journal article·2026-06

Tunnel Design in Rock Masses Under Uncertainty With Reliability Constraints and Natural Gradient Boosting‐Based Surrogates

Tran Vu‐Hoang, Tan Nguyen, Hung‐Thinh Pham‐Tran, Duy Ly‐Khuong, Tuan A. Pham

Publisher page

Abstract

ABSTRACT This study develops a reliability‐based framework for predicting and optimizing tunnel stability in rock masses under surcharge loading while explicitly accounting for both aleatory and epistemic uncertainties. A unified dataset for twin circular and square tunnels is generated using Adaptive Finite Element Limit Analysis under the generalized Hoek–Brown criterion. The results demonstrate that probabilistic predictions obtained using Natural Gradient Boosting provide accurate stability estimates together with well‐calibrated uncertainty bounds, consistently outperforming multiple baseline machine‐learning models. Validation against more than 300 independent Optum G2 simulations confirms strong agreement with numerical benchmarks. A dedicated uncertainty decomposition analysis further shows that neglecting either input uncertainty or model uncertainty can lead to misleading and potentially unsafe reliability estimates, underscoring the necessity of joint uncertainty propagation. Overall, the proposed framework enables robust, uncertainty‐aware tunnel design under reliability constraints and provides a practical decision‐support tool for rock engineering applications.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Geotechnical Engineering and Analysis · Tunneling and Rock Mechanics · Probabilistic and Robust Engineering Design

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Faculty of Civil Engineering Ton Duc Thang University Ho Chi Minh City Vietnam

Smart Computing in Civil Engineering Research Group Faculty of Civil Engineering Ton Duc Thang University Ho Chi Minh City Vietnam

Laboratory For Computational Mechanics Institute for Computational Science and Artificial Intelligence Van Lang University Ho Chi Minh City Vietnam

Faculty of Civil Engineering Van Lang School of Technology Van Lang University Ho Chi Minh City Viet Nam

Department of Civil and Architectural Engineering KTH Royal Institute of Technology Stockholm Sweden

References (45)

Show source-provided references
1. 10.1007/s00603‐011‐0138‐510.1007/s00603‐011‐0138‐5 ↗
2. 10.1007/s10064‐023‐03145‐z10.1007/s10064‐023‐03145‐z ↗
3. 10.1016/j.ijrmms.2019.05.00110.1016/j.ijrmms.2019.05.001 ↗
4. 10.1016/j.compgeo.2019.01.00410.1016/j.compgeo.2019.01.004 ↗
5. 10.1016/j.tust.2019.10303710.1016/j.tust.2019.103037 ↗
6. 10.1016/j.tust.2014.12.00310.1016/j.tust.2014.12.003 ↗
7. 10.1016/j.tust.2016.05.00710.1016/j.tust.2016.05.007 ↗
8. 10.1016/j.undsp.2022.01.00110.1016/j.undsp.2022.01.001 ↗
9. 10.1007/s00603‐017‐1336‐610.1007/s00603‐017‐1336‐6 ↗
10. 10.1007/s00603‐015‐0885‐910.1007/s00603‐015‐0885‐9 ↗
11. 10.1016/j.tust.2015.10.01310.1016/j.tust.2015.10.013 ↗
12. 10.1139/t99‐03810.1139/t99‐038 ↗
13. 10.1038/s41598‐025‐87989‐310.1038/s41598‐025‐87989‐3 ↗
14. 10.1038/s41598‐025‐93091‐510.1038/s41598‐025‐93091‐5 ↗
15. 10.1016/j.engfailanal.2024.10871910.1016/j.engfailanal.2024.108719 ↗
16. K.Krabbenhoft A.Lyamin andJ.Krabbenhoft Optum computational engineering (OptumG2) Computer software(2015).
17. 10.1016/j.compgeo.2018.10.00610.1016/j.compgeo.2018.10.006 ↗
18. 10.1007/s13369‐021‐05632‐510.1007/s13369‐021‐05632‐5 ↗
19. 10.1016/j.ress.2021.10753010.1016/j.ress.2021.107530 ↗
20. 10.1007/s12145‐024‐01380‐w10.1007/s12145‐024‐01380‐w ↗
21. 10.1007/s40098‐024‐00903‐y10.1007/s40098‐024‐00903‐y ↗
22. 10.1007/s40808‐023‐01802‐610.1007/s40808‐023‐01802‐6 ↗
23. 10.1016/j.ress.2014.10.02110.1016/j.ress.2014.10.021 ↗
24. 10.1016/j.ress.2024.11057510.1016/j.ress.2024.110575 ↗
25. 10.1016/j.ress.2021.10794510.1016/j.ress.2021.107945 ↗
26. Smith D. J. · 2021
27. 10.1016/j.ress.2020.10686010.1016/j.ress.2020.106860 ↗
28. 10.1016/j.compgeo.2024.10631910.1016/j.compgeo.2024.106319 ↗
29. 10.1016/j.istruc.2021.03.02010.1016/j.istruc.2021.03.020 ↗
30. T.Duan A.Anand andD. Y.Ding “NGBoost: Natural Gradient Boosting for Probabilistic Prediction ” inProceedings of the 37th International Conference on Machine Learning ed.D.HalIIIandS.Aarti(PMLR 2020) 2690–2700 Proceedings of Machine Learning Research.
31. 10.1016/j.asoc.2024.11166910.1016/j.asoc.2024.111669 ↗
32. 10.1109/tie.2023.333113610.1109/tie.2023.3331136 ↗
33. 10.1016/j.istruc.2024.10754310.1016/j.istruc.2024.107543 ↗
34. 10.1016/j.ress.2008.09.00710.1016/j.ress.2008.09.007 ↗
35. 10.1016/j.ress.2018.02.00410.1016/j.ress.2018.02.004 ↗
36. Zabinsky Z. B. · 2013
37. 10.1109/tevc.2010.205903110.1109/tevc.2010.2059031 ↗
38. 10.1016/j.ress.2011.06.01010.1016/j.ress.2011.06.010 ↗
39. Hoek‐Brown Failure Criterion‐2002 Edition
40. 10.1007/s10462‐020‐09896‐510.1007/s10462‐020‐09896‐5 ↗
41. 10.1038/s41598‐024‐79287‐110.1038/s41598‐024‐79287‐1 ↗
42. 10.1007/s11440‐024‐02266‐310.1007/s11440‐024‐02266‐3 ↗
43. 10.1016/j.compgeo.2023.10570710.1016/j.compgeo.2023.105707 ↗
44. 10.1016/j.tust.2023.10533010.1016/j.tust.2023.105330 ↗
45. 10.1016/j.tust.2019.04.01410.1016/j.tust.2019.04.014 ↗