Internal multiple elimination method based on attention mechanism

PeiNan BAO, WeiHong WANG, ZhiWei LI, SiQi ZHANG

Prog Geophy ›› 2024, Vol. 39 ›› Issue (4) : 1474-1482.

PDF(3717 KB)
Home Journals Progress in Geophysics
Progress in Geophysics

Abbreviation (ISO4): Prog Geophy      Editor in chief:

About  /  Aim & scope  /  Editorial board  /  Indexed  /  Contact  / 
PDF(3717 KB)
Prog Geophy ›› 2024, Vol. 39 ›› Issue (4) : 1474-1482. DOI: 10.6038/pg2024II0196

Internal multiple elimination method based on attention mechanism

Author information +
History +

Abstract

Internal multiple suppression of seismic data has been a research hotspot and difficulty in the field of oil and gas exploration. The strong reflection interface in the subsurface will form internal multiples with strong energy, which seriously affect the identification of primaries. It also can reduce the authenticity and reliability of seismic imaging. The deep learning-based multiple suppression method can form more abstract high-level features by combining the low-level features to better discover the effective features of the data, and the multiple separation accuracy is high. In this paper, the attention mechanism is introduced for the problem of high training cost of traditional convolutional neural network, and an internal multiple suppression method based on the attention mechanism is proposed to reduce the training cost of neural network model. The data test shows that the method is not affected by the limitations of the traditional internal multiple suppression method and can avoid the regularization of seismic data, thus reducing the computational burdens and improving the computational efficiency, which has important theoretical and industrial application value.

Cite this article

Download Citations
PeiNan BAO , WeiHong WANG , ZhiWei LI , et al. Internal multiple elimination method based on attention mechanism[J]. Progress in Geophysics. 2024, 39(4): 1474-1482 https://doi.org/10.6038/pg2024II0196

References

Bao P N , Shi Y , Wang W H . Surface-related and internal multiple elimination using deep learning. Energies, 2022, 15(11): 3883
Di H B , Li C , Smith S . Imposing interpretational constraints on a seismic interpretation convolutional neural network. Geophysics, 2021, 86(3): IM63 IM71
Hu L L , Zheng X D , Duan Y T . First-arrival picking with a U-net convolutional network. Geophysics, 2019, 84(6): U45-U57
Ma T L , Liu H Q , Liao H B . Fracture identification method combining channel and spatial cross attention. Progress in Geophysics, 2024, 39(2): 727-736
Qu S , Verschuur E , Zhang D . Training deep networks with only synthetic data: Deep-learning-based near-offset reconstruction for (closed-loop) surface-related multiple estimation on shallow-water field data. Geophysics, 2021, 86(3): A39-A43
Ross C P , Cole D M . A comparison of popular neural network facies-classification schemes. The Leading Edge, 2017, 36(4): 340-349
Song H , Mao W J , Tang H H . Application of deep neural networks for multiples attenuation. Chinese Journal of Geophysics, 2021, 64(8): 2795-2808
Vrolijk J W , Blacquière G . Source deghosting of coarsely sampled common-receiver data using a convolutional neural network. Geophysics, 2021, 86(3): V185-V196
Wang L L , Du G X , Shi Y . Research on automatic recognition method of 2D seismic fault based on MultiResAttUnet network. Progress in Geophysics, 2023, 38(5): 2160-2171
Wang S W , Song P , Tan J . The least-squares reverse time migration with gradient optimization based on QHAdam. Chinese Journal of Geophysics, 2022, 65(7): 2673-2680
Xu T E , Zhou H L , Liu X Y . Seismic facies identification based on Res-Unet and transfer learning. Progress in Geophysics, 2024, 39(1): 319-333
Yang L Q , Chen W , Wang H . Deep learning seismic random noise attenuation via improved residual convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(9): 7968-7981
Yu S W , Ma J W , Wang W L . Deep learning for denoising. Geophysics, 2019, 84(6): V333-V350
Yuan P Y , Wang S R , Hu W Y . A robust first-arrival picking workflow using convolutional and recurrent neural networks. Geophysics, 2020, 85(5): U109-U119
Zhang W , Gao J H . Deep-learning full-waveform inversion using seismic migration images. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60 5901818
Zhang Z H , Yao Y , Shi Z Y . Deep learning for potential field edge detection. Chinese Journal of Geophysics, 2022, 65(5): 1785-1801
同乐 , 红岐 , 海博 . 融合通道和空间交叉注意力的裂缝识别方法. 地球物理学进展, 2024, 39(2): 727-736
, 伟建 , 欢欢 . 基于深层神经网络压制多次波. 地球物理学报, 2021, 64(8): 2795-2808
莉利 , 功鑫 , . 基于MultiResAttUnet网络的二维地震断层自动识别方法研究. 地球物理学进展, 2023, 38(5): 2160-2171
绍文 , , . 基于QHAdam梯度优化算法的最小二乘逆时偏移. 地球物理学报, 2022, 65(7): 2673-2680
天恩 , 怀来 , 兴业 . 基于Res-Unet与迁移学习的地震相识别. 地球物理学进展, 2024, 39(1): 319-333
志厚 , , 泽玉 . 基于深度学习的位场边界识别方法. 地球物理学报, 2022, 65(5): 1785-1801

感谢审稿专家提出的修改意见和编辑部的大力支持!

RIGHTS & PERMISSIONS

Copyright ©2024 Progress in Geophysics. All rights reserved.
PDF(3717 KB)

Accesses

Citation

Detail

Sections
Recommended

/