Comparison of Convolutional Neural Networks for Dividing Seismic Sequences

Hye-Jin Moon; Hyeong-Tae Jou; Sang Hoon Lee; Han-Joon Kim; Hyunggu Jun

doi:10.32390/ksmer.2020.57.6.541

All Issue

2020 Vol.57, Issue 6 Preview Page Next Page

Research Paper

Comparison of Convolutional Neural Networks for Dividing Seismic Sequences 탄성파 층서 구분을 위한 합성곱 신경망 기법 비교 연구

31 December 2020. pp. 541-553

PDF XML

Abstract

Application of the machine learning technique is expanding to the field of seismic exploration. For the purpose of feasibility assessment, we applied the machine learning technique to seismic sequence identification, which is important in seismic interpretation. From among the convolutional neural network techniques used in image analysis, we applied four models to seismic data obtained in the F3 block, offshore Netherlands, which have yielded remarkable results. One of the four models was ResNet34. The others were encoder–decoder models: U-Net, Residual U-Net, and FD U-Net. We first performed a qualitative analysis of the predicted images and then conducted quantitative analysis using pixel accuracy, mean class accuracy, mean intersection over union, and frequency weighted IU equations. The numerical results showed that ResNet34 had the lowest accuracy and that the encoder–decoder type models had higher accuracy. Considering the number of parameters required for calculation and the learning time, we confirmed that U-Net is the most efficient model.

Keywords

Machine learning

Convolutional neural network

Seismic sequence identification

Encoder–decoder model

Netherlands F3 block

머신 러닝 기술은 탄성파탐사 분야로 그 적용 범위를 확장하고 있다. 탄성파 해석에서 중요한 탄성파 층서 구분에 머신 러닝의 적용 가능성을 알아보았다. 이미지 분야에 탁월한 결과를 보여온 합성곱 신경망 기법 중 4가지 모델을 네덜란드 F3 block에 적용시켰다. 4가지 모델은 ResNet34 모델, 인코더-디코더 형태를 가지는 U-Net, Residual U-Net, FD U-Net이다. 예측된 이미지의 정성적 분석 수행 후 정량적 분석을 위해 pixel accuracy, mean class accuracy, mean intersection over union, frequency weighted IU의 수식을 활용하였다. 본 연구의 분석 결과 ResNet34의 정확도 결과가 가장 낮았고, 인코더-디코더 형태를 가지는 모델들이 높은 정확도를 보여주었다. 그리고 계산에 필요한 파라미터수와 학습시간을 고려 할 때 U-Net이 가장 효율적임을 확인할 수 있었다.

키워드

머신 러닝

합성곱신경망

탄성파층서구분

인코더-디코더 모델

네덜란드 F3 block

References

Alaudah, 2019b, Facies_classification_benchmark, 2019.11.28, https://github.com/yalaudah/fa cies_classification_benchmark.

Alaudah, Y., Michałowicz, P., Alfarraj, M., and AlRegib, G., 2019a. A machine-learning benchmark for facies classification. Interpretation, 7(3), p.SE175-SE187. 10.1190/INT-2018-0249.1

Bengio, Y., Simard, P., and P. Frasconi., 1994. Learning long-term dependencies with gradient descent is difficult, IEEE Transactions on Neural Networks, 5(2), p.157-166. 10.1109/72.27918118267787

Chaki, S., 2015. Reservoir characterization: A machine learning approach, MS Thesis, Indian Institute of Technology, India, 98p.

Chevitarese, D., Szwarcman, D., Silva, R. M. D., and Brazil, E. V., 2018. Seismic facies segmentation using deep learning. AAPG Annual Convention and Exhibition. Salt Lake City, Utah.

Cho, Y., Jeong, D., and Jun, H., 2020. Semi‐auto horizon tracking guided by strata histograms generated with transdimensional Markov‐chain Monte Carlo. Geophysical Prospecting, 68(5), p.1456-1475. 10.1111/1365-2478.12933

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. Geophysics and Geophysical Exploration, 23(2), p.97-114.

dGB Earth Sciences, Seismic interpretation software & services, 2018.

Dramsch, J.S. and Lüthje, M., 2018. Deep-learning seismic facies on state-of-the-art CNN architectures. SEG Technical Program Expanded Abstracts 2018, Society of Exploration Geophysicists. p.2036-2040. 10.1190/segam2018-2996783.1

Glorot, X. and Bengio, Y., 2010. Understanding the difficulty of training deep feedforward neural networks. Proceedings of the thirteenth international conference on artificial intelligence and statistics, AISTATS, 2010, p.249-256.

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), p.SE141-SE150. 10.1190/INT-2018-0227.1

Guillen, P., Larrazabal, G., González, G., Boumber, D., and Vilalta, R., 2015. Supervised learning to detect salt body. SEG Technical Program Expanded Abstracts 2015, Society of Exploration Geophysicists, p.1826-1829. 10.1190/segam2015-5931401.1

He, K., Zhang, X., Ren, S., and Sun, J., 2016a. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, p.770-778. 10.1109/CVPR.2016.9026180094

He, K., Zhang, X., Ren, S., and Sun, J., 2016b. Identity mappings in deep residual networks. In European conference on computer vision. Springer, Cham., p.630-645. 10.1007/978-3-319-46493-0_38

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. 10.1190/INT-2018-0115.1

Krizhevsky, A., Sutskever, I., and Hinton, G.E., 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, p.1097- 1105.

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, p.52-68. 10.1016/j.jappgeo.2018.07.023

Noh, H., Hong, S., and Han, B., 2015. Learning deconvolution network for semantic segmentation. Proceedings of the IEEE international conference on computer vision (ICCV), p.1520-1528. 10.1109/ICCV.2015.178

Onajite, E., 2013. Seismic data analysis techniques in hydrocarbon exploration. Elsevier. 256p.

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. 10.1190/geo2017-0524.1

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. 10.1007/978-3-319-24574-4_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. 10.1190/INT-2018-0229.1

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. 10.1190/INT-2018-0235.1

Silva, R.M., Baroni, L., Ferreira, R.S., Civitarese, D., Szwarcman, D., and Brazil, E.V., 2019. Netherlands dataset: A new public dataset for machine learning in seismic interpretation. arXiv preprint arXiv:1904.00770.

Simonyan, K. and Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

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. 10.1190/geo2018-0202.1

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., and Rabinovich, A., 2015. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition, p.1-9. 10.1109/CVPR.2015.7298594

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. 10.1190/tle37060435.1

Waldeland, A. and A. Solberg, 2016. 3D Attributes and Classification of Salt Bodies on Unlabelled Datasets. 78th EAGE Conference and Exhibition 2016, EAGE Publications BV. 10.3997/2214-4609.201600880

Wrona, T., Pan, I., Gawthorpe, R.L., and Fossen, H., 2018. Seismic facies analysis using machine learning. Geophysics, 83(5), p.O83-O95. 10.1190/geo2017-0595.1

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. 10.1190/geo2017-0666.1

Yi, H.U., 2019, Case Analysis of Applications for Deep Learning Technology in the Mining Industry. Journal of the Korean Society of Mineral and Energy Resources Engineers, 56(5), p.435-446. 10.32390/ksmer.2019.56.5.435

Yu, F. and Koltun, V., 2015. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122.

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, European Association of Geoscientists & Engineers, 2014(1), p.1-5. 10.3997/2214-4609.20141500

Zhang, W., Lu, X., Gu, Y., Liu, Y., Meng, X., and Li, J., 2019. A Robust Iris Segmentation Scheme Based on Improved U-Net. IEEE Access, 7, p.85082-85089. 10.1109/ACCESS.2019.2924464

Zhang, Z., Liu, Q., abd Wang, Y., 2018. Road extraction by deep residual u-net. IEEE Geoscience and Remote Sensing Letters, 15(5), p.749-753. 10.1109/LGRS.2018.2802944

Zhao, T., 2018a. Seismic facies classification using different deep convolutional neural networks. SEG Technical Program Expanded Abstracts 2018, Society of Exploration Geophysicists, p.2046-2050. 10.1190/segam2018-2997085.1

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. 10.1190/geo2017-0192.1

Zhou, X. Y. and Yang, G. Z., 2019. Normalization in training U-Net for 2-D biomedical semantic segmentation. IEEE Robotics and Automation Letters, 4(2), p.1792-1799. 10.1109/LRA.2019.2896518

Information

Publisher :The Korean Society of Mineral and Energy Resources Engineers
Publisher(Ko) :한국자원공학회
Journal Title :Journal of the Korean Society of Mineral and Energy Resources Engineers
Journal Title(Ko) :한국자원공학회지
Volume : 57
No :6
Pages :541-553
Received Date : 2020-09-22
Revised Date : 2020-11-20
Accepted Date : 2020-12-22
DOI :https://doi.org/10.32390/ksmer.2020.57.6.541

Journal of the Korean Society of Mineral and Energy Resources Engineers ISSN:2288-0291(Print) 2288-2790(Online) 한국자원공학회지

All Issue