Explainable XGBoost–SHAP Machine-Learning Model for Prediction of Ground Motion Duration in New Zealand
Abstract
Although ground motion duration significantly influences structural response, there is a lack of accurate prediction models for ground motion duration. Ground motion duration plays a vital role in structural response during an earthquake. Even a small magnitude event may cause severe structural damage if the duration of the earthquake is long. Thus, accurate estimation of ground motion duration is essential for structural seismic design and analysis. This article uses machine learning techniques to estimate ground motion duration for the New Zealand region. This paper investigates the use of emerging machine learning algorithms to address this critical issue using data from the New Zealand earthquakes database. The utility of the prediction models is also evaluated using numerous parameters related to filtering frequencies, fault dimensions, S-wave triggering flag, etc., apart from the traditional source, path, and site. Other parameters, e.g., the usable frequency range and the uncertainty of the available parameters, are also considered in evaluating the prediction of the considered machine learning models. Root mean squared error, along with the coefficient of determination (), is used to evaluate the performance of the machine learning models. The method with the least difference between actual and predicted values on the test set is presented for each duration metric available within the New Zealand database. Most importantly, the game theory-based SHapely Additive exPlanations (SHAP) are provided as to whether each independent variable would push the predictions toward higher or lower values. These explanations demonstrate the relative importance of the parameters within the strong motion database in the prediction of earthquake duration.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data, models, or codes that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The first author acknowledges and appreciates the financial support received from the Ministry of Earth Sciences (MoES) in India through the MoES/P.O.(Seismo)/1(382)/2020 project. This paper represents the opinions of the author(s) and does not mean to represent the position or opinions of the sponsors.
References
Abrahamson, N. A., W. J. Silva, and R. Kamai. 2014. “Summary of the ASK14 ground motion relation for active crustal regions.” Earthquake Spectra 30 (3): 1025–1055. https://doi.org/10.1193/070913EQS198M.
Afshari, K., and J. P. Stewart. 2016. “Physically parameterized prediction equations for significant duration in active crustal regions.” Earthquake Spectra 32 (4): 2057–2081. https://doi.org/10.1193/063015EQS106M.
Akehashi, H., K. Kojima, E. N. Farsangi, and I. Takewaki. 2018. “Critical response evaluation of damped bilinear hysteretic SDOF model under long duration ground motion simulated by multi impulse motion.” Int. J. Earthquake Impact Eng. 2 (4): 298–321. https://doi.org/10.1504/IJEIE.2018.099361.
Arias, A. 1970. “Measure of earthquake intensity.” In Seismic design for nuclear plants, 438–483, edited by R. J. Hansen. Cambridge, MA: Massachusetts Institute of Technology Press.
Arjun, C. R., and A. Kumar. 2011. “Neural network estimation of duration of strong ground motion using Japanese earthquake records.” Soil Dyn. Earthquake Eng. 31 (7): 866–872. https://doi.org/10.1016/j.soildyn.2011.01.001.
Basim, M. C., and H. E. Estekanchi. 2015. “Application of endurance time method in performance-based optimum design of structures.” Struct. Saf. 56 (Sep): 52–67. https://doi.org/10.1016/j.strusafe.2015.05.005.
Bishop, C. M., and N. M. Nasrabadi. 2006. Pattern recognition and machine learning. New York: Springer.
Bolt, B. A. 1973. “Duration of strong ground motion.” In Proc., 5th World Conf. on Earthquake Engineering, 1304–1313. Tokyo: International Association for Earthquake Engineering.
Bommer, J. J., J. Hancock, and J. E. Alarcón. 2006. “Correlations between duration and number of effective cycles of earthquake ground motion.” Soil Dyn. Earthquake Eng. 26 (1): 1–13. https://doi.org/10.1016/j.soildyn.2005.10.004.
Bommer, J. J., G. Magenes, J. Hancock, and P. Penazzo. 2004. “The influence of strong-motion duration on the seismic response of masonry structures.” Bull. Earthquake Eng. 2 (Jan): 1–26. https://doi.org/10.1023/B:BEEE.0000038948.95616.bf.
Bommer, J. J., and A. Martinez-Pereira. 1999. “The effective duration of earthquake strong motion.” J. Earthquake Eng. 3 (2): 127–172. https://doi.org/10.1142/S1363246999000077.
Bommer, J. J., P. J. Stafford, and J. E. Alarcón. 2009. “Empirical equations for the prediction of the significant, bracketed, and uniform duration of earthquake ground motion.” Bull. Seismol. Soc. Am. 99 (6): 3217–3233. https://doi.org/10.1785/0120080298.
Boore, D. M., J. P. Stewart, E. Seyhan, and G. M. Atkinson. 2014. “NGA-West2 equations for predicting PGA, PGV, and 5% damped PSA for shallow crustal earthquakes.” Earthquake Spectra 30 (3): 1057–1085. https://doi.org/10.1193/070113EQS184M.
Bravo-Haro, M. A., and A. Y. Elghazouli. 2018. “Influence of earthquake duration on the response of steel moment frames.” Soil Dyn. Earthquake Eng. 115 (Dec): 634–651. https://doi.org/10.1016/j.soildyn.2018.08.027.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (Oct): 5–32. https://doi.org/10.1023/A:1010933404324.
Campbell, K. W., and Y. Bozorgnia. 2014. “NGA-West2 ground motion model for the average horizontal components of PGA, PGV, and 5% damped linear acceleration response spectra.” Earthquake Spectra 30 (3): 1087–1115. https://doi.org/10.1193/062913EQS175M.
Chalup, S. K., C. L. Murch, and M. J. Quinlan. 2007. “Machine learning with AIBO robots in the four-legged league of RoboCup.” IEEE Trans. Syst. Man Cybern. Part C: Appl. Rev. 37 (3): 297–310. https://doi.org/10.1109/TSMCC.2006.886964.
Chandramohan, R., J. W. Baker, and G. G. Deierlein. 2016. “Quantifying the influence of ground motion duration on structural collapse capacity using spectrally equivalent records.” Earthquake Spectra 32 (Sep): 927–950. https://doi.org/10.1193/122813eqs298mr2.
Chen, T., and C. Guestrin. 2016. “XGBoost: A scalable tree boosting system.” In Proc., 22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 785–794. New York: Association for Computing Machinery.
Chen, T., T. He, M. Benesty, V. Khotilovich, Y. Tang, H. Cho, K. Chen, R. Mitchell, I. Cano, and T. Zhou. 2015. “XGBoost: Extreme gradient boosting.” R Package 1 (4): 1–4.
Derras, B., P. Y. Bard, and F. Cotton. 2014. “Towards fully data driven ground-motion prediction models for Europe.” Bull. Earthquake Eng. 12 (1): 495–516. https://doi.org/10.1007/s10518-013-9481-0.
Derras, B., P.-Y. Bard, and F. Cotton. 2016. “Site-condition proxies, ground motion variability, and data-driven GMPEs: Insights from the NGA-West2 and RESORCE data sets.” Earthquake Spectra 32 (4): 2027–2056. https://doi.org/10.1193/060215EQS082M.
Derras, B., P.-Y. Bard, F. Cotton, and A. Bekkouche. 2012. “Adapting the neural network approach to PGA prediction: An example based on the KiK-net data.” Bull. Seismol. Soc. Am. 102 (4): 1446–1461. https://doi.org/10.1785/0120110088.
Dobry, R., I. M. Idriss, and E. Ng. 1978. “Duration characteristics of horizontal components of strong-motion earthquake records.” Bull. Seismol. Soc. Am. 68 (5): 1487–1520. https://doi.org/10.1785/BSSA0680051487.
Douglas, J. 2003. “Earthquake ground motion estimation using strong-motion records: A review of equations for the estimation of peak ground acceleration and response spectral ordinates.” Earth Sci. Rev. 61 (1–2): 43–104. https://doi.org/10.1016/S0012-8252(02)00112-5.
Douglas, J., and B. Edwards. 2016. “Recent and future developments in earthquake ground motion estimation.” Earth Sci. Rev. 160 (Sep): 203–219. https://doi.org/10.1016/j.earscirev.2016.07.005.
Du, W., and G. Wang. 2017. “Prediction equations for ground-motion significant durations using the NGA-West2 database.” Bull. Seismol. Soc. Am. 107 (1): 319–333. https://doi.org/10.1785/0120150352.
Estekanchi, H. E., K. Arjomandi, and A. Vafai. 2008. “Estimating structural damage of steel moment frames by endurance time method.” J. Constr. Steel Res. 64 (2): 145–155. https://doi.org/10.1016/j.jcsr.2007.05.010.
Feng, D.-C., W.-J. Wang, S. Mangalathu, and E. Taciroglu. 2021. “Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls.” J. Struct. Eng. 147 (11): 04021173. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003115.
Giouvanidis, A. I., and E. G. Dimitrakopoulos. 2018. “Rocking amplification and strong-motion duration.” Earthquake Eng. Struct. Dyn. 47 (10): 2094–2116. https://doi.org/10.1002/eqe.3058.
Guo, G., D. Yang, and Y. Liu. 2018. “Duration effect of near-fault pulse-like ground motions and identification of most suitable duration measure.” Bull. Earthquake Eng. 16 (Nov): 5095–5119. https://doi.org/10.1007/s10518-018-0386-9.
Hastie, T., R. Tibshirani, and J. Friedman. 2009. The elements of statistical learning: Data mining, inference, and prediction. 2nd ed. New York: Springer.
Hoshiba, M., O. Kamigaichi, M. Saito, S. Y. Tsukada, and N. Hamada. 2008. “Earthquake early warning starts nationwide in Japan.” EOS Trans. Am. Geophys. Union 89 (8): 73–74. https://doi.org/10.1029/2008EO080001.
Husid, R. 1969. “Características de terremotos Análisis general.” Rev. IDIEM 8 (1): 21–42.
Iervolino, I., G. Manfredi, and E. Cosenza. 2006. “Ground motion duration effects on nonlinear seismic response.” Earthquake Eng. Struct. Dyn. 35 (1): 21–38. https://doi.org/10.1002/eqe.529.
Janiesch, C., P. Zschech, and K. Heinrich. 2021. “Machine learning and deep learning.” Electron. Mark. 31 (3): 685–695. https://doi.org/10.1007/s12525-021-00475-2.
Jordan, M. I., and T. M. Mitchell. 2015. “Machine learning: Trends, perspectives, and prospects.” Science 349 (6245): 255–260. https://doi.org/10.1126/science.aaa8415.
Kawashima, K., and K. Aizawa. 1989. “Bracketed and normalized durations of earthquake ground acceleration.” Earthquake Eng. Struct. Dyn. 18 (7): 1041–1051. https://doi.org/10.1002/eqe.4290180709.
Kempton, J. J., and J. P. Stewart. 2006. “Prediction equations for significant duration of earthquake ground motions considering site and near-source effects.” Earthquake Spectra 22 (4): 985–1013. https://doi.org/10.1193/1.2358175.
Kiani, J., C. Camp, and S. Pezeshk. 2018. “Role of conditioning intensity measure in the influence of ground motion duration on the structural response.” Soil Dyn. Earthquake Eng. 104 (Jan): 408–417. https://doi.org/10.1016/j.soildyn.2017.11.021.
Kubo, H., T. Kunugi, W. Suzuki, S. Suzuki, and S. Aoi. 2020. “Hybrid predictor for ground-motion intensity with machine learning and conventional ground motion prediction equation.” Sci. Rep. 10 (1): 11871. https://doi.org/10.1038/s41598-020-68630-x.
Lundberg, S. M., and S.-I. Lee. 2017. “A unified approach to interpreting model predictions.” In Proc., 31st Int. Conf. on Neural Information Processing Systems, 4768–4777. Red Hook, NY: Curran Associates.
Mangalathu, S., H. Jang, S.-H. Hwang, and J.-S. Jeon. 2020. “Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls.” Eng. Struct. 208 (Apr): 110331. https://doi.org/10.1016/j.engstruct.2020.110331.
Mangalathu, S., K. Karthikeyan, D.-C. Feng, and J.-S. Jeon. 2022. “Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems.” Eng. Struct. 250 (Jan): 112883. https://doi.org/10.1016/j.engstruct.2021.112883.
Meimandi-Parizi, A., M. Daryoushi, A. Mahdavian, and H. Saffari. 2020. “Ground-motion models for the prediction of significant duration using strong-motion data from Iran.” Bull. Seismol. Soc. Am. 110 (1): 319–330. https://doi.org/10.1785/0120190109.
Morikawa, N., and H. Fujiwara. 2013. “A new ground motion prediction equation for Japan applicable up to M9 mega-earthquake.” J. Disaster Res. 8 (5): 878–888. https://doi.org/10.20965/jdr.2013.p0878.
Novikova, E. I., and M. D. Trifunac. 1994. “Duration of strong ground motion in terms of earthquake magnitude, epicentral distance, site conditions and site geometry.” Earthquake Eng. Struct. Dyn. 23 (9): 1023–1043. https://doi.org/10.1002/eqe.4290230907.
Ou, Y.-C., J. Song, P.-H. Wang, L. Adidharma, K. C. Chang, and G. C. Lee. 2014. “Ground motion duration effects on hysteretic behavior of reinforced concrete bridge columns.” J. Struct. Eng. 140 (3): 04013065. https://doi.org/10.1061/(ASCE)ST.1943-541X.0000856.
Pan, Y., C. E. Ventura, and W. Liam Finn. 2018. “Effects of ground motion duration on the seismic performance and collapse rate of light-frame wood houses.” J. Struct. Eng. 144 (8): 04018112. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002104.
Park, Y., and J. C. Ho. 2019. “Tackling overfitting in boosting for noisy healthcare data.” IEEE Trans. Knowl. Data Eng. 33 (7): 2995–3006. https://doi.org/10.1109/TKDE.2019.2959988.
Raghunandan, M., and A. B. Liel. 2013. “Effect of ground motion duration on earthquake-induced structural collapse.” Struct. Saf. 41 (Mar): 119–133. https://doi.org/10.1016/j.strusafe.2012.12.002.
Sarieddine, M., and L. Lin. 2013. “Investigation correlations between strong-motion duration and structural damage.” In Proc., Structures Congress 2013: Bridging Your Passion with Your Profession, 2926–2936. Reston, VA: Structural Engineering Institute of ASCE.
Stafford, P. J., R. Mendis, and J. J. Bommer. 2008. “Dependence of damping correction factors for response spectra on duration and numbers of cycles.” J. Struct. Eng. 134 (8): 1364–1373. https://doi.org/10.1061/(ASCE)0733-9445(2008)134:8(1364).
Trifunac, M. D., and A. G. Brady. 1975. “A study on the duration of strong earthquake ground motion.” Bull. Seismol. Soc. Am. 65 (3): 307–321. https://doi.org/10.1785/BSSA0650020307.
Trugman, D. T., and P. M. Shearer. 2018. “Strong correlation between stress drop and peak ground acceleration for recent M 1–4 earthquakes in the San Francisco Bay area.” Bull. Seismol. Soc. Am. 108 (2): 929–945. https://doi.org/10.1785/0120170245.
van de Lindt, J. W., and G. Goh. 2004. “Earthquake duration effect on structural reliability.” J. Struct. Eng. 130 (5): 821–826. https://doi.org/10.1061/(ASCE)0733-9445(2004)130:5(821).
Wang, C., H. Hao, S. Zhang, and G. Wang. 2020. “Influence of ground motion duration on responses of concrete gravity dams.” J. Earthquake Eng. 24 (7): 1156–1180. https://doi.org/10.1080/13632469.2018.1453422.
Won, J., and J. Shin. 2021. “Machine learning-based approach for seismic damage prediction method of building structures considering soil-structure interaction.” Sustainability 13 (8): 4334. https://doi.org/10.3390/su13084334.
Zengin, E., N. A. Abrahamson, and S. Kunnath. 2020. “Isolating the effect of ground-motion duration on structural damage and collapse of steel frame buildings.” Earthquake Spectra 36 (2): 718–740. https://doi.org/10.1177/8755293019891720.
Zhang, S., G. Wang, B. Pang, and C. Du. 2013. “The effects of strong motion duration on the dynamic response and accumulated damage of concrete gravity dams.” Soil Dyn. Earthquake Eng. 45 (Feb): 112–124. https://doi.org/10.1016/j.soildyn.2012.11.011.
Zhou, J., K. Tang, H. Wang, and X. Fang. 2014. “Influence of ground motion duration on damping reduction factor.” J. Earthquake Eng. 18 (5): 816–830. https://doi.org/10.1080/13632469.2014.908152.
Information & Authors
Information
Published In
Natural Hazards Review
Volume 25 • Issue 2 • May 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Jan 2, 2023
Accepted: Nov 16, 2023
Published online: Jan 27, 2024
Published in print: May 1, 2024
Discussion open until: Jun 27, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Continuum mechanics
- Databases
- Dynamics (solid mechanics)
- Earthquakes
- Engineering fundamentals
- Engineering mechanics
- Geohazards
- Geotechnical engineering
- Geotechnical investigation
- Ground motion
- Information Technology (IT)
- Mathematics
- Model accuracy
- Models (by type)
- Parameters (statistics)
- Solid mechanics
- Statistics
- Structural dynamics
- Structural models
- Structural response
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.