[논문]탄성파 자료 잡음 제거를 위한 비지도 학습 연구

김수정; 전형구

doi:10.7582/gge.2022.25.2.071

[국내논문] 탄성파 자료 잡음 제거를 위한 비지도 학습 연구
The Use of Unsupervised Machine Learning for the Attenuation of Seismic Noise 원문보기

지구물리와 물리탐사 = Geophysics and geophysical exploration, v.25 no.2, 2022년, pp.71 - 84

김수정 (경북대학교 지질학과) , 전형구 (경북대학교 지질학과)

초록
AI-Helper

탄성파 자료 취득 시 신호와 함께 기록되는 다양한 형태의 잡음은 탄성파 자료의 정확한 해석을 방해하는 요인으로 작용한다. 따라서 탄성파 자료의 잡음 제거는 탄성파 자료 처리 과정 중 필수적인 절차이므로 기계 학습을 포함한 다양한 방식의 잡음 제거 연구가 수행되고 있다. 본 연구에서는 비지도 학습 기반의 탄성파 잡음 제거 모델을 이용하여 중합 전 탄성파 자료의 잡음 제거를 수행하고자 하였으며 총 세 가지의 비지도 학습 기반 기계 학습 모델을 비교하였다. 세 가지의 비지도 학습 모델은 N2NUNET, PATCHUNET, DDUL로 각각 서로 다른 신경망 구조를 통해 정답 자료 없이 탄성파 잡음을 제거한다. 세 가지 모델들을 인공 합성 및 현장 중합 전 탄성파 자료에 적용하여 잡음을 제거한 후 그 결과를 정성적·정량적으로 분석하였으며, 분석 결과 세 가지 비지도 학습 모델 모두 인공 합성 및 현장 자료의 탄성파 잡음을 적절히 제거하였음을 확인하였다. 그 중 N2NUNET 모델이 가장 낮은 잡음 제거 성능을 보여주었으며, PATCHUNET과 DDUL은 거의 유사한 결과를 도출하였지만, DDUL이 정량적으로 근소한 우위를 보였다.

Abstract ▼ AI-Helper

When acquiring seismic data, various types of simultaneously recorded seismic noise hinder accurate interpretation. Therefore, it is essential to attenuate this noise during the processing of seismic data and research on seismic noise attenuation. For this purpose, machine learning is extensively used. This study attempts to attenuate noise in prestack seismic data using unsupervised machine learning. Three unsupervised machine learning models, N2NUNET, PATCHUNET, and DDUL, are trained and applied to synthetic and field prestack seismic data to attenuate the noise and leave clean seismic data. The results are qualitatively and quantitatively analyzed and demonstrated that all three unsupervised learning models succeeded in removing seismic noise from both synthetic and field data. Of the three, the N2NUNET model performed the worst, and the PATCHUNET and DDUL models produced almost identical results, although the DDUL model performed slightly better.

주제어

표/그림 (13)

그림 Fig. 1. The training data sampling strategy for the N2NUNET model (Liu et al., 2021).
그림 Fig. 2. The architecture of the N2NUNET model.
그림 Fig. 3. A schematic of the (a) patching and (b) unpatching methods (Saad and Chen, 2021).
그림 Fig. 4. The architecture of the PATCHUNET model (Saad and Chen, 2021).
그림 Fig. 5. The architecture of the DDUL model (Yang et al., 2021).
그림 Fig. 6. The synthetic seismic data (a) before and (b) after adding noise.
그림 Fig. 7. The training data for the (a) N2NUNET and (b) PATCHUNET and DDUL models. After this training, the models were tested using synthetic data.
그림 Fig. 8. A comparison of the denoised results and the local similarities for synthetic seismic data. ( a) T he c lean data. The denoised results generated using the machine learning models (b) N2NUNET, (c) PATCHUNET, and (d) DDUL. (e) The noisy data. The noise removed by the models (f) N2NUNET, (g) PATCHUNET, and (h) DDUL. The local similarity maps of (i) the clean data and the denoised data generated by (j) N2NUNET, (k) PATCHUNET, and (l) DDUL.
그림 Fig. 9. The field seismic data.
그림 Fig. 10. The training data for the (a) N2NUNET and (b) PATCHUNET and DDUL models. After this training, the models were tested using field data.
그림 Fig. 11. A comparison of the denoised results and the local similarities for the field seismic data. The denoised results generated using the machine learning models (a) DnCNN (Jun et al., 2021), (b) N2NUNET, (c) PATCHUNET, and (d) DDUL. The noise removed by the models (e) DnCNN, (f) N2NUNET, (g) PATCHUNET, and (h) DDUL. The local similarity maps of the denoised data generated by (i) DnCNN, (j) N2NUNET, (k) PATCHUNET, and (l) DDUL.
표 Table 1. Average PSNR (dB)/SSIM results for the synthetic data using the unsupervised machine learning models (N2NUNET, PATCHUNET, and DDUL) and noisy input data. The best results are highlighted.
표 Table 2. Pearson correlation coefficients for the field seismic data analyzed using the unsupervised machine learning models (N2NUNET, PATCHUNET, and DDUL) and the supervised machine learning model (DnCNN). The best result is highlighted.

참고문헌 (33)

Benesty, J., Chen, J., Huang, Y., and Cohen, I., 2009, Pearson correlation coefficient, In Noise reduction in speech processing, Springer, Berlin, Heidelberg. 1-4. doi: 10.1007/978-3-642-00296-0_5.
Canales, L. L., 1984, Random noise reduction, In SEG Technical Program Expanded Abstracts 1984, Society of Exploration Geophysicists, 525-527. doi: 10.1190/1.1894168.
Chen, Y., and Fomel, S., 2014, Random noise attenuation using local similarity, In SEG Technical Program Expanded Abstracts 2014, Society of Exploration Geophysicists, 4360-4365. doi: 10.1190/segam2014-0594.1.
Chen, Y., Zhang, M., Bai, M., and Chen, W., 2019, Improving the signal-to-noise ratio of seismological datasets by unsupervised machine learning, Seismological Research Letters, 90(4), 1552-1564. doi: 10.1785/0220190028.
Di, H., Li, C., Smith, S., and Abubakar, A., 2019, Machine learning-assisted seismic interpretation with geologic constraints, In SEG International Exposition and Annual Meeting, Society of Exploration Geophysicists, 5360-5364. doi: 10.1190/segam2019-w4-01.1.
Dondurur, D., 2018, Acquisition and processing of marine seismic data, Elsevier, 174-212. https://www.elsevier.com/books/acquisition-and-processing-of-marine-seismic-data/dondurur/978-0-12-811490-2
Fabien-Ouellet, G., and Sarkar, R., 2020, Seismic velocity estimation: A deep recurrent neural-network approach, Geophysics, 85(1), U21-U29. doi: 10.1190/geo2018-0786.1.

상세보기
Fomel, S, 2007, Local seismic attributes, Geophysics, 72(3), A29-A33. doi: 10.1190/1.2437573.

상세보기
Graves, R. W., 1996, Simulating seismic wave propagation in 3D elastic media using staggered-grid finite differences, Bulletin of the seismological society of America, 1091-1106. http://web.gps.caltech.edu/~clay/Ge263/Graves1996.pdf.
Hore, A. and Ziou, D., 2010, Image quality metrics: PSNR vs. SSIM, Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, Turkey, 2366-2369. doi: 10.1109/ICPR.2010.579.
Jia, Y., and Ma, J., 2017, What can machine learning do for seismic data processing? An interpolation application, Geophysics, 82(3), V163-V177. doi: 10.1190/geo2016-0300.1.

상세보기
Jun, H., Jou, H. T., Kim, C. H., Lee, S. H., and Kim, H. J., 2020, Random noise attenuation of sparker seismic oceanography data with machine learning, Ocean Science, 16(6), 1367-1383. https://os.copernicus.org/articles/16/1367/2020/os-16-1367-2020.pdf.

상세보기
Jun, H., Kim, C., Kim, H.-J., 2021, Machine-learning based noise attenuation of field seismic data using noise data acquisition, Journal of the Korean Society of Mineral and Energy Resources Engineers, 58(5), 408-417. (in Korean with English abstract) https://www.jksmer.or.kr/articles/article/Pwv9/.
Jun, H., and Cho, Y., 2022, Repeatability enhancement of time-lapse seismic data via a convolutional autoencoder, Geophysical Journal International, 228(2), 1150-1170. doi: 10.1093/gji/ggab397.

상세보기
Kumar, P. C., and Sain, K., 2018, Attribute amalgamation-aiding interpretation of faults from seismic data: An example from Waitara 3D prospect in Taranaki basin off New Zealand, Journal of Applied Geophysics, 159, 52-68. doi: 10.1016/j.jappgeo.2018.07.023.

상세보기
Lehtinen, J., Munkberg, J., Hasselgren, J., Laine, S., Karras, T., Aittala, M., and Aila, T., 2018, Noise2noise: Learning image restoration without clean data, arXiv. doi: 10.48550/arXiv.1803.04189.
Li, D., Peng, S., Lu, Y., Guo, Y., and Cui, X., 2019, Seismic structure interpretation based on machine learning: A case study in coal mining, Interpretation, 7(3), SE69-SE79. doi: 10.1190/INT-2018-0208.1.

상세보기
Li, H., Yang, W., and Yong, X., 2018, Deep learning for ground-roll noise attenuation, In SEG Technical Program Expanded Abstracts 2018, Society of Exploration Geophysicists, 1981-1985. doi: 10.1190/segam2018-2981295.1.
Liu, B., Yue, J., Zuo, Z., Xu, X., Fu, C., Yang, S., and Jiang, P., 2021, Unsupervised deep learning for random noise attenuation of seismic data, IEEE Geoscience and Remote Sensing Letters, 19, 1-5. doi: 10.1109/LGRS.2021.3057631.

상세보기
Martin G. S., Wiley R., and Marfurt K. J., 2006, Marmousi2: An elastic upgrade for Marmousi, The Leading Edge, 25, 156-166. doi: 10.1190/1.2172306.

상세보기
Quan, Y., Chen, M., Pang, T., and Ji, H., 2020, Self2self with dropout: Learning self-supervised denoising from single image, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10, 1890-1898. doi: 10.1109/CVPR42600.2020.00196.
Ronneberger, O., Fischer, P., and Brox, T., 2015, October, U-net: Convolutional networks for biomedical image segmentation, In International Conference on Medical image computing and computer-assisted intervention, Springer, Cham, 234-241. https://link.springer.com/chapter/10.1007/978-3-319-24574-4_28.
Saad, O. M., and Chen, Y., 2020, Deep denoising autoencoder for seismic random noise attenuation, Geophysics, 85(4), V367-V376. doi: 10.1190/geo2019-0468.1.

상세보기
Saad, O. M., and Chen, Y., 2021, A fully unsupervised and highly generalized deep learning approach for random noise suppression, Geophysical Prospecting, 69(4), 709-726. doi: 10.1111/1365-2478.13062.

상세보기
Schober, P., Boer, C., and Schwarte, L. A., 2018, Correlation coefficients: appropriate use and interpretation, Anesthesia & Analgesia, 126(5), 1763-1768. doi: 10.1213/ANE.0000000000002864.

상세보기
Schuba, C. N., Schuba, J. P., Gray, G. G., and Davy, R. G., 2019, Interface-targeted seismic velocity estimation using machine learning, Geophysical Journal International, 218(1), 45-56. doi: 10.1093/gji/ggz142.

상세보기
Si, X., and Yuan, Y., 2018, Random noise attenuation based on residual learning of deep convolutional neural network, In SEG technical program expanded abstracts 2018, Society of Exploration Geophysicists, 1986-1990. doi: 10.1190/segam2018-2985176.1.
Si, X., 2020, Ground roll attenuation with conditional generative adversarial networks, In SEG International Exposition and Annual Meeting, Society of Exploration Geophysicists, Society of Exploration Geophysicists. doi: 10.1190/segam2020-3424945.1.
Wang, H., Zhang, Q., Zhang, G., Fang, J., and Chen, Y., 2020, Self-training and learning the waveform features of microseismic data using an adaptive dictionary, Geophysics, 85(3), KS51-KS61. doi: 10.1190/geo2019-0213.1.

상세보기
Yang, L., Wang, S., Chen, X., Saad, O. M., Chen, W., Oboue, Y. A. S. I., and Chen, Y., 2021, Unsupervised 3-D random noise attenuation using deep skip autoencoder, IEEE Transactions on Geoscience and Remote Sensing, 60, 1-16. doi: 10.1109/tgrs.2021.3100455.

상세보기
Zhang, C., Frogner, C., Araya-Polo, M., and Hohl, D., 2014, Machine-learning based automated fault detection in seismic traces, In 76th EAGE Conference and Exhibition 2014, European Association of Geoscientists & Engineers, 1-5. doi: 10.3997/2214-4609.20141500.
Zhang, K., Zuo, W., Chen, Y., Meng, D., and Zhang, L., 2017, Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising, IEEE Transactions on Image Processing, 26(7), 3142-3155. doi: 10.1109/TIP.2017.2662206.

상세보기
Zhou, C., and Brown, S., 2020, Automatic velocity model building with machine learning, In SEG Technical Program Expanded Abstracts 2020, Society of Exploration Geophysicists, 1596-1600. doi: 10.1190/segam2020-3427836.1.

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증