A deep learning approach to rapid regional post‐event seismic damage assessment using time‐frequency distributions of ground motions

Xinzheng Lu; Yongjia Xu; Yuan Tian; Barbaros Cetiner; Ertugrul Taciroglu

doi:10.1002/eqe.3415

journal article Jan 05, 2021

A deep learning approach to rapid regional post‐event seismic damage assessment using time‐frequency distributions of ground motions

Xinzheng Lu

Yongjia Xu

Yuan Tian

Barbaros Cetiner Ertugrul Taciroglu

Earthquake Engineering & Structural Dynamics Vol. 50 No. 6 pp. 1612-1627 · Wiley

View at Publisher Save 10.1002/eqe.3415

Abstract

AbstractEvery year, earthquakes result in severe economic losses and a significant number of casualties worldwide. In limiting the losses that occur after these extreme events, timely and accurate assessment of seismic damages and mobilizing proportionate post‐event relief efforts play crucial roles. Traditional on‐site investigation generally results in prolonged evaluation windows. Several computational alternatives exist that show promise in addressing the downsides of the traditional approach. Damage estimates based on pre‐computed fragility libraries can provide near‐real time seismic damage quantification, but at present, they are coarse and involve considerable uncertainties. Estimates based on nonlinear time‐history analyses simulate the seismic response in greater detail, yet due to the computation and data requirements, their use at the regional scale is challenging. Given this perspective, herein, a rapid regional post‐event seismic damage assessment procedure based on convolutional neural network (CNN) is proposed. In this approach, an inventory of buildings, anticipated ground motion datasets, and corresponding damage levels for a region are brought together into a scenario bank. The time‐frequency distribution graphs of the ground motions, which serve as detailed visual representations of their frequency‐domain as well as time‐domain features, are generated. These data are then used to train CNN models, which could predict the damage states. The proposed methodology is verified through two numerical studies—one for an individual building, and the other, regional case, involving the buildings in the Tsinghua University campus. The results confirm that the proposed method offers prediction results with sufficient accuracy in near real‐time.

Topics

No keywords indexed for this article. Browse by subject →

References

77

[1]

China News Service.The number of deaths in Mianyang city due to the earthquake was nearly 16 000.2020.http://www.chinanews.com/gn/news/2008/05-21/1256776.shtml. Accessed April 1 2020.

[2]

10.1193/041417eqs072m

[3]

Wald DJ "PAGER ‐ rapid assessment of an earthquake's impact" Fact Sheet (2010)

[4]

European Commission.Global disaster alert and coordination system (GDACS).2020.http://www.gdacs.org/. Accessed December 22 2020.

[5]

DemirciogluMB ErdikM HancilarU et al.ELER v3.0: Technical Manual and Users Guide.2020.https://eqe.boun.edu.tr/en/eler-tool. Accessed August 1 2020.

[6]

10.1007/978-981-10-3087-1

[7]

10.3390/app9173497

[8]

10.1002/eqe.646

[9]

10.1002/eqe.645

[10]

10.1193/072215eqs118m

[11]

10.1016/j.soildyn.2016.09.041

[12]

10.1142/p644

[13]

Multi-LOD seismic-damage simulation of urban buildings and case study in Beijing CBD

Chen Xiong, Xinzheng Lu, Jin Huang et al.

Bulletin of Earthquake Engineering 10.1007/s10518-018-00522-y

[14]

10.1002/eqe.386

[15]

10.1080/13632460701673076

[16]

BurattiN.A comparison of the performances of various ground–motion intensity measures. Paper presented at:Proceedings of the 15th World Conference on Earthquake Engineering; September 24‐28 2012;Lisbon Portugal.

[17]

10.1007/s10518-012-9402-7

[18]

10.1007/s11803-010-0002-8

[19]

Boashash B (2015)

[20]

The wavelet transform, time-frequency localization and signal analysis

I. Daubechies

IEEE Transactions on Information Theory 10.1109/18.57199

[21]

10.1109/tim.2013.2279001

[22]

2006 California Institute of Technology California SC Bradford Time‐Frequency Analysis of Systems with Changing Dynamic Properties

[23]

Response-only modal identification of structures using limited sensors

F. Abazarsa, S. F. Ghahari, F. Nateghi et al.

Structural Control and Health Monitoring 10.1002/stc.1513

[24]

10.1061/(asce)em.1943-7889.0000990

[25]

10.1002/eqe.2268

[26]

ImageNet classification with deep convolutional neural networks

Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton

Communications of the ACM 10.1145/3065386

[27]

Emerging artificial intelligence methods in structural engineering

Hadi Salehi, Rigoberto Burgueño

Engineering Structures 10.1016/j.engstruct.2018.05.084

[28]

10.3390/rs8100868

[29]

10.3390/rs10101636

[30]

10.1016/j.isprsjprs.2017.03.001

[31]

10.1002/eqe.3258

[32]

10.1111/mice.12517

[33]

10.1177/1475921720931745

[34]

10.1016/j.engstruct.2020.110704

[35]

Lu XZ "An improved linear quadratic regulator control method through convolutional neural network–based vibration identification" J Vib Control (2020)

[36]

Xu YJ "Real‐time regional seismic damage assessment framework based on long short‐term memory neural network" Comput‐Aided Civil Infrastruct Eng (2020)

[37]

Real-Time Seismic Damage Prediction and Comparison of Various Ground Motion Intensity Measures Based on Machine Learning

Yongjia Xu, Xinzheng Lu, Yuan Tian et al.

Journal of Earthquake Engineering 10.1080/13632469.2020.1826371

[38]

Jalayer F (2003)

[39]

10.1007/s00024-010-0161-6

[40]

TamhidiA KuehnN BozorgniaY TacirogluE KishidaT.Prediction of ground‐motion time‐series at an arbitrary location using gaussian process interpolation: application to the Ridgecrest earthquake. Paper presented at:Poster #247 of the SCEC Annual Meeting; Accessed September 8 2019;California USA.

[41]

NIED.Seismograph station information of the NIED Hi‐net and F‐net.2019.http://www.hinet.bosai.go.jp/st_info/detail/dataset.php?LANG=en. Accessed December 1 2019.

[42]

PEER.PEER NGA Database (NGA‐West NGA‐West2 NGA‐East). 2020.https://peer.berkeley.edu/research/data-sciences. Accessed January 1 2020.

[43]

NIED.The NIED Strong‐Motion Seismograph Networks. 2020.http://www.kyoshin.bosai.go.jp. Accessed March 1 2020.

[44]

10.1080/13632469.2016.1160009

[45]

10.1007/s10518-017-0168-9

[46]

An open‐source framework for regional earthquake loss estimation using the city‐scale nonlinear time history analysis

Xinzheng Lu, Frank McKenna, Qingsu Cheng et al.

Earthquake Spectra 10.1177/8755293019891724

[47]

China Earthquake Administration (CEA) (2009)

[48]

Federal Emergency Management Agency (FEMA) (2012)

[49]

Ministry of Housing and Urban‐Rural Development of the People's Republic of China (MOHURD) 2010 Architecture & Building Press Beijing China

[50]

Yang C "Status quo of China earthquake networks and analyses on its early warning capacity" Acta Seismologica Sinica (2015)

Showing 50 of 77 references

Cited By

143

Constitutive model-constrained physics-informed neural networks framework for nonlinear structural seismic response prediction

Yongxin Wu, Zhanpeng Yin · 2025

Computer Methods in Applied Mechani...

Machine learning in earthquake engineering: A review on recent progress and future trends in seismic performance evaluation and design

Shuling Hu, Tong Guo · 2025

Engineering Structures

Pre-earthquake fuzzy logic-based rapid hazard assessment of reinforced concrete buildings

Atakan Mangir, Vefa Okumus · 2023

Case Studies in Construction Materi...

Convolutional neural networks (CNNs)-based multi-category damage detection and recognition of high-speed rail (HSR) reinforced concrete (RC) bridges using test images

Longqian Chen, Wenxin Chen · 2023

Engineering Structures

Probabilistic Machine-Learning Methods for Performance Prediction of Structure and Infrastructures through Natural Gradient Boosting

Shi-Zhi Chen, De-Cheng Feng · 2022

Journal of Structural Engineering

Metrics

143

Citations

77

References

Details

Published: Jan 05, 2021
Vol/Issue: 50(6)
Pages: 1612-1627
License: View

Authors

X

Xinzheng Lu

Key Laboratory of Civil Engineering Safety and Durability of Ministry of Education, Department of Civil Engineering Tsinghua University Beijing P.R. China

Y

Yongjia Xu

Key Laboratory of Civil Engineering Safety and Durability of Ministry of Education, Department of Civil Engineering Tsinghua University Beijing P.R. China

Y

Yuan Tian

Key Laboratory of Civil Engineering Safety and Durability of Ministry of Education, Department of Civil Engineering Tsinghua University Beijing P.R. China

B

Barbaros Cetiner

Department of Civil and Environmental Engineering University of California Los Angeles California USA

E

Ertugrul Taciroglu

Department of Civil and Environmental Engineering University of California Los Angeles California USA

Cite This Article

Xinzheng Lu, Yongjia Xu, Yuan Tian, et al. (2021). A deep learning approach to rapid regional post‐event seismic damage assessment using time‐frequency distributions of ground motions. Earthquake Engineering & Structural Dynamics, 50(6), 1612-1627. https://doi.org/10.1002/eqe.3415

A deep learning approach to rapid regional post‐event seismic damage assessment using time‐frequency distributions of ground motions

You May Also Like