지구물리와물리탐사 (Geophysics and Geophysical Exploration)

  • 제25권4호
  • /
  • Pages.177-188
  • /
  • 2022
  • /
  • 1229-1064(pISSN)
  • /
  • 2384-051X(eISSN)
한국지구물리·물리탐사학회 (Korean Society of Earth and Exploration Geophysicists)
권호 표지
DOI QR코드

DOI QR Code

분포형 광섬유 센서 자료 적용을 위한 기계학습 기반 P, S파 위상 발췌 알고리즘 개발

Machine Learning-based Phase Picking Algorithm of P and S Waves for Distributed Acoustic Sensing Data

  • 최용규 (한양대학교 자원환경공학과) ;
  • 송영석 (한양대학교 자원환경공학과) ;
  • 설순지 (한양대학교 자원환경공학과) ;
  • 변중무 (한양대학교 자원환경공학과)
  • Yonggyu, Choi (Department of Earth Resources and Environmental Engineering, Hanyang University) ;
  • Youngseok, Song (Department of Earth Resources and Environmental Engineering, Hanyang University) ;
  • Soon Jee, Seol (Department of Earth Resources and Environmental Engineering, Hanyang University) ;
  • Joongmoo, Byun (Department of Earth Resources and Environmental Engineering, Hanyang University)
  • 투고 : 2022.09.22
  • 심사 : 2022.10.13
  • 발행 : 2022.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 이산화탄소 지중저장 모니터링 기술 중 하나인 미소진동 모니터링 기술에 대한 관심이 증가하면서 과거에 주로 사용되었던 지오폰이나 지진계가 아닌 분포형 광섬유 센서(distributed acoustic sensing, DAS)의 적용도 증가하고 있다. 특히 DAS를 이용하여 모니터링을 수행하면 시×공간적으로 거의 연속된 자료가 기록되게 되어 자료의 양이 방대해지게 되고 빠르고 정확한 자료 처리가 중요하게 된다. 자료처리 중 이벤트 탐지 및 위상 발췌는 가장 기초적인 과정으로 모든 자료에 대해 필수적으로 수행되어야 한다. 이 논문에서는 기계학습 기반의 P, S파 위상 발췌 알고리즘을 개발하여 전통적인 위상 발췌 방법의 한계를 보완하고, 전이학습 방법을 이용하여 신호 대 잡음비가 낮은 단일 성분 자료만 존재하는 DAS 자료에도 적용이 가능하도록 하였다. 사용된 기계학습 모델은 위상 발췌에 뛰어난 성능을 보이는 합성곱 신경망 기반의 EQTransformer를 ResUNet의 특성을 포함하도록 수정하여 구성하였다. 훈련자료는 전세계적으로 기록된 지진파형 자료인 STEAD자료를 이용하였고 학습 자료에 포함되지 않은 특성들에 대해서도 좋은 성능을 보이도록 기본 자료를 다양하게 변형시킨 자료도 학습에 사용하였다. 개발된 알고리즘은 학습자료와 다른 특성을 갖는 K-net 및 KiK-net 자료에 의해 성능이 검증되었다. 또한, 전이 학습을 통해 DAS 자료의 특성에 맞게 변형시킨 후 포항 장기분지에서 측정된 DAS자료에 적용시켜 그 성능을 검증하였다.

Recently, the application of distributed acoustic sensors (DAS), which can replace geophones and seismometers, has significantly increased along with interest in micro-seismic monitoring technique, which is one of the CO2 storage monitoring techniques. A significant amount of temporally and spatially continuous data is recorded in a DAS monitoring system, thereby necessitating fast and accurate data processing techniques. Because event detection and seismic phase picking are the most basic data processing techniques, they should be performed on all data. In this study, a machine learning-based P, S wave phase picking algorithm was developed to compensate for the limitations of conventional phase picking algorithms, and it was modified using a transfer learning technique for the application of DAS data consisting of a single component with a low signal-to-noise ratio. Our model was constructed by modifying the convolution-based EQTransformer, which performs well in phase picking, to the ResUNet structure. Not only the global earthquake dataset, STEAD but also the augmented dataset was used as training datasets to enhance the prediction performance on the unseen characteristics of the target dataset. The performance of the developed algorithm was verified using K-net and KiK-net data with characteristics different from the training data. Additionally, after modifying the trained model to suit DAS data using the transfer learning technique, the performance was verified by applying it to the DAS field data measured in the Pohang Janggi basin.

키워드

과제정보

이 논문은 2021년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원과(No. 2021R1A2C2014315) 2022년도 정부(교육부, 산업통상자원부)의 재원으로 K-CCUS 추진단의 지원을 받아 수행된 연구입니다(KCCUS20220001, 온실가스 감축 혁신인재양성사업). 또한, 본 연구를 위해 귀중한 현장 자료를 제공해주신 한국지질자원연구원과 광섬유 탄성파 연구팀에 감사를 드립니다.

참고문헌

  1. Allen, R., 1978, Automatic earthquake recognition and timing from single traces: Bull. Seismol. Soc. Amer., 68(5), 1521-1532. https://doi.org/10.1785/BSSA0680051521
  2. Daley, T. M., Miller, D. E., Dodds, K., Cook, P., and Freifeld, B. M., 2016, Field testing of modular borehole monitoring with simultaneous distributed acoustic sensing and geophone vertical seismic profiles at Citronelle, Alabama, Geophys. Prospect., 64(5), 1318-1334. https://doi.org/10.1111/1365-2478.12324
  3. Diakogiannis, F. I., Waldner, F., Caccetta, P., and Wu, C., 2020, ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data, ISPRS J. Photogramm. Remote Sens., 162, 94-114. https://doi.org/10.1016/j.isprsjprs.2020.01.013
  4. Gwon, L., 2016, Review of CO2 Storage Projects and Driving Strategy of CO2 Storage Program in Korea, KEPCO J. Electr. Power Energy, 2(2), 167-165. https://doi.org/10.18770/KEPCO.2016.02.02.167
  5. Huh, D., and Park, Y., 2009, Status of Otway CO2 Storage Project in Australia, J. Geol. Soc. Korea, 45(5), 517-525. https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART001389834
  6. KIGAM, 2015, Development of In-situ Monitoring Technology for Detecting Underground Behavior and Leakage of Injected CO2. https://scienceon.kisti.re.kr/commons/util/originalView.do?dbt=TRKO&cn=TRKO201700000433
  7. Lomax A., Satriano, C., and Vassallo, M., 2012, Automatic Picker Developments and Optimization: FilterPicker-a Robust, Broadband Picker for Real-Time Seismic Monitoring and Earthquake Early Warning, Seismol. Res. Lett., 83(3), 531-540. https://doi.org/10.1785/gssrl.83.3.531
  8. Mousavi, S. M., Ellsworth, W. L., Zhu, W., Chuang, L. Y., and Beroza, G. C., 2020, Earthquake transformer-an attentive deep-learning model for simultaneous earthquake detection and phase picking, Nat. Commun., 11, 3592 (2020). https://doi.org/10.1038%2Fs41467-020-17591-w https://doi.org/10.1038%2Fs41467-020-17591-w
  9. Mousavi, S. M., Sheng, Y., Zhu, W., and Beroza, G. C., 2019, Stanford Earthquake Dataset (STEAD): A Global Data Set of Seismic Signals for AI, IEEE Access, 7, 179464-179476. https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8871127 https://doi.org/10.1109/access.2019.2947848
  10. National Research Institute for Earth Science and Disaster Resilience, 2019, NIED K-NET, KiK-net, National Research Institute for Earth Science and Disaster Resilience, doi:10.17598/NIED.0004.
  11. Pan, S. J., and Yang, Q., 2010, A Survey on Transfer Learning, IEEE Trans. Knowl. Data Eng., 22(10), 1345-1359. https://doi.org/10.1109/TKDE.2009.191
  12. Peng, Z., and Zhao, P., 2009, Migration of early aftershocks following the 2004 Parkfield earthquake, Nat. Geosci., 2, 877-881. https://www.nature.com/articles/ngeo697 https://doi.org/10.1038/ngeo697
  13. Ronneberger, O., Fischer, P., and Brox, T., 2015, U-Net: Convolutional Networks for Biomedical Image Segmentation, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, 234-241. https://link.springer.com/chapter/10.1007/978-3-319-24574-4_28
  14. Ross, Z. E., Meier, M., Hauksson, E., and Heaton, T. H., 2018, Generalized Seismic Phase Detection with Deep Learning, Bull. Seismol. Soc. Amer., 108(5A), 2894-2901. https://doi.org/10.1785/0120180080
  15. Saragiotis, C. D., Hadjileontiadis, L. J., and Panas, S. M., 2002, PAI-S/K: A robust automatic seismic P phase arrival identification scheme, IEEE Trans Geosci Remote Sens, 40(6), 1395-1404. https://doi.org/10.1109/TGRS.2002.800438
  16. Shelly, D. R., Beroza, G. C., and Ide, S., 2007, Non-volcanic tremor and low-frequency earthquake swarms, Nature, 446, 305-307. https://www.nature.com/articles/nature05666 https://doi.org/10.1038/nature05666
  17. Silixa, 2022, https://silixa.com/technology/idas-intelligentdistributed-acoustic-sensor/, (October 12, 2022 Accessed)
  18. Sleeman, R., and Van Eck, T., 1999, Robust automatic P-phase picking: an on-line implementation in the analysis of broadband seismogram recordings, Phy. Earth and Planet. Inter., 113(1-4), 265-275. https://doi.org/10.1016/S0031-9201(99)00007-2
  19. Zhu, W., and Beroza, G. C., 2019, PhaseNet: a deep-neuralnetwork-based seismic arrival-time picking method, Geophys. J. Int., 216(1), 261-273. https://doi.org/10.1093/gji/ggy423