A seismic random noise suppression method based on self-supervised deep learning and transfer learning

• Autorzy: Wu, Tianqi , Meng, Xiaohong , Liu, Hong , Li, Wenda
• Języki publikacji: EN

Abstrakty

EN

Random noise suppression is an essential task in the seismic data processing. In recent years deep learning methods have achieved superior results in seismic data denoising. However, obtaining clean data from field seismic data for training is challenging. Therefore, supervised deep learning denoising methods can only use synthetic datasets or field datasets constructed by conventional seismic denoising methods for training. Aiming at this problem, we proposed a self-supervised deep learning seismic denoising method based on Neighbor2Neighbor. This method only requires sampling the noisy data twice to train the denoising network without clean data. For the characteristics of seismic data, we designed a vertical neighbor subsample to make Neighbor2Neighbor more suitable for seismic data. In addition, to further improve the denoising effect in field data, we introduced a transfer learning strategy in our method. Numerical experiments demonstrated that our method outperformed both the conventional denoising seismic method and the supervised learning seismic denoising method after transfer learning.

Słowa kluczowe

PL

losowy szum sejsmiczny; głębokie uczenie; samonadzorowane uczenie; uczenie transferowe

EN

seismic random noise; deep learning; self-supervised learning; transfer learning

• Czasopismo: Acta Geophysica
• Rocznik: 2024
• Tom: Vol. 72, no. 2
• Strony: 655--671
• Opis fizyczny: Bibliogr. 31 poz.

Twórcy

autor

Wu, Tianqi

• School of Geophysics and Information Engineering, China University of Geosciences, Beijing 100083, China,
• Key Laboratory of Petroleum Resources Research, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China

autor

Meng, Xiaohong

• School of Geophysics and Information Engineering, China University of Geosciences, Beijing 100083, China,

autor

Liu, Hong

• Key Laboratory of Petroleum Resources Research, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China,

autor

Li, Wenda

• Key Laboratory of Petroleum Resources Research, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China,

Bibliografia

• 1. Bao L, Yang Z, Wang S et al (2020) Real image denoising based on multi-scale residual dense block and cascaded U-net with blockconnection, pp 448-449. https://openaccess.thecvf.com/content_ CVPRW_2020/html/w31/Bao_Real_Image_Denoising_Based_ on_Multi-Scale_Residual_Dense_Block_and_CVPRW_2020_ paper.html
• 2. Bekara M, van der Baan M (2009) Random and coherent noise attenuation by empirical mode decomposition. Geophysics 74(5):V89-V98. https://doi.org/10.1190/1.3157244
• 3. Canales LL (1984) Random noise reduction. In: SEG Technical Program Expanded Abstracts 1984. SEG Technical Program Expanded Abstracts, Society of Exploration Geophysicists, p 525-527, https://doi.org/10.1190Z1.1894168,
• 4. Dong X, Lin J, Lu S et al (2022) Seismic shot gather denoising by using a supervised-deep-learning method with weak dependence on real noise data: a solution to the lack of real noise data. Surv Geophys 43:1363
• 5. Gao Z, Li C, Yang T et al (2021) OMMDE-Net: a deep learning-based global optimization method for seismic inversion. IEEE Geosci Remote Sens Lett 18(2):208-212, In: IEEE geoscience and remote sensing letters. https://doi.org/10.1109/LGRS.2020.2973266,
• 6. Geng Z, Wu X, Shi Y et al (2020) Deep learning for relative geologic time and seismic horizons. Geophysics 85(4):87-100. https://doi. org/10.1190/geo2019-0252.1
• 7. Huang T, Li S, Jia X et al (2021) Neighbor2Neighbor: self-supervised denoising from single noisy images. pp 14781-14790. https:// openaccess.thecvf.com/content/CVPR2021/html/Huang_Neigh bor2Neighbor_Self-Supervised_Denoising_From_Single_Noisy_ Images_CVPR_2021_paper.html
• 8. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
• 9. Lehtinen J, Munkberg J, Hasselgren J et al (2018) Noise2Noise: learning image restoration without clean data. arXiv:1803.04189 [cs, stat]
• 10. Li S, Liu B, Ren Y et al (2020) Deep-learning inversion of seismic data. IEEE Trans Geosci Remote Sens 58(3):2135-2149. https://doi. org/10.1109/TGRS.2019.2953473. arXiv:1901.07733
• 11. Li W, Liu H, Wang J (2021) A Deep learning method for denoising based on a fast and flexible convolutional neural network. IEEE Trans Geosci Remote Sens, pp 1-13. In: IEEE transactions on geoscience and remote sensing. https://doi.org/10.1109/TGRS. 2021.3073001
• 12. Liu Y, Li B (2018) Streaming orthogonal prediction filter in the t-x domain for random noise attenuation. Geophysics 83(4):F41-F48. https://doi.org/10.1190/geo2017-0322.1
• 13. Lu Z, Chen Y (2021) Single image super-resolution based on a modified U-net with mixed gradient loss. Signal Image Video Process. https://doi.org/10.1007/s11760-021-02063-5
• 14. Mousavi SM, Langston CA (2016) Hybrid seismic denoising using higher-order statistics and improved wavelet block thresholding hybrid seismic denoising using higher-order statistics and improved wavelet block thresholding. Bull Seismol Soc Am 106(4):1380-1393. https://doi.org/10.1785/0120150345
• 15. Neelamani R, Baumstein AI, Gillard DG et al (2008) Coherent and random noise attenuation using the curvelet transform. Lead Edge 27(2):240-248. https://doi.org/10.1190/1.2840373
• 16. Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM et al (eds) Medical image computing and computer-assisted intervention—MICCAI 2015, Lecture notes in computer science. Springer, Cham, pp 234-241. https:// doi.org/10.1007/978-3-319-24574-4_28
• 17. Saad OM, Chen Y (2020) Deep denoising autoencoder for seismic random noise attenuation. Geophysics 85(4):V367-V376. https://doi.org/10.1190/geo2019-0468.1
• 18. Sang W, Yuan S, Yong X et al (2020) DCNNS-based denoising with a novel data generation for multidimensional geological structures learning. IEEE Geosci Remote Sens Lett 18(10):1861-1865
• 19. Shi Y, Wu X, Fomel S (2020) Waveform embedding: automatic horizon picking with unsupervised deep learning. Geophysics 85(4):WA67-WA76. https://doi.org/10.1190/geo2019-0438.1
• 20. Tang G, Ma JW, Yang HZ (2012) Seismic data denoising based on learning-type overcomplete dictionaries. Appl Geophys 1(9):27-32. https://doi.org/10.1007/s11770-012-0310-z
• 21. Tibi R, Hammond P, Brogan R et al (2021) Deep learning denoising applied to regional distance seismic data in Utah. Bull Seismol Soc Am 111(2):775-790
• 22. Tsai KC, Hu W, Wu X, et al (2020) Automatic First Arrival Picking via Deep Learning With Human Interactive Learning. IEEE Trans Geosci Remote Sens 58(2):1380-1391. In: IEEE transactions on geoscience and remote sensing. https://doi.org/10.1109/TGRS. 2019.2946118,
• 23. Turquais P, Asgedom EG, Söllner W (2017) A method of combining coherence-constrained sparse coding and dictionary learning for denoising. Geophysics 82(3):V137-V148. https://doi.org/10. 1190/geo2016-0164.1
• 24. Wang B, Wu RS, Chen X et al (2015) Simultaneous seismic data interpolation and denoising with a new adaptive method based on Dreamlet transform. Geophys J Int 201(2):1182-1194. https:// doi.org/10.1093/gji/ggv072
• 25. Wang F, Chen S (2019) Residual learning of deep convolutional neural network for seismic random noise attenuation. IEEE Geosci Remote Sens Lett 16(8):1314-1318. https://doi.org/10.1109/ LGRS.2019.2895702
• 26. Wang W, McMechan GA, Ma J et al (2021) Automatic velocity picking from semblances with a new deep-learning regression strategy: comparison with a classification approach. Geophysics 86(2):U1-U13. https://doi.org/10.1190/geo2020-0423.1
• 27. Wu Y, McMechan GA (2019) Parametric convolutional neural networkdomain full-waveform inversion. Geophysics 84(6):R881-R896. https://doi.org/10.1190/geo2018-0224.1
• 28. Yu S, Ma J, Zhang X et al (2015) Interpolation and denoising of highdimensional seismic data by learning a tight frame. Geophysics 80(5):V119-V132. https://doi.org/10.1190/geo2014-0396.1
• 29. Yu S, Ma J, Wang W (2019) Deep learning for denoising. Geophysics 84(6):V333-V350. https://doi.org/10.1190/geo2018-0668.1
• 30. Zheng Y, Zhang Q, Yusifov A et al (2019) Applications of supervised deep learning for seismic interpretation and inversion. Lead Edge 38(7):526-533. https://doi.org/10.1190/tle38070526.1
• 31. Zhu L, Liu E, McClellan JH (2015) Seismic data denoising through multiscale and sparsity-promoting dictionary learning. Geophysics 80(6):WD45-WD57. https://doi.org/10.1190/geo2015-0047.1

Identyfikatory

DOI

10.1007/s11600-023-01105-5