All Issue

2026 Vol.36, Issue 2 Preview Page

Original Article

Multi-Parameter Back Analysis of Rock Mass Properties Using Sparse Axis-Aligned Bayesian Optimization (SAASBO)

희소 축정렬 베이지안 최적화를 이용한 다중 암반 물성 역해석 기법

Dong-Gun Lee1
,
Soo-Ho Chang2
,
Gi-Jun Lee3
,
Tae-Ho Kang3
,
Ki-Il Song4
,
Gi-Yun Kim1
,
Soon-Wook Choi2*
이 동건1
,
장 수호2
,
이 기준3
,
강 태호3
,
송 기일4
,
김 기윤1
,
최 순욱2*
1Postdoctoral Researcher, Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology
2Senior Research Fellow, Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology
3Senior Researcher, Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology
4Professor, Department of Civil Engineering, Inha University
1한국건설기술연구원 지반연구본부 박사후연구원
2한국건설기술연구원 지반연구본부 선임연구위원
3한국건설기술연구원 지반연구본부 수석연구원
4인하대학교 사회인프라공학과 교수
*Corresponding Author
30 April 2026. pp. 171-187
PDF XML Citation
Abstract

The stability of underground structures is highly dependent on the uncertainty of in-situ rock mass properties, making reliable back analysis based on monitored responses essential. However, conventional back-analysis methods often encounter difficulties in high-dimensional problems involving the simultaneous estimation of multiple parameters, including excessive computational cost and premature convergence to local optima. To address these limitations, this study proposes a multi-parameter back-analysis method using Sparse Axis-Aligned Bayesian Optimization (SAASBO). The proposed approach estimates multiple rock mass properties simultaneously by minimizing the discrepancy between monitored responses and numerical analysis results. In the case of inverse analysis with nine parameters, SAASBO showed the fastest convergence and the lowest estimation error among the compared optimization methods, and it provided the best reproduction of the target responses. The results demonstrate that SAASBO can efficiently identify influential variables in a high-dimensional parameter space and achieve stable and accurate parameter estimation with a limited number of numerical evaluations. Therefore, the proposed method can be considered an effective and practical framework for multi-parameter back analysis in deep rock engineering applications.

Keywords
SAASBO
Back analysis
Rock mass properties
Bayesian optimization
High dimension

지하공간의 안정성 평가는 실제 암반 물성의 불확실성에 크게 좌우되므로, 계측응답을 이용한 신뢰성 높은 역해석 기법이 요구된다. 그러나 기존 역해석 기법은 다중 물성을 동시에 추정하는 고차원 문제에서 계산 비용 증가와 국부해 수렴 등의 한계를 가진다. 본 연구에서는 희소 축정렬 베이지안 최적화(SAASBO)를 이용한 다중 암반 물성 역해석 기법을 제안하였다. 제안 기법은 계측응답과 수치해석 결과의 오차를 최소화하도록 다수의 암반 물성을 동시에 추정하는 방식으로 구성하였다. 적용 결과, 9개 물성에 대한 역해석에서 SAASBO는 기존 기법 대비 가장 빠른 수렴 특성과 가장 낮은 추정 오차를 나타내었으며, 계측응답 재현성 또한 우수한 것으로 확인되었다. 이는 SAASBO가 고차원 다변수 역해석 문제에서 탐색 효율과 추정 정확도를 동시에 확보할 수 있음을 보여준다. 따라서 본 기법은 심부 암반의 물성 추정 및 안정성 평가를 위한 효과적인 역해석 방법으로 활용될 수 있을 것으로 판단된다.

키워드
희소 축정렬 최적화
역해석
암반 물성
베이지안 최적화
고차원
References
1

An, J.-S., Kim, B.-C., Moon, H.-K., Song, K.-I., and Su, G.-S., 2016, DEA optimization for operating tunnel back analysis. Journal of Korean Tunnelling and Underground Space Association, 18(2), 183-193.

10.9711/KTAJ.2016.18.2.183
2

Balandat, M., Karrer, B., Jiang, D., Daulton, S., Letham, B., Wilson, A.G., and Bakshy, E., 2020, BoTorch: A framework for efficient Monte-Carlo Bayesian optimization. Advances in Neural Information Processing Systems, 33, 21524-21538.

3

Brochu, E., Cora, V.M., and de Freitas, N., 2010, A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv:1012.2599.

4

Carvalho, C.M., Polson, N.G., and Scott, J.G., 2010, The horseshoe estimator for sparse signals. Biometrika, 97(2), 465-480.

10.1093/biomet/asq017
5

Ching, J., and Phoon, K.-K., 2012, Modeling parameters of structured clays as a multivariate normal distribution. Canadian Geotechnical Journal, 49(5), 522-545.

10.1139/t2012-015
6

Cividini, A., Jurina, L., and Gioda, G., 1981, Some aspects of characterization problems in geomechanics. International Journal of Rock Mechanics and Mining Sciences, 18(6), 487-503.

10.1016/0148-9062(81)90513-1
7

Deb, K., 2001, Multi-Objective Optimization Using Evolutionary Algorithms. John Wiley & Sons.

8

Eriksson, D., and Jankowiak, M., 2021, High-dimensional Bayesian optimization with sparse axis-aligned subspaces. Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI 2021), 493-503.

9

Feng, X.-T., Zhang, Z., and Sheng, Q., 2000, Estimating mechanical rock mass parameters relating to the Three Gorges Project permanent shiplock using an intelligent displacement back analysis method. International Journal of Rock Mechanics and Mining Sciences, 37(7), 1039-1054.

10.1016/S1365-1609(00)00035-6
10

Gioda, G., and Sakurai, S., 1987, Back analysis procedures for the interpretation of field measurements in geomechanics. International Journal for Numerical and Analytical Methods in Geomechanics, 11(6), 555-583.

10.1002/nag.1610110604
11

Hoffman, M.D., and Gelman, A., 2014, The No-U-Turn sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo. Journal of Machine Learning Research, 15(47), 1593-1623.

12

Holland, J.H., 1975, Adaptation in Natural and Artificial Systems. University of Michigan Press.

13

Jones, D.R., Schonlau, M., and Welch, W.J., 1998, Efficient global optimization of expensive black-box functions. Journal of Global Optimization, 13(4), 455-492.

10.1023/A:1008306431147
14

Kennedy, J., and Eberhart, R., 1995, Particle swarm optimization. Proceedings of ICNN 1995, 4, 1942-1948.

10.1109/ICNN.1995.488968
15

Lee, D., Kang, K., and Song, K., 2022, Multi-layered ground back analysis of retaining wall using differential evolution algorithm: basic research of digital twin. Journal of the Korean GEO-environmental Society, 23(1), 25-30.

10.14481/JKGES.2022.23.1.25
16

Miranda, T., Correia, A.G., and Sousa, L.R., 2011, Bayesian methodology for updating geomechanical parameters and uncertainty quantification. International Journal of Rock Mechanics and Mining Sciences, 48(7), 1013-1028.

17

Moreira, N., Miranda, T., Pinheiro, M., Fernandes, P., Dias, D., and Sousa, L.R., 2013, Back analysis of geomechanical parameters in underground works using an evolution strategy algorithm. Tunnelling and Underground Space Technology, 33, 143-158.

10.1016/j.tust.2012.08.011
18

Nocedal, J., and Wright, S.J., 2006, Numerical Optimization(2nd ed., Springer.

19

Park, J.-H., Park, D., and Lee, I.-M., 2013, Inverse analysis for estimating the ground properties with the measured tunneling data. Journal of Korean Tunnelling and Underground Space Association, 15(3), 235-245.

20

Rao, S.S., 1996, Engineering Optimization: Theory and Practice(3rd ed., John Wiley & Sons.

21

Sakurai, S., 1997, Lessons learned from field measurements in tunnelling. Tunnelling and Underground Space Technology, 12(4), 453-460.

10.1016/S0886-7798(98)00004-2
22

Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., and de Freitas, N., 2016, Taking the human out of the loop: A review of Bayesian optimization. Proceedings of the IEEE, 104(1), 148-175.

10.1109/JPROC.2015.2494218
23

Sharan, S.K., 2003, Elastic-brittle-plastic analysis of circular openings in Hoek-Brown media. International Journal of Rock Mechanics and Mining Sciences, 40(6), 817-824.

10.1016/S1365-1609(03)00040-6
24

Song, K.-I., Lee, D., and Kang, K., 2023, Digital twin-based back analysis for geotechnical structures. Computers and Geotechnics, 154, 105134.

25

Storn, R., and Price, K., 1997, Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, 11, 341-359.

10.1023/A:1008202821328
26

Swoboda, G., Ichikawa, Y., Dong, Q., and Zaki, M., 1999, Back analysis of large geotechnical models. International Journal for Numerical and Analytical Methods in Geomechanics, 23(13), 1455-1472.

10.1002/(SICI)1096-9853(199911)23:13<1455::AID-NAG33>3.0.CO;2-C
27

Vardakos, S., 2007, Back-analysis methods for optimal tunnel design. Ph.D. Thesis, Virginia Polytechnic Institute and State University.

28

Wang, Z., Hutter, F., Zoghi, M., Matheson, D., and de Freitas, N., 2016, Bayesian optimization in a billion dimensions via random embeddings. Journal of Artificial Intelligence Research, 55, 361-387.

10.1613/jair.4806
29

Zhu, W., Zhang, Q., and Li, S., 2014, Back analysis of geomechanical parameters using response surface method and numerical simulation. Rock and Soil Mechanics, 35(1), 77-85.

Information
  • Publisher :Korean Society for Rock Mechanics and Rock Engineering
  • Publisher(Ko) :한국암반공학회
  • Journal Title :Tunnel and Underground Space
  • Journal Title(Ko) :터널과 지하공간
  • Volume : 36
  • No :2
  • Pages :171-187
  • Received Date : 2026-04-09
  • Revised Date : 2026-04-23
  • Accepted Date : 2026-04-23
  • DOI :https://doi.org/10.7474/TUS.2026.36.2.171
Journal Informaiton Tunnel and Underground Space Tunnel and Underground Space
Online Submission
Archives
: Vol.27, 2017 ~
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close