All Issue

2024 Vol.3, Issue 3

Research Article

Deep Learning for Shear Wave Velocity Prediction from MASW: A Proof of Concept

딥러닝을 활용한 MASW의 전단파 속도 예측: 개념 증명

Aram Seo1
,
SangUk Han2*
서 아람1
,
한 상욱2*
1Master Course Student, Department of Civil and Environmental Engineering, Hanyang University
2Corresponding Author, Member, Associate Professor, Department of Civil and Environmental Engineering, Hanyang University
1한양대학교 건설환경공학과 석사과정
2교신저자․정회원․한양대학교 건설환경공학과 부교수
*Corresponding Author
30 September 2024. pp. 1-5
PDF XML Citation
Abstract

The Multichannel Analysis of Surface Waves (MASW) method has recently garnered significant attention due to its capability to non-destructively evaluate subsurface ground characteristics. However, the conventional inversion methods for estimating shear wave velocity at different depths have issues due to the non-uniqueness, non-linearity, and ill-posed nature of dispersion curves, leading to reliance on the engineer’s subjective judgment and experience. To avoid such issues of inversion methods, this study proposes a deep learning-based approach to directly predict shear wave velocity from MASW data. A Temporal Convolutional Network (TCN), suitable for processing spatiotemporal data, was applied with MASW measurements as an input and shear wave velocity as an output. The experiment results, obtained with 2,778 samples augmented from 926 measurements, show that the proposed method achieved the prediction accuracy of 90.20% and 88.02% for the training and testing datasets, respectively. It can thus be expected that the accuracy of shear wave velocity predictions can be further improved through the advancement of deep learning models and the training of data under various ground conditions.

Keywords
Deep Learning
Temporal Convolutional Network
Multi-channel Analysis of Surface Waves
S-wave velocity

최근 지반의 특성을 비파괴적으로 평가하는 다중채널분석 표면파 탐사(MASW) 기법에 대한 연구가 활발히 이루어지고 있다. 하지만, 깊이별 전단파 속도(shear wave velocity)를 추정하기 위한 기존의 역산 방식은 분산곡선의 비고유성(non-unique), 비선형성(non-linear), 불확정성(ill-posed)으로 인해 분석자의 주관적 판단 및 경험에 의존하는 문제점이 있다. 본 연구는 기존의 역산 방식이 아닌, MASW 데이터를 기반으로 전단파 속도를 직접 예측할 수 있는 딥러닝 기반의 접근법을 제안하고, 그 활용 가능성을 평가하고자 한다. 시간 순서에 따른 데이터 처리에 적합한 Temporal Convolutional Network(TCN)를 적용하였으며, MASW 측정치를 입력으로 전단파 속도를 출력으로 모델을 학습시켰다. 926개의 측정 데이터를 2,778개로 증강시켜 학습시킨 결과, 학습 데이터 및 테스트 데이터에 대한 전단파 속도의 예측 정확도는 각각 90.20%와 88.02%를 달성하였다. 향후 딥러닝 모델의 고도화 및 다양한 지반 조건에 대한 데이터 학습을 통해 전단파 속도 예측의 정확도를 더욱 향상시킬 수 있으리라 기대된다.

키워드
딥러닝
TCN
다중채널 분석 표면파 탐사
전단파 속도 예측
References
1

Bai, S., Kolter, J. Z., and Koltun V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint, arXiv:1803.01271.

2

Chamorro, D., Zhao, J., Birnie, C., Staring, M., Moritz, F., and Ravasi M. (2024). Deep learning‐based extraction of surface wave disperfrom seismic shot gathers. Near Surface Geophysics. arXiv preprint, arXiv:2305.13990.

10.1002/nsg.12298
3

Cho, S., Choi, B., Lee, G., Jang, S., and Choi, Y. (2024). Prediction of S-wave velocity models from surface waves using deep learning. Near Surface Geophysics, 22(3), pp. 281-297.

10.1002/nsg.12284
4

Chou, J. S., and Truong, D. N. (2021). A novel metaheuristic optimizer inspired by behavior of jellyfish in ocean. Applied Mathematics and Computation, 389, 125535.

10.1016/j.amc.2020.125535
5

Cox, B. R., and Teague, D. P. (2016). Layering ratios: a systematic approach to the inversion of surface wave data in the absence of a priori information. Geophysical Journal International, 207(1), pp. 422-438.

10.1093/gji/ggw282
6

Cox, B., and Vantassel, J. (2018). Dynamic Characterization of WellingZDynamic Characterization of Wellington, New Zealand [Data set]. DesignSafe-CI. https://doi.org/10.17603/DS24M6J

10.17603/DS24M6J
7

Foti, S., Hollender, F., Garofalo, F., Albarello, D., Asten, M., Bard, P. Y., Comina, C., Cornou, C., and Cox, B., et al. (2018). Guidelines for the good practice of surface wave analysis: a product of the InterPACIFIC project. Bulletin of Earthquake Engineering, 16, pp. 2367-2420.

10.1007/s10518-017-0206-7
8

Kim, B., Cho, A., Cho, S. O., Nam, M. J., Pyun, S., and Hayashi, K. (2019). Surface wave method: focused on active method. Geophysics and Geophysical Exploration, 22(4), pp. 210-224.

9

Nolet, G., and Panza, G. F. (1976). Array analysis of seismic surface waves: Limits and possibilities. Pure and Applied Geophysics, 114(5), pp. 775-790.

10.1007/BF00875787
10

Park, C., B., Miller, R. D., and Xia, J. (1999). Multichannel analysis of surface waves. Geophysics, 64(3), pp. 800-808.

10.1190/1.1444590
11

Poormirzaee, R., and Kabgani, A. (2022). Characterizing the Vs profile from surface wave data using a customized artificial jellyfish search algorithm. Pure and Applied Geophysics, 179(12), pp. 4429-4444.

10.1007/s00024-022-03173-y
12

Rayleigh, L. (1885). On waves propagated along the plane surface of an elastic solid. Proceedings of the London mathematical Society, s1-17(1) pp. 4-11.

10.1112/plms/s1-17.1.4
13

Wathelet, M., Jongmans, D., and Ohrnberger, M. (2004). Surface-wave inversion using a direct search algorithm and its application to ambient vibration measurements. Near Surface Geophysics, 2(4), pp. 211-221.

10.3997/1873-0604.2004018
14

Zywicki, D. J. (1999). Advanced signal processing methods applied to engineering analysis of seismic surface waves. Ph.D. Dissertation, School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, Georgia.

Information
  • Publisher :Korean Society of Automation and Robotics in Construction
  • Publisher(Ko) :(사)한국건설자동화·로보틱스학회
  • Journal Title :Journal of Construction Automation and Robotics
  • Journal Title(Ko) :건설자동화·로보틱스 논문집
  • Volume : 3
  • No :3
  • Pages :1-5
  • Received Date : 2024-06-17
  • Accepted Date : 2024-08-01
  • DOI :https://doi.org/10.55785/JCAR.3.3.1
Journal Informaiton Journal of Construction Automation and Robotics Journal of Construction Automation and Robotics
Online Submission
  • crossref crossmark
  • crossref cited-by
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close