[논문]3D fault detection: Using human reasoning to improve performance of convolutional neural networks

Zhu, Donglin; Li, Lei; Guo, Rui; Tao, Chunfeng; Zhan, Shifan

doi:10.1190/geo2020-0905.1

3D fault detection: Using human reasoning to improve performance of convolutional neural networks

Geophysics, v.87 no.4, 2022년, pp.IM143 - IM156

Zhu, Donglin (CNPC, BGP Inc., BGP Research and Development Center, Zhuozhou, China. (corresponding author)) , Li, Lei (CNPC, BGP Inc., BGP Research and Development Center, Zhuozhou, China.) , Guo, Rui (CNPC, BGP Inc., BGP Research and Development Center, Zhuozhou, China.) , Tao, Chunfeng (CNPC, BGP Inc., BGP Research and Development Center, Zhuozhou, China.) , Zhan, Shifan (CNPC, BGP Inc., Zhuozhou, China.)

Abstract ▼ AI-Helper

Depicting faults in seismic data is one of the key steps in seismic structure interpretation. However, the manual identification of faults is a time-consuming and tedious process. In conventional methods, seismic attributes associated with the reflection continuities or discontinuities of seismic data are extracted for fault detection. In recent years, convolutional neural networks (CNNs) have been introduced to solve geophysical problems. Herein, we have proposed powerful and efficient methods to enhance the performance of CNN-based fault detection. We first introduce human reasoning to improve the performance of a 3D neural network, which is trained with synthetic seismic data. We propose two methods that efficiently use human reasoning. Manually identified faults can be easily added to train an efficient spatial pyramid network (ESPNet) and contextual information can be obtained to improve the continuity of the faults. We propose an unsupervised fault registration framework to fuse the results from commonly used 3D CNNs and ESPNet, which simultaneously preserves high data accuracy and continuity. Furthermore, to use sparse manually identified faults to directly train a 3D CNN, we propose a weakly supervised learning method. Multiple examples find that faults can be more accurately predicted with the proposed methods than with previously established algorithms, including conventional seismic attributes and CNN-based methods.

참고문헌 (40)

10.2118/168061-MS
Al-Dossary, Saleh, Marfurt, Kurt J.. 3D volumetric multispectral estimates of reflector curvature and rotation. Geophysics, vol.71, no.5, P41-P51.

상세보기
10.1190/1.3628241
Ashraf, Haroon, Mousa, Wail A., Al Dossary, Saleh. Sobel filter for edge detection of hexagonally sampled 3D seismic data. Geophysics, vol.81, no.6, N41-N51.

상세보기
10.1109/CVPR.2018.00964
10.1190/segam2018-2996921.1
Gersztenkorn, Adam, Marfurt, Kurt J.. Eigenstructure‐based coherence computations as an aid to 3-D structural and stratigraphic mapping. Geophysics, vol.64, no.5, 1468-1479.

상세보기
10.3997/2214-4609.201800732
Jaderberg, M., K. Simonyan, A. Zisserman, and K. Kavukcuoglu, 2015, Spatial transformer networks: Conference and Workshop on Neural Information Processing Systems, 2017-2025.
10.1190/1.2792759
Kingma, D. P., and J. Ba, 2014, ADAM: A method for stochastic optimization, https://arxiv.org/abs/1412.6980, accessed 1 April 2021.
LeCun, Yann, Bengio, Yoshua, Hinton, Geoffrey. Deep learning. Nature, vol.521, no.7553, 436-444.

상세보기
Li, Fangyu, Lu, Wenkai. Coherence attribute at different spectral scales. Interpretation, vol.2, no.1, SA99-SA106.

상세보기
Marfurt, Kurt J., Kirlin, R. Lynn, Farmer, Steven L., Bahorich, Michael S.. 3-D seismic attributes using a semblance‐based coherency algorithm. Geophysics, vol.63, no.4, 1150-1165.

상세보기
Marfurt, Kurt J., Sudhaker, V., Gersztenkorn, Adam, Crawford, Kelly D., Nissen, Susan E.. Coherency calculations in the presence of structural dip. Geophysics, vol.64, no.1, 104-111.

상세보기
10.1007/978-3-030-01249-6_34
10.1109/CVPR.2019.00941
10.1190/1.1817297
10.1190/segam2016-13773079.1
Qi, Jie, Lyu, Bin, AlAli, Abdulmohsen, Machado, Gabriel, Hu, Ying, Marfurt, Kurt. Image processing of seismic attributes for automatic fault extraction. Geophysics, vol.84, no.1, O25-O37.

상세보기
10.1190/segam2020-3428171.1
10.1190/1.1816675
Ronneberger, O., P. Fischer, and T. Brox, 2015, U-Net: Convolutional networks for biomedical image segmentation, https://arxiv.org/abs/1505.04597v1, accessed 1 December 2020.
Shan, S., W. Yan, X. Guo, E. I. Chang, Y. Fan, and Y. Xu, 2017, Unsupervised end-to-end learning for deformable medical image registration, https://arxiv.org/abs/1711.08608v2, accessed 1 December 2020.
Sobel, I., and G. Feldman, 1968, A 3× 3 isotropic gradient operator for image processing: Presented at the Stanford Artificial Project, 271-272.
10.1109/CVPR.2019.00584
Sun, K., Y. Zhao, B. Jiang, T. Cheng, B. Xiao, D. Liu, Y. Mu, X. Wang, W. Liu, and J. Wang, 2019b, High-resolution representations for labeling pixels and regions, https://arxiv.org/abs/1904.04514, accessed 1 December 2020.
Vaswani, A., N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, 2017, Attention is all you need, https://arxiv.org/abs/1706.03762, accessed 1 December 2020.
Wu, Xinming, Geng, Zhicheng, Shi, Yunzhi, Pham, Nam, Fomel, Sergey, Caumon, Guillaume. Building realistic structure models to train convolutional neural networks for seismic structural interpretation. Geophysics, vol.85, no.4, WA27-WA39.

상세보기
Wu, Xinming, Hale, Dave. 3D seismic image processing for faults. Geophysics, vol.81, no.2, IM1-IM11.

상세보기
Wu, Xinming, Liang, Luming, Shi, Yunzhi, Fomel, Sergey. FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation. Geophysics, vol.84, no.3, IM35-IM45.

상세보기
10.1190/segam2018-2995341.1
10.1109/ICCV.2015.164
Xiong, Wei, Ji, Xu, Ma, Yue, Wang, Yuxiang, AlBinHassan, Nasher M., Ali, Mustafa N., Luo, Yi. Seismic fault detection with convolutional neural network. Geophysics, vol.83, no.5, O97-O103.

상세보기
10.1109/CVPR.2015.7299002
10.1190/segam2020-3426516.1
10.1109/CVPR.2017.660
10.1190/segam2018-2997005.1
Zhou, Zhi-Hua. A brief introduction to weakly supervised learning. National science review, vol.5, no.1, 44-53.

상세보기
Zhou, Z., M. R. Siddiquee, N. Tajbakhsh, and J. Liang, 2018, UNet++: A nested U-Net architecture for medical image segmentation, https://arxiv.org/abs/1807.10165v1, accessed 1 December 2020.

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

3D fault detection: Using human reasoning to improve performance of convolutional neural networks

Abstract ▼ AI-Helper

참고문헌 (40)

이 논문을 인용한 문헌

관련 콘텐츠

원문 URL 링크

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트