Machine Learning for Enhanced Regional Seismic Risk Assessments
Publication: Journal of Structural Engineering
Volume 148, Issue 9
Abstract
The ability to conduct accurate regional seismic risk assessments is key to informing a risk-reduction policy and fostering community resilience. This paper presents a machine learning-based framework to predict a building’s postearthquake damage state using structural properties and ground motion intensity measures as model inputs. The machine learning techniques assessed, namely, logistic regression, k-nearest neighbors, decision tree, random forest, AdaBoost, and gradient boosting, are trained using a dataset of nonlinear response history analysis results from 36 detailed structural models of modern reinforced concrete shear wall buildings ranging from four to 24 stories and subjected to approximately 500 ground motion records with a range of shaking intensities. The results indicate that the gradient boosting classifier is the most efficient algorithm by achieving a prediction success (F1-score) of 87%. The proposed framework also leverages synthetic data samples to support the prediction of severe damage state instances, that is, collapse. The percentage of observed collapse cases correctly classified by the gradient boosting algorithm is increased from 76% to 93% when synthetic data are also used for training. The framework is implemented in a portfolio of reinforced concrete shear wall buildings across the Metro Seattle region to quantify earthquake-induced damage and collapse risk. The framework shows great potential for enhancing regional seismic risk assessments by leveraging datasets of detailed nonlinear response history analysis results.
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 generated or used during the study are available in a repository or online in accordance with funder data retention policies. The data compiled as a companion to this paper can be found by locating the paper in the publications list found on the following web page (https://www.carlosmolinahutt.com/publications) and accessing the supplied “Electronic Supplement” link in the Data Availability Statement. The electronic supplement includes the following:
(I): Input data spreadsheet,
(II): Hyperparameter optimization procedure,
(III): Predictive modeling process and calculation for damage state classification, and
(IV): Predictive modeling process and calculation for collapse status identification.
Acknowledgments
The authors thank Nasser Marafi (Risk Management Solutions) for sharing the structural design and analysis results of archetype buildings used in this manuscript.
References
Andrew, E., T. Jo, and N. Japkowicz. 2004. “A multiple resampling method for learning from imbalanced data sets.” Comput. Intell. 20 (1): 18–36. https://doi.org/10.1111/j.0824-7935.2004.t01-1-00228.x.
ASCE. 2016. Minimum design loads for buildings and other structures. ASCE/SEI 7-16. Reston, VA: ASCE.
ATC (Applied Technology Council). 1995. Procedures for postearthquake building safety evaluation procedures. ATC-20. Redwood, CA: ATC.
Awoyemi, J. O., A. O. Adetunmbi, and S. A. Oluwadare. 2017. “Credit card fraud detection using machine learning techniques: A comparative analysis.” In Proc., Int. Conf. on Computing, Networking and Informatics, ICCNI 2017. New York: IEEE. https://doi.org/10.1109/ICCNI.2017.8123782.
Bradley, B. A. 2011. “Empirical equations for the prediction of displacement spectrum intensity and its correlation with other intensity measures.” Soil Dyn. Earthquake Eng. 31 (8): 1182–1191. https://doi.org/10.1016/j.soildyn.2011.04.007.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Breiman, L., J. Friedman, R. Olshen, and C. Stone. 2017. Classification and regression tree. Boca Raton, FL: Routledge.
Cawley, G. C., and N. L. C. Talbot. 2010. “On over-fitting in model selection and subsequent selection bias in performance evaluation.” J. Mach. Learn. Res. 11 (70): 2079–2107.
Charney, F. A. 1990. “Wind drift serviceability limit state design of multistory buildings.” J. Wind Eng. Ind. Aerodyn. 36 (Jan): 203–212. https://doi.org/10.1016/0167-6105(90)90305-V.
Chawla, N. V., K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer. 2002. “SMOTE: Synthetic minority over-sampling technique.” J. Artif. Intell. Res. 16 (2): 321–357. https://doi.org/10.1613/jair.953.
City of Seattle Department of Planning and Developments. 2015. “Alternate design requirements for use of special reinforced concrete shear walls in over height buildings.” Accessed April 21, 2018. www.seattle.gov/dpd/codes/dr/DR2015-5.pdf.
Dilger, W. G., and H. Cao. 1991. “Behaviour of slab-column connections under reversed cyclic loading.” In Proc., 2nd Int. Conf. of High-Rise Buildings. Beijing: Atlantis Press.
Dilger, W. H., and S. J. Brown. 1995. “Earthquake resistance of slab-column connections.” In Vol. 60 of Festschrift Professor Dr. Hugo Bachmann Zum, 22–27. Zurich, Switzerland: Institut fur Baustatik unf Konstruktion.
Eksir Monfared, A., C. Molina Hutt, P. Kakoty, P. Kourehpaz, and J. Centeno. 2021. “Effects of the Georgia sedimentary basin on the response of modern tall RC shear-wall buildings to M9 Cascadia subduction zone earthquakes.” J. Struct. Eng. 147 (8): 05021003. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003067.
Emporis. 2018. “The global provider of building data.” Accessed January 20, 2021. https://www.emporis.com/.
Fairhurst, M., A. Bebamzadeh, and C. E. Ventura. 2019. “Effect of ground motion duration on reinforced concrete shear wall buildings.” Earthquake Spectra 35 (1): 311–331. https://doi.org/10.1193/101117EQS201M.
FEMA. 2012. Seismic performance assessment of buildings. FEMA P-58. Washington, DC: FEMA.
FEMA. 2020. Hazus–MH 4.2: Earthquake model technical manual. Washington, DC: FEMA.
Frankel, A. 2013. “Rupture history of the 2011 M9 Tohoku Japan earthquake determined from strong-motion and high-rate GPS recordings: Subevents radiating energy in different frequency bands.” Bull. Seismol. Soc. Am. 103 (2B): 1290–1306. https://doi.org/10.1785/0120120148.
Frankel, A. 2017. “Modeling strong-motion recordings of the 2010 8.8 Maule, Chile, earthquake with high stress-drop subevents and background slip.” Bull. Seismol. Soc. Am. 107 (1): 372–386. https://doi.org/10.1785/0120160127.
Frankel, A., W. Stephenson, and D. Carver. 2009. “Sedimentary basin effects in Seattle, Washington: Ground-motion observations and 3D simulations.” Bull. Seismol. Soc. Am. 99 (3): 1579–1611. https://doi.org/10.1785/0120080203.
Frankel, A., E. Wirth, N. Marafi, J. Vidale, and W. Stephenson. 2018. “Broadband synthetic seismograms for magnitude 9 earthquakes on the Cascadia megathrust based on 3D simulations and stochastic synthetics, Part 1: Methodology and overall results.” Bull. Seismol. Soc. Am. 108 (5): 2347–2369. https://doi.org/10.1785/0120180034.
Freund, Y., and R. E. Schapire. 1997. “A decision-theoretic generalization of on-line learning and an application to boosting.” J. Comput. Syst. Sci. 55 (1): 119–139. https://doi.org/10.1006/jcss.1997.1504.
Friedman, J. 2001. “Greedy function approximation: A gradient boosting machine.” Ann. Stat. 29 (5): 1189–1232. https://doi.org/10.1214/aos/1013203451.
Hosmer, D. W., Jr., S. Lemeshow, and R. X. Sturdivant. 2013. Applied logistic regression. Hoboken, NJ: Wiley.
Hossin, M., and M. N. Sulaiman. 2015. “A review on evaluation metrics for data classification evaluations.” Int. J. Data Min. Knowl. Manage. Process 5 (2): 1–11. https://doi.org/10.5121/ijdkp.2015.5201.
Housner, G. W. 1952. “Spectrum intensities of strong-motion earthquakes.” In Proc., Symp. on Earthquake and Blast Effects on Structures, 20–36. Los Angeles: Earthquake Engineering Research Institute.
Hueste, M. B. D., J. Browning, A. Lepage, and J. W. Wallace. 2007. “Seismic design criteria for slab-column connections.” ACI Struct. J. 104 (4): 448–458. https://doi.org/10.14359/18775.
Hueste, M. B. D., T. H. K. Kang, and I. N. Robertson. 2009. “Lateral drift limits for structural concrete slab-column connections including shear reinforcement effects.” In Proc., ASCE 2009 Structures Congress. Reston, VA: ASCE.
Hwang, S. H., S. Mangalathu, J. Shin, and J. S. Jeon. 2021. “Machine learning-based approaches for seismic demand and collapse of ductile reinforced concrete building frames.” J. Build. Eng. 34 (Feb): 101905. https://doi.org/10.1016/j.jobe.2020.101905.
Jalayer, F., and C. A. Cornell. 2009. “Alternative nonlinear demand estimation methods for probability-based seismic assessments.” Earthquake Eng. Struct. Dyn. 38 (8): 951–972. https://doi.org/10.1002/eqe.876.
Jeni, L. A., J. F. Cohn, and F. De La Torre. 2013. “Facing imbalanced data—Recommendations for the use of performance metrics.” In Proc., 2013 Humaine Association Conf. on Affective Computing and Intelligent Interaction, ACII 2013, 245–251. New York: IEEE.
Kakoty, P., S. M. Dyaga, and C. Molina Hutt. 2021. “Impacts of simulated M9 Cascadia subduction zone earthquakes considering amplifications due to the Georgia sedimentary basin on reinforced concrete shear wall buildings.” Earthquake Eng. Struct. Dyn. 50 (1): 237–256. https://doi.org/10.1002/eqe.3361.
Kiani, J., C. Camp, and S. Pezeshk. 2019. “On the application of machine learning techniques to derive seismic fragility curves.” Comput. Struct. 218 (Jul): 108–122. https://doi.org/10.1016/j.compstruc.2019.03.004.
King County. 2018. “ParcelViewer.” Accessed January 20, 2021. https://gismaps.kingcounty.gov/parcelviewer2.
Kourehpaz, P., C. Molina Hutt, N. A. Marafi, J. W. Berman, and M. O. Eberhard. 2021. “Estimating economic losses of midrise reinforced concrete shear wall buildings in sedimentary basins by combining empirical and simulated seismic hazard characterizations.” Earthquake Eng. Struct. Dyn. 50 (1): 26–42. https://doi.org/10.1002/eqe.3325.
Kunnath, S. K., Y. Heo, and J. F. Mohle. 2009. “Nonlinear uniaxial material model for reinforcing steel bars.” J. Struct. Eng. 135 (4): 335–343. https://doi.org/10.1061/(ASCE)0733-9445(2009)135:4(335).
Mangalathu, S., H. Sun, C. C. Nweke, Z. Yi, and H. V. Burton. 2020. “Classifying earthquake damage to buildings using machine learning.” Earthquake Spectra 36 (1): 183–208. https://doi.org/10.1177/8755293019878137.
Marafi, N. A., K. A. Ahmed, D. E. Lehman, and L. N. Lowes. 2019. “Variability in seismic collapse probabilities of solid- and coupled-wall buildings.” J. Struct. Eng. 145 (6): 04019047. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002311.
Marafi, N. A., J. W. Berman, and M. O. Eberhard. 2016. “Ductility-dependent intensity measure that accounts for ground-motion spectral shape and duration.” Earthquake Eng. Struct. Dyn. 45 (4): 653–672. https://doi.org/10.1002/eqe.2678.
Marafi, N. A., M. O. Eberhard, J. W. Berman, E. A. Wirth, and A. D. Frankel. 2017. “Effects of deep basins on structural collapse during large subduction earthquakes.” Earthquake Spectra 33 (3): 963–997. https://doi.org/10.1193/071916eqs114m.
Marafi, N. A., A. J. Makdisi, J. W. Berman, and M. O. Eberhard. 2020a. “Design strategies to achieve target collapse risks for reinforced concrete wall buildings in sedimentary basins.” Earthquake Spectra 36 (3): 1038–1073. https://doi.org/10.1177/8755293019899965.
Marafi, N. A., A. J. Makdisi, M. O. Eberhard, and J. W. Berman. 2020b. “Impacts of an M9 Cascadia Subduction Zone earthquake and Seattle basin on performance of RC Core Wall buildings.” J. Struct. Eng. 146 (2): 04019201. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002490.
Martins, L., and V. Silva. 2021. “Development of a fragility and vulnerability model for global seismic risk analyses.” Bull. Earthquake Eng. 19 (15): 6719–6745. https://doi.org/10.1007/s10518-020-00885-1.
Megally, S., and A. Ghali. 2000. “Punching shear design of earthquake-resistant slab column connections.” ACI Struct. J. 97 (5): 720–730. https://doi.org/10.14359/8807.
Menegotto, M., and P. E. Pinto. 1973. “Method of analysis for cyclically loaded reinforced concrete plane frames including changes in geometry and nonelastic behavior of elements under combined normal force and bending.” In Proc., Symp. on the Resistance and Ultimate Deformability of Structures Acted on by Well Defined Repeated Loads, 15–22. Zurich, Switzerland: International Association for Bridge and Structural Engineering.
Molina Hutt, C., A. M. Hulsey, P. Kakoty, G. G. Deierlein, A. Eksir Monfared, Y. Wen-Yi, and J. D. Hooper. 2021. “Toward functional recovery performance in the seismic design of modern tall buildings.” Earthquake Spectra 38 (1): 283–309. https://doi.org/10.1177/87552930211033620.
Molina Hutt, C., T. Rossetto, and G. G. Deierlein. 2019. “Comparative risk-based seismic assessment of 1970s vs modern tall steel moment frames.” J. Constr. Steel Res. 159 (Aug): 598–610. https://doi.org/10.1016/j.jcsr.2019.05.012.
Nguyen, H. M., E. W. Cooper, and K. Kamei. 2011. “Borderline over-sampling for imbalanced data classification.” Int. J. Knowl. Eng. Soft Data Paradigms 3 (1): 4–21. https://doi.org/10.1504/IJKESDP.2011.039875.
Pagani, M., et al. 2014. “OpenQuake engine: An open hazard (and risk) software for the global earthquake model.” Seismol. Res. Lett. 85 (3): 692–702. https://doi.org/10.1785/0220130087.
Parvin, H., B. Minaei-Bidgoli, and H. Alinejad-Rokny. 2013. “A new imbalanced learning and dictions tree method for breast cancer diagnosis.” J. Bionanosci. 7 (6): 673–678. https://doi.org/10.1166/jbns.2013.1162.
Pedregosa, F., et al. 2011. “Scikit-learn: Machine learning in Python.” J. Mach. Learn. Res. 12 (Oct): 2825–2830. https://doi.org/10.48550/arXiv.1201.0490.
PEER (Pacific Earthquake Engineering Research Center). 2017. Guidelines for performance-based seismic design of tall buildings. Berkeley, CA: PEER Center, Univ. of California.
Petersen, M. D., et al. 2020. “The 2018 update of the US National Seismic Hazard Model: Overview of model and implications.” Earthquake Spectra 36 (1): 5–41. https://doi.org/10.1177/8755293019878199.
Peterson, L. 2009. “K-nearest neighbor.” Scholarpedia 4 (2): 1883. https://doi.org/10.4249/scholarpedia.1883.
Popovics, S. 1973. “A numerical approach to the complete stress-strain curve of concrete.” Cem. Concr. Res. 3 (5): 583–599. https://doi.org/10.1016/0008-8846(73)90096-3.
Pugh, J. S., L. N. Lowes, and D. E. Lehman. 2015. “Nonlinear line-element modeling of flexural reinforced concrete walls.” Eng. Struct. 104 (Dec): 174–192. https://doi.org/10.1016/j.engstruct.2015.08.037.
Pulagam, S. 2020. “Feature scaling: Effectively choose input variables based on distributions.” Accessed November 30, 2021. https://towardsdatascience.com/feature-scaling-effectively-choose-input-variables-based-on-distributions-3032207c921f.
Ray, S. 2019. “A quick review of machine learning algorithms.” In Proc., 2019 Int. Conf. on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon). New York: IEEE. https://doi.org/10.1109/COMITCon.2019.8862451.
Shamsudin, H., U. K. Yusof, A. Jayalakshmi, and M. N. Akmal Khalid. 2020. “Combining oversampling and undersampling techniques for imbalanced classification: A comparative study using credit card fraudulent transaction dataset.” In Proc., 2020 IEEE 16th Int. Conf. on Control & Automation (ICCA), 803–808. New York: IEEE.
Silva, V., et al. 2019. “Current challenges and future trends in analytical fragility and vulnerability modeling.” Earthquake Spectra 35 (4): 1927–1952. https://doi.org/10.1193/042418EQS101O.
Sun, H., H. Burton, and J. Wallace. 2019. “Reconstructing seismic response demands across multiple tall buildings using kernel-based machine learning methods.” Struct. Control Health Monit. 26 (7): 1–26. https://doi.org/10.1002/stc.2359.
Vishal, R. 2018. “Feature selection-correlation and P-value.” Accessed November 30, 2021. https://towardsdatascience.com/feature-selection-correlation-and-p-value-da8921bfb3cf.
Yassin, M. H. 1994. Nonlinear analysis of prestressed concrete structures under monotonic and cycling loads. Berkeley, CA: Univ. of California.
Zhang, C., and Y. Ma. 2012. Ensemble machine learning: Methods and applications. New York: Springer.
Zhang, Y., H. V. Burton, H. Sun, and M. Shokrabadi. 2018. “A machine learning framework for assessing postearthquake structural safety.” Struct. Saf. 72 (May): 1–16. https://doi.org/10.1016/j.strusafe.2017.12.001.
Information & Authors
Information
Published In
Journal of Structural Engineering
Volume 148 • Issue 9 • September 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Jan 7, 2022
Accepted: Apr 15, 2022
Published online: Jun 29, 2022
Published in print: Sep 1, 2022
Discussion open until: Nov 29, 2022
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.
Cited by
- Abdelrahman Abushanab, Tadesse Gemeda Wakjira, Wael Alnahhal, Machine Learning-Based Flexural Capacity Prediction of Corroded RC Beams with an Efficient and User-Friendly Tool, Sustainability, 10.3390/su15064824, 15, 6, (4824), (2023).
- Jishuai Wang, Yazhou Xie, Tong Guo, Zhenyu Du, Predicting seismic interaction effect between soil and structure group using convolutional neural network, Structures, 10.1016/j.istruc.2023.02.087, 50, (1011-1020), (2023).