Abstract
Land reclamation from ocean is a major solution to deal with land shortage in coastal megacities such as Hong Kong. The primary geotechnical risk associated with land reclamation is consolidation of fine-grained materials, e.g., soft marine deposit, and a sound understanding of spatial distribution of three-dimensional (3D) subsurface soil layer boundaries, or interfaces, and their stratigraphic connectivity to surrounding drainage boundaries is a prerequisite for an effective reclamation design. In practice, accurate delineation of 3D subsurface stratigraphic boundaries is challenging due to a lack of effective tools for building 3D subsurface geological domains from limited site-specific data while taking full account of geological uncertainty. In this study, a novel stratigraphic modelling and uncertainty quantification method, called 3D iterative convolution eXtreme Gradient Boosting (IC-XGBoost3D), is adopted for automatically developing 3D subsurface geological domains from limited measurements. IC-XGBoost3D roots in deep learning and learns typical stratigraphic features from a pair of perpendicular training images reflecting local prior geological knowledge. The method is physics-informed and data-driven and can efficiently build and update subsurface geological models from limited site-specific data with quantified uncertainty. The method is applied to develop the 3D subsurface geological domain of a reclamation site in Hong Kong. The model performance is evaluated statistically using leave-one-out cross-validation. Results indicate that complex depositional stratigraphic patterns of fine-grained materials at the reclamation site can reasonably be replicated. Effects of measurement data number on the model performance are investigated, and useful insights are gained for developing subsurface geological domains of reclamation sites.
Similar content being viewed by others
Change history
17 March 2023
A Correction to this paper has been published: https://doi.org/10.1007/s10064-023-03171-x
References
Caers J (2011) Modeling uncertainty in the earth sciences. John Wiley & Sons
Carle SF, Labolle EM, Weissmann GS, Van Brocklin D, Fogg GE (1998) Conditional simulation of hydrofacies architecture: a transition probability/Markov approach. Hydrogeol Models Sediment Aquifers Concepts Hydrogeol Environ Geol 1:147–170
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp 785–794
Ching J, Huang WH, Phoon KK (2020) 3D probabilistic site characterization by sparse Bayesian learning. J Eng Mech 146(12):04020134
Deutsch CV, Wang L (1996) Hierarchical object-based stochastic modeling of fluvial reservoirs. Math Geol 28(7):857–880
Deutsch CV, Journel AG (1992) Geostatistical software library and user’s guide. New York 119(147)
Dubuisson M, Jain AK (1994) A modified Hausdorff distance for object matching, vol 1. Proceedings of 12th International Conference on Pattern Recognition, Jerusalem, Israel, Abstract no. 4985725, pp 566–568
Feng W, Wu S, Yin Y, Zhang J, Zhang K (2017) A training image evaluation and selection method based on minimum data event distance for multiple-point geostatistics. Comput Geosci 104:35–53
Fung AKL, Foott R, Cheung RKH, Koutsoftas DC (1984) Practical conclusions from the geotechnical studies on offshore reclamation for the proposed Chek Lap Kok airport. Hong Kong Engineer 13(6):17–26
Glaser R, Haberzettl P, Walsh RP (1991) Land reclamation in Singapore, Hong Kong and Macau. GeoJournal 24(4):365–373
Gong W, Tang H, Wang H, Wang X, Juang CH (2019) Probabilistic analysis and design of stabilizing piles in slope considering stratigraphic uncertainty. Eng Geol 259:105162
Guardiano FB, Srivastava RM (1993) Multivariate geostatistics: beyond bivariate moments. Geostatistics Troia’92. Springer, Dordrecht, pp 133–144
Hastie T, Tibshirani R, Friedman J, Franklin J (2005) The elements of statistical learning: data mining, inference and prediction. Springer Science & Business Media
Han L, Wang L, Ding X, Wen H, Yuan X, Zhang W (2022a) Similarity quantification of soil parametric data and sites using confidence ellipses. Geosci Front 13(1):101280
Han L, Wang L, Zhang W, Geng B, Li S (2022b) Rockhead profile simulation using an improved generation method of conditional random field. J Rock Mech Geotech Eng 14(3):896–908
Huttenlocher DP, Klanderman GA, Rucklidge WJ (1993) Comparing images using the Hausdorff distance. IEEE Trans Pattern Anal 15:850–863
Lim TW (2020) Housing Policies in Hong Kong. East Asian Policy 12(01):110–124
Mariethoz G, Caers J (2014) Multiple-point geostatistics: stochastic modeling with training images. John Wiley & Sons
Mitchell TM (1997) Machine learning, vol 45. McGraw Hill, Burr Ridge, IL, pp 870–877 (issue 37)
Mood AM (1940) The distribution theory of runs. Ann Math Stat 11(4):367–392
Ngo V, Swift J, Chiang YY (2015) Visualizing land reclamation in Hong Kong: a web application. International Cartographic Conference
Pérez C, Mariethoz G, Ortiz JM (2014) Verifying the high-order consistency of training images with data for multiple-point geostatistics. Comput Geosci 70:190–205
Phoon K, Ching J, Shuku T (2021) Challenges in data-driven site characterization. Georisk Assess Manag Risk Eng Syst Geohazards 1–13
Qi X, Wang H, Chu J, Chiam K (2022) Two-dimensional prediction of the interface of geological formations: a comparative study. Tunn Undergr Space Technol 121:104329
Qi X, Wang H, Pan X, Chu J, Chiam K (2021) Prediction of interfaces of geological formations using the multivariate adaptive regression spline method. Undergr Sp 6(3):252–266
Shi C, Wang Y (2021a) Nonparametric and data-driven interpolation of subsurface soil stratigraphy from limited data using multiple point statistics. Can Geotech J 58(2):261–280
Shi C, Wang Y (2021b) Smart determination of borehole number and locations for stability analysis of multi-layered slopes using multiple point statistics and information entropy. Can Geotech J. https://doi.org/10.1139/cgj-2020-0327
Shi C, Wang Y (2021c) Development of subsurface geological cross-section from limited site-specific boreholes and prior geological knowledge using iterative convolution XGBoost. J Geotech Geoenviron Eng 147(9):04021082
Shi C, Wang Y (2021d) Training image selection for development of subsurface geological cross-section by conditional simulations. Eng Geol 295:106415
Shi C, Wang Y (2022a) Data-driven construction of three-dimensional subsurface geological models from limited site-specific boreholes and prior geological knowledge for underground digital twin. Tunn Undergr Space Technol 126:104493
Shi C, Wang Y (2022b) Data-driven sequential development of geological cross-sections along tunnel trajectory. Acta Geotechnica. https://doi.org/10.1007/s11440-022-01707-1
Strebelle S (2002) Sequential simulation drawing structures from training images. Stanford University, p 374 (Ph. D. thesis)
Wang X, Wang H, Liang RY, Zhu H, Di H (2018) A hidden Markov random field model based approach for probabilistic site characterization using multiple cone penetration test data. Struct Saf 70:128–138
Wang Y, Hu Y, Zhao T (2020) CPT-based subsurface soil classification and zonation in a 2D vertical cross-section using Bayesian compressive sampling. Can Geotech J 57(7):947–958
Wu S, Zhang JM, Wang R (2021) Machine learning method for CPTu based 3D stratification of New Zealand geotechnical database sites. Adv Eng Inform 50:101397
Yeung AT (2016) Geotechnical works of the Hong Kong-Zhuhai-Macao bridge project. Jpn Geotech Soc Spec Publ 2(2):109–121
Yeung AT, So ST (2001) Geotechnical engineering properties of Hong Kong marine clays. Soft Soil Engineering. Routledge, pp 695–700
Zhou C, Ouyang J, Ming W, Zhang G, Du Z, Liu Z (2019) A stratigraphic prediction method based on machine learning. Appl Sci 9(17):3553
Funding
The work described in this paper was supported by a grant from the Research Grant Council of Hong Kong Special Administrative Region (Project no. CityU 11202121) and a grant from Shenzhen Science and Technology Innovation Commission (Shenzhen-Hong Kong-Macau Science and Technology Project (Category C) No: SGDX20210823104002020), China. The financial support is gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
The original online version of this article was revised: The article was originally published with error. Figure 8 has been updated and its legend/caption.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Shi, C., Wang, Y. Machine learning of three-dimensional subsurface geological model for a reclamation site in Hong Kong. Bull Eng Geol Environ 81, 504 (2022). https://doi.org/10.1007/s10064-022-03009-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10064-022-03009-y