지구물리와물리탐사 (Geophysics and Geophysical Exploration)

  • 제25권2호
  • /
  • Pages.59-70
  • /
  • 2022
  • /
  • 1229-1064(pISSN)
  • /
  • 2384-051X(eISSN)
한국지구물리·물리탐사학회 (Korean Society of Earth and Exploration Geophysicists)
권호 표지
DOI QR코드

DOI QR Code

3차원 탄성파자료의 층서구분을 위한 패치기반 기계학습 방법의 개선

Improvements in Patch-Based Machine Learning for Analyzing Three-Dimensional Seismic Sequence Data

  • 이동욱 (해저활성단층연구단, 한국해양과학기술원) ;
  • 문혜진 (해저활성단층연구단, 한국해양과학기술원) ;
  • 김충호 (해저활성단층연구단, 한국해양과학기술원) ;
  • 문성훈 (해저활성단층연구단, 한국해양과학기술원) ;
  • 이수환 (해저활성단층연구단, 한국해양과학기술원) ;
  • 주형태 (해저활성단층연구단, 한국해양과학기술원)
  • Lee, Donguk (Marine Active Fault Research Unit, Korea Institute of Ocean Science and Technology) ;
  • Moon, Hye-Jin (Marine Active Fault Research Unit, Korea Institute of Ocean Science and Technology) ;
  • Kim, Chung-Ho (Marine Active Fault Research Unit, Korea Institute of Ocean Science and Technology) ;
  • Moon, Seonghoon (Marine Active Fault Research Unit, Korea Institute of Ocean Science and Technology) ;
  • Lee, Su Hwan (Marine Active Fault Research Unit, Korea Institute of Ocean Science and Technology) ;
  • Jou, Hyeong-Tae (Marine Active Fault Research Unit, Korea Institute of Ocean Science and Technology)
  • 투고 : 2022.01.19
  • 심사 : 2022.03.29
  • 발행 : 2022.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근의 연구들을 통해 기계학습은 탄성파 해석 분야에 그 적용 범위를 확장하고 있으며, 탄성파 해석에서 중요한 탄성파 층서 구분을 수행하는 합성곱 신경망들의 개발도 수행되었다. 하지만 지도 학습의 경우 대량의 학습 자료가 필요하며, 비용과 시간의 한계로 탄성파 층서구분의 지도학습은 학습 자료의 부족이 문제가 될 수 있다. 이번 연구에서는 자료 부족 문제를 보완하기위해 탄성파 단면에 패치 분할과 자료증강을 적용하였다. 또한 패치 분할로 손실될 수 있는 공간정보를 제공하기 위해 깊이를 고려할 수 있는 인공 채널을 생성하여 추가하였다. 실험을 위한 학습 모델로 U-Net을 사용하였으며, 층서 구분을 위한 학습 자료가 제공되는 F3 block 자료를 이용하여 학습과 예측 결과에 대한 평가를 수행하였다. 분석 결과 자료증강과 인공 채널의 추가로 패치 기반의 층서 구분 학습 모델을 개선할 수 있음을 확인하였다.

Recent studies demonstrate that machine learning has expanded in the field of seismic interpretation. Many convolutional neural networks have been developed for seismic sequence identification, which is important for seismic interpretation. However, expense and time limitations indicate that there is insufficient data available to provide a sufficient dataset to train supervised machine learning programs to identify seismic sequences. In this study, patch division and data augmentation are applied to mitigate this lack of data. Furthermore, to obtain spatial information that could be lost during patch division, an artificial channel is added to the original data to indicate depth. Seismic sequence identification is performed using a U-Net network and the Netherlands F3 block dataset from the dGB Open Seismic Repository, which offers datasets for machine learning, and the predicted results are evaluated. The results show that patch-based U-Net seismic sequence identification is improved by data augmentation and the addition of an artificial channel.

키워드

과제정보

이 연구는 한국해양과학기술원 주요사업인 '해양방위 및 안전기술 개발(PEA0041)'과 산업통상자원부의 '대심도 해양 탐사시추를 통한 대규모 CO2 지중저장소 확보(PN90810)'의 지원을 받아 수행되었습니다.

참고문헌

  1. Alaudah, Y., Michalowicz, P., Alfarraj, M., and AlRegib, G., 2019, A machine-learning benchmark for facies classification, Interpretation, 7(3), p.SE175-SE187, doi: 10.1190/INT-2018-0249.1.
  2. Chaki, S., 2015, Reservoir characterization: A machine learning approach, arXiv preprint, arXiv:1506.05070, doi: 10.48550/arXiv.1506.05070.
  3. Chevitarese, D., Szwarcman, D., Silva, R. M. D., and Brazil, E. V., 2018. Seismic facies segmentation using deep learning, AAPG Ann. Convention and Exhibition, https://www.searchanddiscovery.com/documents/2018/42286chevitarese/ndx_chevitarese.pdf
  4. Choi, W. C., Lee, G. H., Cho, S. I., Choi, B. H., and Pyun, S. J., 2020, Fault detection for seismic data interpretation based on machine learning: Research trends and technological introduction, Geophys. and Geophys. Explor., 23(2), p.97-114, doi: 10.7582/GGE.2020.23.2.097.
  5. Choi, W. C., and Pyun, S. J., 2021, Synthetic training data generation for fault detection based on deep learning, Geophys. and Geophys. Explor., 24(3), p.89-97, doi: 10.7582/GGE.2021.24.3.089.
  6. Csurka, G., Larlus, D., Perronnin, F. and Meylan F., 2013, What is a good evaluation measure for semantic segmentation?, BMVC, 27, p.2013, doi: 10.5244/C.27.32.
  7. Cunha, A., Pochet, A., Lopes, H., and Gattass, M., 2020, Seismic fault detection in real data using transfer learning from a convolutional neural network pre-trained with synthetic seismic data, Comput. Geosci., 135, p.104344, doi: 10.1016/j.cageo.2019.104344.
  8. Forman, G., and Scholz, M., 2010. Apples-to-apples in crossvalidation studies: pitfalls in classifier performance measurement, SIGKDD Explor., 12(1), pp.49-57, doi: 10.1145/1882471.1882479.
  9. Griffith, D. P., Zamanian, S. A., Vila, J., Vial-Aussavy, A., Solum, J., Potter, R. D., and Menapace, F., 2019, Deep learning applied to seismic attribute computation, Interpretation, 7(3), SE141-SE150, doi: 10.1190/INT-2018-0227.1.
  10. Guillen, P., Larrazabal, G., Gonzalez, G., Boumber, D., and Vilalta, R., 2015, Supervised learning to detect salt body, SEG Technical Program Expanded Abstracts 2015, Soc. Expl. Geophys., p.1826-1829, doi: 10.1190/segam2015-5931401.1.
  11. Guillon, S., Joncour, F., Goutorbe, P., and Castanie, L., 2019, Reducing training dataset bias for automatic fault detection, 89th Ann. Internat. Mtg., Soc. Expl. Geophys., Expanded Abstract, p.2423-2427, doi: 10.1190/segam2019-3216557.1.
  12. Kao, P., Shailja, S., Jiang, J., Zhang, A., Khan, A., Chen, J. W., and Manjunath, B. S., 2020, Improving Patch-Based Convolutional Neural Networks for MRI Brain Tumor Segmentation by Leveraging Location Information, Frontiers in Neuroscience, 13, p.1449, doi: 10.3389/fnins.2019.01449.
  13. Keynejad, S., Sbar, M. L., and Jhonson, R. A., 2019, Assessment of machine-learning techniques in predicting lithofluid facies logs in hydrocarbon wells, Interpretation, 7(3), p.SF1-SF13, doi: 10.1190/INT-2018-0115.1.
  14. Krizhevsky, A., Sutskever, I., and Hinton, G. E., 2012. Imagenet classification with deep convolutional neural networks, Adv. Neural Inf. Process. Syst., p.1097-1105, https://dl.acm.org/doi/10.5555/2999134.2999257.
  15. 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, J. Appl. Geophy., 159, p.52-68, doi: 10.1016/j.jappgeo.2018.07.023.
  16. Lee, H., Nam, H., Kim, B., Kang, M., and Park, K., 2019, Status of Marine Seismic Exploration Technology, J. Korean Soc. Miner. Energy Resour. Eng., 56(1), pp. 86-106, https://doi.org/10.32390/ksmer.2019.56.1.086
  17. Li, S., Yang, C., Sun, H., and Zhang, H., 2019, Seismic fault detection using an encoder-decoder convolutional neural network with a small training set, J. Geophys. Eng., 16(1), p.175-189, doi: 10.1093/jge/gxy015.
  18. Liu, N., He, T., Tian, Y., Wu, B., Gao, J., and Xu, Z., 2020, Common-azimuth seismic data fault analysis using residual UNet, Interpretation, 8(3), SM25-SM37, doi: 10.1190/INT2019-0173.1.
  19. Mandelli, S., Lipari, V., Bestagini, P., and Tubaro, S., 2019, Interpolation and Denoising of Seismic Data using Convolutional Neural Networks, arXiv preprint, arXiv:1901.07927, doi: 10.48550/arXiv.1901.07927.
  20. Misra, D., Crispim-Junior, C., and Tougne, L., 2020, Patch-based CNN evaluation for bark classification. ECCV, Springer, Cham., pp.197-212, doi: 10.1007/978-3-030-65414-6_15.
  21. Moon, H., Jou, H., Lee, S., Kim, H., and Jun, H., 2020, Comparison of Convolutional Neural Networks for Dividing Seismic Sequences, J. The Korean Soc. Miner. Energy Resour. Eng., 57(6), pp.541-553, doi: 10.32390/ksmer.2020.57.6.541.
  22. Noh, H., Hong, S., and Han, B., 2015. Learning deconvolution network for semantic segmentation, arXiv preprint, arXiv: 1505.04366, doi: 10.48550/arXiv.1505.04366.
  23. Onajite, E., 2013, Seismic data analysis techniques in hydrocarbon exploration, Elsevier, p256. https://www.bookdepository.com/Seismic-Data-Analysis-Techniques-Hydrocarbon-ExplorationEnwenode-Onajite/9780124200234
  24. Pochet, A., Diniz, P. H., Lopes, H., and Gattass, M., 2019, Seismic fault detection using convolutional neural networks trained on synthetic poststacked amplitude maps, IEEE Trans. Geosci. Remote. Sens., 16(3), p.352-356, doi: 10.1109/LGRS.2018.2875836.
  25. Qi, J., Lyu, B., Wu, X., and Marfurt, K., 2020, Comparing convolutional neural networking and image processing seismic fault detection methods, 90th Ann. Internat. Mtg., Soc. Expl. Geophys., Expanded Abstract, p.1111-1115, doi: 10.1190/segam2020-3428171.1.
  26. Qian, F., Yin, M., Liu, X. Y., Wang, Y. J., Lu, C., and Hu, G. M., 2018. Unsupervised seismic facies analysis via deep convolutional autoencoders, Geophysics, 83(3), p.A39-A43, doi: 10.1190/geo2017-0524.1.
  27. Ronneberger, O., Fischer, P., and Brox, T., 2015, U-net: Convolutional networks for biomedical image segmentation, International Conference on Medical image computing and computer-assisted intervention, Springer, Cham, p.234-241, doi: 10.1007/978-3-319-24574-4_28.
  28. Sen, S., Kainkaryam, S., Ong, C., and Sharma, A., 2019, Regularization strategies for deep-learning-based salt model building, Interpretation, 7(4), p.T911-T922, doi: 10.1190/INT-2018-0229.1.
  29. Shi, Y., Wu, X., and Fomel, S., 2019, SaltSeg: Automatic 3D salt segmentation using a deep convolutional neural network, Interpretation, 7(3), p.SE113-SE122, doi: 10.1190/INT-2018-0235.1.
  30. Simonyan, K., and Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition, arXiv preprint, arXiv:1409.1556, doi: 10.48550/arXiv.1409.1556.
  31. Smith, R., Mukerji, T., and Lupo, T., 2019, Correlating geologic and seismic data with unconventional resource production curves using machine learning, Geophysics, 84(2), p.O39-O47, doi: 10.1190/geo2018-0202.1.
  32. Tian, X., and Daigle, H., 2018, Machine-learning-based object detection in images for reservoir characterization: A case study of fracture detection in shales, The Leading Edge, 37(6), p.435-442, doi: 10.1190/tle37060435.1.
  33. Wrona, T., Pan, I., Gawthorpe, R. L., and Fossen, H., 2018, Seismic facies analysis using machine learning, Geophysics, 83(5), p.O83-O95, doi: 10.1190/geo2017-0595.1.
  34. Wu, X., Liang, L., Shi, Y., and Fomel, S., 2019, FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation, Geophysics, 84(3), p.IM35-IM45, doi: 10.1190/geo2018-0646.1.
  35. Wu, X., Geng, Z., Shi, Y., Pham, N., Fomel, S., and Caumon, G., 2020, Building realistic structure models to train convolutional neural networks for seismic structural interpretation, Geophysics, 85(4), p.WA27-WA39, doi: 10.1190/geo2019-0375.1.
  36. Xiong, W., Ji, X., Ma, Y., Wang, Y., ALBinHassan, N. M., Ali, M. N., and Luo, Y., 2018, Seismic fault detection with convolutional neural network, Geophysics, 83(5), p.O97-O103, doi: 10.1190/geo2017-0666.1.
  37. Yuan, C., Cai, M., Lu, F., Li, H., and Li, G., 2020, 3D Fault Detection Based on GCS-Net, 82nd Ann. Internat. Mtg., Eur. Assn. Geosci. Eng., Conference Proceedings, doi: 10.3997/2214-4609.202010699.
  38. Zhang, C., Frogner, C., Araya-Polo, M., and Hohl, D., 2014, Machine-learning based automated fault detection in seismic traces, 76th EAGE Conference and Exhibition 2014, Eur. Assn. Geosci. Eng., p.1-5, doi: 10.3997/2214-4609.20141500.
  39. Zhao, T., 2018a. Seismic facies classification using different deep convolutional neural networks, SEG Technical Program Expanded Abstracts 2018, Soc. Expl. Geophys., p.2046-2050, doi: 10.1190/segam2018-2997085.1.
  40. Zhao, T., Li, F., and Marfurt, K. J., 2018b, Seismic attribute selection for unsupervised seismic facies analysis using user-guided data-adaptive weights, Geophysics, 83(2), p.O31-O44, doi: 10.1190/geo2017-0192.1.