Application of machine learning for adaptive subtraction of multiple reflected waves
https://doi.org/10.18303/2619-1563-2023-1-54
Abstract
This work is devoted to the development and testing of an algorithm for adaptive subtraction of multiple reflected waves using a convolutional neural network. The algorithm is one of the main steps in the method of suppression of multiple reflected waves based on the separation of wave forms in the Radon region. The paper considers the formulation of a problem for a neural network, the preparation of training and test data sets and the testing of the algorithm. Using a convolutional neural network allows to automate and speed up the adaptive subtraction procedure. The algorithm was tested on synthetic data. Testing shows the effective adaptation of multiple waves, as well as the importance of correctly constructing a model of multiples.
About the Authors
A. M. Kamashev
http://www.ipgg.sbras.ru/ru/institute/staff/kamashevam
Trofimuk Institute of Petroleum Geology and Geophysics SB RAS
Koptyug Ave., 3, Novosibirsk, 630090
Novosibirsk State University
Pirogova Str., 1, Novosibirsk, 630090
Russian Federation
Trofimuk Institute of Petroleum Geology and Geophysics SB RAS
Koptyug Ave., 3, Novosibirsk, 630090
Novosibirsk State University
Pirogova Str., 1, Novosibirsk, 630090
Russian Federation
A. A. Duchkov
http://www.ipgg.sbras.ru/ru/institute/staff/duchkovaa
Trofimuk Institute of Petroleum Geology and Geophysics SB RAS
Koptyug Ave., 3, Novosibirsk, 630090
Novosibirsk State University
Pirogova Str., 1, Novosibirsk, 630090
Russian Federation
Trofimuk Institute of Petroleum Geology and Geophysics SB RAS
Koptyug Ave., 3, Novosibirsk, 630090
Novosibirsk State University
Pirogova Str., 1, Novosibirsk, 630090
Russian Federation
References
1. Boganik G.N., Gurvich I.I. Seismic prospecting [in Russian]. – AIS, Tver, 2006. – 743 p.
2. Nikitin V.V., Duchkov A.A., Romanenko A.A., Andersson F. Parallel algorithm for the expansion of functions in wave packets for GPU and its application in geophysics // NSU Bulletin. Series: Information Technology. – 2013. – Vol. 11 (1) – P. 93–104.
3. Chen W., Yang L., Wang H., Chen Y. Fast high-resolution hyperbolic radon transform // IEEE Transactions on Geoscience and Remote Sensing. – 2021. – Vol. 60. – P. 1–10, doi: 10.1109/TGRS.2021.3084612.
4. Hampson D. Inverse velocity stacking for multiple elimination // Journal of the Canadian Society of Exploration Geophysicists. – 1986. – P. 44–55.
5. Loginov G., Duchkov A., Litvichenko D., Alyamkin S. The first-break detection for real seismic data with use of convolutional neural network // 81st EAGE Conference and Exhibition 2019. – 2019. – Vol. 2019 (1). – P. 1–5, doi: 10.3997/2214-4609.201901614.
6. Neelamani R., Baumstein A., Ross W.S. Adaptive subtraction using complex-valued curvelet transforms // Geophysics. – 2010. – Vol. 75 (4) – P. V51–V60, doi: 10.1190/1.3453425.
7. Nikitin V.V., Anderson F., Carlsson M., Duchkov A.A. Fast hyperbolic Radon transform represented as convolutions in log-polar coordinates // Computers & Geosciences. – 2017. – Vol. 105. – P. 21–33, doi: 10.1016/j.cageo.2017.04.013.
8. Ronneberger O., Fischer P., Brox T. U-net: Convolutional networks for biomedical image segmentation // International Conference on Medical image computing and computer-assisted intervention. – Springer, Cham, 2015. – P. 234–241.
9. Verschuur D.J. Seismic multiple removal techniques: past, present and future. – EAGE Publications, Houten, 2013. – 300 p.
10. Yilmaz Ö. Seismic data analysis: Processing, inversion, and interpretation of seismic data. – SEG, 2001. – 2065 p., doi: 10.1190/1.9781560801580.
11. Zheng Y., He D.K., Hou J., Feng X. Surface wave suppressing and decomposition using deep neural networks // 83rd EAGE Annual Conference & Exhibition. – 2022. – Vol. 2022 (1). – P. 1–5.
12. Zhu W., Mousavi S.M., Beroza G.C. Seismic signal denoising and decomposition using deep neural networks // IEEE Transactions on Geoscience and Remote Sensing. – 2019. – Vol. 57 (11). – P. 9476–9488, doi: 10.1109/TGRS.2019.2926772.
Review
For citations:
Kamashev A.M., Duchkov A.A. Application of machine learning for adaptive subtraction of multiple reflected waves. Russian Journal of Geophysical Technologies. 2023;(1):54-65. (In Russ.) https://doi.org/10.18303/2619-1563-2023-1-54
Views:
309
Email this article 