirani, R. (1996). Discriminant adaptive nearest neighbor classification. IEEE transactions on pattern analysis and machine intelligence, 18(6), 607–616.
Juang, C. H., Zhang, J., Shen, M., and Hu, J. (2019). Probabilistic methods for unified treatment of geotechnical and geological uncertainties in a geotechnical analysis. Engineering geology, 249, 148–161.
Koller, D., and Friedman, N. (2009). Probabilistic graphical models: principles and techniques. MIT press.
Li, S. Z. (2009). Markov random field modeling in image analysis. Springer Science & Business Media.
Li, Z., Wang, X., Wang, H., and Liang, R. Y. (2016c). Quantifying stratigraphic uncertainties by stochastic simulation techniques based on Markov random field. Engineering Geology, 201, 106–122.
Pan, Z., Wang, Y., and Ku, W. (2017). A new k-harmonic nearest neighbor classifier based on the multi-local means. Expert Systems with Applications, 67, 115–125.
Qi, X. H., Li, D. Q., Phoon, K. K., Cao, Z. J., and Tang, X. S. (2016). Simulation of geologic uncertainty using coupled Markov chain. Engineering geology, 207, 129–140.
Shi, C., and Wang, Y. (2021). Development of Subsurface Geological Cross-Section from Limited Site-Specific Boreholes and Prior Geological Knowledge Using Iterative Convolution XGBoost. Journal of Geotechnical and Geoenvironmental Engineering, 147, 04021082.
Wang, H., and Wei, X. Stochastic Stratigraphic Simulation and Uncertainty Quantification Using Machine Learning. In Geo-Congress 2022 (pp. 337–346).
Wang, H., Wang, X., Wellmann, J. F., and Liang, R. Y. (2019). A Bayesian unsupervised learning approach for identifying soil stratification using cone penetration data. Canadian Geotechnical Journal, 56, 1184–1205.
Wang, H., Wellmann, J. F., Li, Z., Wang, X., and Liang, R. Y. (2017). A segmentation approach for stochastic geological modeling using hidden Markov random fields. Mathematical Geosciences, 49(2), 145–177.
Wang, H., Wellmann, J. F., Li, Z., Wang, X., and Liang, R. Y. (2017). A segmentation approach for stochastic geological modeling using hidden Markov random fields. Mathematical Geosciences, 49, 145–177.
Wang, X., Wang, H., and Liang, R. Y. (2018). A method for slope stability analysis considering subsurface stratigraphic uncertainty. Landslides, 15(5), 925–936.
Wei, X., and Wang, H. (2022). Stochastic stratigraphic modeling using Bayesian machine learning. Engineering Geology, 307, 106789.
Zhang, J. Z., Liu, Z. Q., Zhang, D. M., Huang, H. W., Phoon, K. K., and Xue, Y. D. (2022). Improved coupled Markov chain method for simulating geological uncertainty. Engineering Geology, 298, 106539.
Zhao, C., Gong, W., Li, T., Juang, C. H., Tang, H., and Wang, H. (2021). Probabilistic characterization of subsurface stratigraphic configuration with modified random field approach. Engineering Geology, 288, 106138.
Information & Authors
Information
Published In
Geo-Risk 2023
Pages: 12 - 24
History
Published online: Jul 20, 2023
ASCE Technical Topics:
- Computer models
- Computer vision and image processing
- Continuum mechanics
- Deformation (mechanics)
- Engineering fundamentals
- Engineering mechanics
- Field tests
- Geology
- Geotechnical engineering
- Mathematics
- Methodology (by type)
- Models (by type)
- Probability
- Simulation models
- Solid mechanics
- Stochastic processes
- Structural mechanics
- Tests (by type)
- Warpage
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.