Quantifying the Uncertainty of Structural Parameters Using Machine Learning–Based Surrogate Models
Publication: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 11, Issue 2
Abstract
Uncertainty quantification is crucial for accurately assessing the seismic vulnerability of structures in performance-based earthquake engineering (PBEE). Traditional methods, such as the first order second moment (FOSM) approach, struggle with handling nonlinear structural responses, while Monte Carlo sampling simulations are computationally expensive. Machine learning–based surrogate models offer a more efficient alternative for uncertainty quantification. Despite their widespread use, current research on surrogate models often focuses on model training and predictive accuracy, without fully evaluating their efficiency and overall accuracy in uncertainty propagation. Moreover, selecting the most appropriate model and assessing its overall performance remain challenging. This study addresses these gaps by introducing machine learning–based surrogate models for more efficient uncertainty quantification, with a focus on concrete moment-resisting frames. The study identifies five key quantities of interest and conducts sensitivity analysis to determine influential variables under different seismic intensities. Six surrogate models—Gaussian process regression (GPR), multivariate adaptive regression splines (MARS), moving least squares (MLS), neural networks (NN), linear polynomial regression, and quadratic polynomial regression—are employed to quantify parameter uncertainty. A benchmark of 1,000 Latin hypercube sampling (LHS) finite element simulations is established as benchmark. Results demonstrate that surrogate models significantly reduce computational costs while maintaining high accuracy. The GPR method performs best under all conditions, followed by NN, both of which achieve high accuracy even with a limited sample size.
Practical Applications
The modeling parameters of engineering structures are often subject to uncertainty, which leads to variability in structural responses under seismic excitation. When quantifying the propagation of this uncertainty, traditional methods such as the first-order second-moment (FOSM) approach and Monte Carlo simulations present notable drawbacks—namely, low accuracy and high computational cost, respectively. Surrogate modeling provides an effective means to overcome these limitations. This study quantifies the uncertainty of modeling parameters for a four-story concrete moment-resisting frame using six commonly applied surrogate models. The models include Gaussian process regression (GPR), multivariate adaptive regression splines (MARS), moving least squares (MLS), neural networks (NN), linear polynomial (LP), and quadratic polynomial (QP) regression. Among these, GPR and NN demonstrate the highest accuracy, with GPR consistently delivering superior performance. The findings of this study offer valuable insights and practical guidance for selecting appropriate surrogate models in engineering applications, supporting more efficient and reliable uncertainty quantification in seismic response analysis.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This study was supported by funds from the National Key Research and Development Program of China (Grant No. 2023YFC3805203), the Scientific Research Fund of Institute of Engineering Mechanics, China Earthquake Administration (No. 2023B07), and Heilongjiang Natural Science Foundation for Distinguished Young Scholars (JQ2022E006).
References
Abrahamson, N. A., and J. J. Bommer. 2005. “Probability and uncertainty in seismic hazard analysis.” Earthquake Spectra 21 (2): 603–607. https://doi.org/10.1193/1.1899158.
Altoontash, A. 2004. “Simulation and damage models for performance assessment of reinforced concrete beam-column joints.” Ph.D. dissertation, Dept. of Civil and Environmental Engineering, Stanford Univ.
Baker, J. W., and C. A. Cornell. 2003. Uncertainty specification and propagation for loss estimation using FOSM method. San Francisco: Pacific Earthquake Engineering Research Center.
Bhattacharyya, B. 2022. “Uncertainty quantification of dynamical systems by a POD–Kriging surrogate model.” J. Comput. Sci. 60 (Apr): 101602. https://doi.org/10.1016/j.jocs.2022.101602.
Bradley, B. A. 2013. “A critical examination of seismic response uncertainty analysis in earthquake engineering.” Earthquake Eng. Struct. Dyn. 42 (11): 1717–1729. https://doi.org/10.1002/eqe.2331.
Bradley, B. A., and D. S. Lee. 2010. “Accuracy of approximate methods of uncertainty propagation in seismic loss estimation.” Struct. Saf. 32 (1): 13–24. https://doi.org/10.1016/j.strusafe.2009.04.001.
Çolak, H., H. T. Türker, and H. Coşkun. 2023. “Accurate estimation of inter-story drift ratio in multistory framed buildings using a novel continuous beam model.” Appl. Sci. 13 (13): 7819. https://doi.org/10.3390/app13137819.
Cornell, C. A., and H. Krawinkler. 2000. Progress and challenges in seismic performance assessment. Berkeley, CA: Pacific Earthquake Engineering Research Center.
Das, S., and S. Tesfamariam. 2023. “Reliability analysis of structures using probability density evolution method and stochastic spectral embedding surrogate model.” Earthquake Eng. Struct. Dyn. 52 (8): 2480–2497. https://doi.org/10.1002/eqe.3835.
Der Kiureghian, A., and O. Ditlevsen. 2009. “Aleatory or epistemic? Does it matter?” Struct. Saf. 31 (2): 105–112. https://doi.org/10.1016/j.strusafe.2008.06.020.
Elkady, A., and D. G. Lignos. 2015. “Effect of gravity framing on the overstrength and collapse capacity of steel frame buildings with perimeter special moment frames.” Earthquake Eng. Struct. Dyn. 44 (8): 1289–1307. https://doi.org/10.1002/eqe.2519.
Ellingwood, B. 1980. Development of a probability based load criterion for American National Standard A58. Gaithersburg, MD: NIST.
Ellingwood, B. R., O. C. Celik, and K. Kinali. 2007. “Fragility assessment of building structural systems in Mid-America.” Earthquake Eng. Struct. Dyn. 36 (13): 1935–1952. https://doi.org/10.1002/eqe.693.
Fardis, M. N., and D. E. Biskinis. 2003. “Deformation capacity of RC members, as controlled by flexure or shear.” In Proc., Otani Symp., 511–530. Lausanne, Switzerland: International Federation for Structural Concrete.
FEMA. 2009. Quantification of building seismic performance factors. Washington, DC: FEMA.
FEMA. 2012. Next-generation methodology for seismic performance assessment of buildings. Washington, DC: FEMA.
Forrester, A. I. J., and A. J. Keane. 2009. “Recent advances in surrogate-based optimization.” Prog. Aerosp. Sci. 45 (1–3): 50–79. https://doi.org/10.1016/j.paerosci.2008.11.001.
Friedman, J. H. 1991. “Multivariate adaptive regression splines.” Ann. Stat. 19 (1): 1–67. https://doi.org/10.1214/aos/1176347963.
Gokkaya, B. U., J. W. Baker, and G. G. Deierlein. 2016. “Quantifying the impacts of modeling uncertainties on the seismic drift demands and collapse risk of buildings with implications on seismic design checks.” Earthquake Eng. Struct. Dyn. 45 (10): 1661–1683. https://doi.org/10.1002/eqe.2740.
Hamburger R. O. 2011. “FEMA P-58-next-generation performance assessment of buildings.” In Proc., AEI 2011: Building Integration Solutions, 211–218. Reston, VA: ASCE.
Hardyniec, A., and F. A. Charney. 2014. “The effect of epistemic uncertainties in the assessment of seismic collapse of building structures.” In Proc., NCEE 2014—10th US National Conf. on Earthquake Engineering: Frontiers of Earthquake Engineering. Oakland, CA: Earthquake Engineering Research Institute.
Hariri-Ardebili, M. A., and B. Sudret. 2020. “Polynomial chaos expansion for uncertainty quantification of dam engineering problems.” Eng. Struct. 203 (Jan): 109631. https://doi.org/10.1016/j.engstruct.2019.109631.
Hart, G. C., and R. Vasudevan. 1975. “Earthquake design of buildings: Damping.” J. Struct. Div. 101 (1): 11–30. https://doi.org/10.1061/JSDEAG.0003964.
Haselton Baker Risk Group, LLC. 2021. “OpenSees structural model database.” Seismic Performance Prediction Platform. Accessed October 18, 2023. https://sp3risk.com/structural-model-database/.
Haselton, C. B., and G. G. Deierlein. 2007. Assessing seismic collapse safety of modern reinforced concrete moment-frame buildings. Berkeley, CA: Pacific Earthquake Engineering Research Center, Univ. of California.
Ibarra, L. 2003. “Global collapse of frame structures under seismic excitations.” Ph.D. dissertation, Dept. of Civil and Environmental Engineering, Stanford Univ.
Jalayer, F., I. Iervolino, and G. Manfredi. 2010. “Structural modeling uncertainties and their influence on seismic assessment of existing RC structures.” Struct. Saf. 32 (3): 220–228. https://doi.org/10.1016/j.strusafe.2010.02.004.
Kosič, M., P. Fajfar, and M. Dolšek. 2014. “Approximate seismic risk assessment of building structures with explicit consideration of uncertainties.” Earthquake Eng. Struct. Dyn. 43 (10): 1483–1502. https://doi.org/10.1002/eqe.2407.
Lancaster, P., and K. Salkauskas. 1981. “Surfaces generated by moving least squares methods.” Math. Comput. 37 (155): 141–158. https://doi.org/10.1090/S0025-5718-1981-0616367-1.
LeCun, Y., Y. Bengio, and G. Hinton. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Li, M., and Z. Wang. 2019. “Surrogate model uncertainty quantification for reliability-based design optimization.” Reliab. Eng. Syst. Saf. 192 (Dec): 106432. https://doi.org/10.1016/j.ress.2019.03.039.
Liel, A. B., C. B. Haselton, G. G. Deierlein, and J. W. Baker. 2009. “Incorporating modeling uncertainties in the assessment of seismic collapse risk of buildings.” Struct. Saf. 31 (2): 197–211. https://doi.org/10.1016/j.strusafe.2008.06.002.
Luco, N., B. R. Ellingwood, R. O. Hamburger, J. D. Hooper, J. K. Kimball, and C. A. Kircher. 2007. Risk-targeted versus current seismic design maps for the conterminous United States. Sacramento, CA: Structural Engineers Association of California.
Marelli, S., and B. Sudret. 2018. “An active-learning algorithm that combines sparse polynomial chaos expansions and bootstrap for structural reliability analysis.” Struct. Saf. 75 (Nov): 67–74. https://doi.org/10.1016/j.strusafe.2018.06.003.
McKay, M. D., R. J. Beckman, and W. J. Conover. 2000. “A comparison of three methods for selecting values of input variables in the analysis of output from a computer code.” Technometrics 42 (1): 55–61. https://doi.org/10.1080/00401706.2000.10485979.
Melchers, R. E. 1999. Structural reliability: Analysis and prediction. New York: Wiley.
Micheli, L., A. Alipour, and S. Laflamme. 2020. “Multiple-surrogate models for probabilistic performance assessment of wind-excited tall buildings under uncertainties.” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part A: Civ. Eng. 6 (4): 04020042. https://doi.org/10.1061/AJRUA6.0001091.
Moustapha, M., J.-M. Bourinet, B. Guillaume, and B. Sudret. 2018. “Comparative study of Kriging and support vector regression for structural engineering applications.” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part A: Civ. Eng. 4 (2): 04018005. https://doi.org/10.1061/AJRUA6.0000950.
O’Reilly, G. J., and T. J. Sullivan. 2018. “Quantification of modelling uncertainty in existing Italian RC frames.” Earthquake Eng. Struct. Dyn. 47 (4): 1054–1074. https://doi.org/10.1002/eqe.3005.
Panagiotakos, T. B., and M. N. Fardis. 2001. “Deformations of reinforced concrete members at yielding and ultimate.” ACI Struct. J. 98 (2): 135–148. https://doi.org/10.14359/10181.
Porter, K. A., J. L. Beck, and R. V. Shaikhutdinov. 2002. Investigation of sensitivity of building loss estimates to major uncertain variables for the Van Nuys testbed. Berkeley, CA: Pacific Earthquake Engineering Research Center. https://peer.berkeley.edu/publications/2002-03.
Rota, M., A. Penna, and G. Magenes. 2014. “A framework for the seismic assessment of existing masonry buildings accounting for different sources of uncertainty.” Earthquake Eng. Struct. Dyn. 43 (7): 1045–1066. https://doi.org/10.1002/eqe.2386.
Seeger, M. 2004. “Gaussian processes for machine learning.” Int. J. Neural Syst. 14 (2): 69–106. https://doi.org/10.1142/S0129065704001899.
Shome, N., N. Jayaram, and M. Rahnama. 2012. “Uncertainty and spatial correlation models for earthquake losses.” In Proc., 15th World Conf. on Earthquake Engineering. Tokyo: International Association for Earthquake Engineering.
Slot, R. M. M., J. D. Sørensen, B. Sudret, L. Svenningsen, and M. L. Thøgersen. 2020. “Surrogate model uncertainty in wind turbine reliability assessment.” Renewable Energy 151 (May): 1150–1162. https://doi.org/10.1016/j.renene.2019.11.101.
Su, L., X.-L. Li, and Y.-P. Jiang. 2020. “Comparison of methodologies for seismic fragility analysis of unreinforced masonry buildings considering epistemic uncertainty.” Eng. Struct. 205 (Feb): 110059. https://doi.org/10.1016/j.engstruct.2019.110059.
Sudret, B., S. Marelli, and J. Wiart. 2017. “Surrogate models for uncertainty quantification: An overview.” In Proc., 2017 11th European Conf. on Antennas and Propagation (EUCAP), 793–797. New York: IEEE.
Vamvatsikos, D., and M. Fragiadakis. 2010. “Incremental dynamic analysis for estimating seismic performance sensitivity and uncertainty.” Earthquake Eng. Struct. Dyn. 39 (2): 141–163. https://doi.org/10.1002/eqe.935.
Zaker Esteghamati, M., and M. M. Flint. 2021. “Developing data-driven surrogate models for holistic performance-based assessment of mid-rise RC frame buildings at early design.” Eng. Struct. 245 (Oct): 112971. https://doi.org/10.1016/j.engstruct.2021.112971.
Zhang, X., and S. Mahadevan. 2020. “Bayesian neural networks for flight trajectory prediction and safety assessment.” Decis. Support Syst. 131 (Apr): 113246. https://doi.org/10.1016/j.dss.2020.113246.
Information & Authors
Information
Published In
ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 11 • Issue 2 • June 2025
Copyright
© 2025 American Society of Civil Engineers.
History
Received: Oct 30, 2024
Accepted: Jan 29, 2025
Published online: Apr 4, 2025
Published in print: Jun 1, 2025
Discussion open until: Sep 4, 2025
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.
