Deblending of multi-source Seismic Data Based on Dual-Element Attention Mechanism Network

Zhe Zhou

doi:10.47297/wspeiWSP2516-253509.20250901

PDF
Export
Share
Collection
Album

Deblending of multi-source Seismic Data Based on Dual-Element Attention Mechanism Network

Volume 9, Issue 1

Views: 0 Downloads: 0

Deblending of multi-source Seismic Data Based on Dual-Element Attention Mechanism Network
Deblending of multi-source Seismic Data Based on Dual-Element Attention Mechanism Network
School of Geophysics and Oil Recourses, Yangtze University, Wuhan, Hubei 430100, China
Vol. 9, Issue 1, Pages: 44-49(2025)
Published：25 February 2025
DOI：10.47297/wspeiWSP2516-253509.20250901
Accepted：

Scan QR Code

Zhou Zhe.Deblending of multi-source Seismic Data Based on Dual-Element Attention Mechanism Network[J].Entrepreneurship and Innovation,2025,09(01):44-49.
DOI：

Zhou Zhe.Deblending of multi-source Seismic Data Based on Dual-Element Attention Mechanism Network[J].Entrepreneurship and Innovation,2025,09(01):44-49. DOI： 10.47297/wspeiWSP2516-253509.20250901.

摘要

Abstract

The high-density blended acquisition technology effectively improves the acquisition efficiency in seismic exploration

but it requires addressing the aliasing problem of its acquired data

known as the deblending problem. Among numerous deblending methods

deep learning-based denoising has gained increasing attention and research from scholars in recent years due to its efficiency in handling complex aliased data and the advantage of not requiring manual adjustment of numerous parameters. Given the complexity of blended data and the correlation between source signals

a DeamNet network incorporating a Dual-Element Attention Mechanism is proposed to achieve blended data separation. This Dual-Element Attention Mechanism can effectively extract the features of blended data for complex multi-source blended datasets

allowing for the retention of more valid signals during deblending

facilitating subsequent imaging processing. To verify the deblending performance of the DeamNet network

numerical experiments were conducted using both synthetic and real data

and its performance was compared with DnCNN and U-Net

both of which have also been applied in the deblending field in recent years. The final comparison results confirmed the effectiveness of the DeamNet network in deblending.

关键词

Keywords

references

Cheng J , Liu C , Zhou L , Chen W and Gu H , " Deblending of Simultaneous-Source Seismic Data Based on Deep Convolutional Neural Network ," in IEEE Transactions on Geoscience and Remote Sensing , vol. 60 , pp. 1 - 13 , 2022, Art no. 5912613, doi: 10.1109/TGRS.2022.3153642 http://dx.doi.org/10.1109/TGRS.2022.3153642 .

Wang K , Hu T , and Wang S . Iterative deblending using unsupervised learning with double-deep neural networks . GEOPHYSICS 2023 88 : 3 , V187-V205.

Zu S , Cao J , Qu S , et al . Iterative deblending for simultaneous source data using the deep neural network [J ] . Geophysics , 2020 , 85 . DOI: 10.1190/geo2019-0319.1 http://dx.doi.org/10.1190/geo2019-0319.1 .

Sun J , Hou S , Vinje V , et al . Deep learning-based shot-domain seismic deblending [J ] . Geophysics: Journal of the Society of Exploration Geophysicists , 2022 ( 3 ): 87 .

Dai W. , Wang X. , & Schuster G . T . ( 2011 ). Least-squares migration of multisource data with a deblurring filter. Geophysics , 76 ( 5 ), R135 - R146 .

Wang H. C. , Chen S. C. , Zhang B. , et al. , 2013 . Separation method for multi-source blended seismic data : Applied Geophysics , 10 ( 3 ), 251 - 264 .

Lu X. T. , Han L. G. , Zhang P. , et al. , 2015 , Direct migration method of multi-source blended data based on total variation: Chinese J . Geophys. in Chinese , 58 ( 9 ), 3335 - 3345 .

Wang H. C. , Chen S. C. , Chen G. X. , et al. , 2014 . Migration methods for blended seismic data of multi-source: Chinese J . Geophys. in Chinese , 57 ( 3 ), 918 - 931 .

Chen Y , Bai M , Zhou T , Zhang Q , Wang Y , and Chen H . Substituting smoothing with low-rank decomposition — Applications to least-squares reverse time migration of simultaneous source and incomplete seismic data . GEOPHYSICS 2019 84 : 4 , S267 - S283 .

Shi Taikun , Xu Hai , Huang Liang , etc . Research progress of high-efficiency and high-precision separation and processing methods for mixed mining seismic data [J ] . Petroleum geophysical exploration , 2020 , 59 ( 05 ): 703 - 712+743 .

WANG W C , LI H Q , ZHAO B , et al . Suppression of crosstalk from simultaneous sources with alphatrimmed vector median filtering [J ] . Oil Geophysical Prospecting , 2014 , 49 ( 6 ): 1061 - 1067 .

ZHOU L , ZHUANG Z , CHENG J W , et al . Multi-source blended wavefield separation for marine seismic based on an adaptive iterative multi-level median filtering [J ] . Oil Geophysical Prospecting , 2016 , 51 ( 3 ): 434 - 443 .

Chen S , Cao S , Sun Y . Deblending based on the frequency-structure weighted threshold: The case of the slope-constrained f-k transform [J ] . GEOPHYSICS , 2021 . DOI: 10.1190/geo2021-0095.1 http://dx.doi.org/10.1190/geo2021-0095.1 .

Yang Xixi , Zhang Hua , Wu Zhaoqi , et al . Multi-source seismic data separation based on curvelet transform and fast exponential threshold iteration [J ] . Science, technology and engineering , 2024 , 24 ( 13 ): 5296 - 5303 .

Chen Y , Fomel S , and Hu J . Iterative deblending of simultaneous-source seismic data using seislet-domain shaping regularization . GEOPHYSICS 2014 79 : 5 , V179-V189.

Zhu Lihua . Data separation technology of multi-source seismic mixed acquisition based on sparse inversion [J ] . Petroleum geophysical exploration , 2018 , 57 ( 02 ): 208 - 212 .

Zhang Xianna , Han Liguo , Liu Qiang , et al . Study on wave field separation method of three-dimensional multi-source mixed acquisition data [J ] . Science, technology and engineering , 2017 , 17 ( 05 ): 147 - 151 .

Wang B , Li J , Luo J , et al . Intelligent Deblending of Seismic Data Based on U-Net and Transfer Learning [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2021 , PP( 99 ): 1 - 10 . DOI: 10.1109/TGRS.2020.3048746 http://dx.doi.org/10.1109/TGRS.2020.3048746 .

Wang S , Hu W , Hu Y , et al . A physics-augmented deep learning method for seismic data deblending [C ] . SEG Technical Program Expanded Abstracts 2020 . 2020 . DOI: 10.1190/segam2020-w13-07.1 http://dx.doi.org/10.1190/segam2020-w13-07.1 .

Sun J , Slang S , Elboth T , et al . A convolutional neural network approach to deblending seismic data [J ] . Geophysics , 2019 , 85 ( 4 ): 1 - 57 . DOI: 10.1190/geo2019-0173.1 http://dx.doi.org/10.1190/geo2019-0173.1 .

Wang B , Li J , Han D , et al . Deblending and recovery of incomplete blended data via MultiResUnet [J ] . Surveys in Geophysics , 2022 , 43 ( 6 ): 1901 - 1927 .

Ren C , He X , Wang C and Zhao Z , "Adaptive Consistency Prior based Deep Network for Image Denoising," 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Nashville , TN , USA , 2021 , pp. 8592 - 8602 , doi: 10.1109/CVPR46437.2021.00849 http://dx.doi.org/10.1109/CVPR46437.2021.00849 .

Wang S et al , " A Self-Supervised Deep Learning Method for Seismic Data Deblending Using a Blind-Trace Network ," in IEEE Transactions on Neural Networks and Learning Systems , vol. 34 , no. 7 , pp. 3405 - 3414 , July 2023, doi: 10.1109/TNNLS.2022.3188915 http://dx.doi.org/10.1109/TNNLS.2022.3188915 .

Xu W , Zhou Y , Liu Y , Wang X and Chen W , " Seismic Intelligent Deblending via Plug and Play Method With Blended CSGs Trained Deep CNN Gaussian Denoiser ," in IEEE Transactions on Geoscience and Remote Sensing , vol. 60 , pp. 1 - 13 , 2022, Art no. 5913413, doi: 10.1109/TGRS.2022.3166029 http://dx.doi.org/10.1109/TGRS.2022.3166029 .

Richardson A , Feller C . Seismic data denoising and deblending using deep learning [J ] . 2019 . DOI: 10.48550/arXiv.1907.01497 http://dx.doi.org/10.48550/arXiv.1907.01497 .

Wang , K , Mao , W , Song , H . & Evinemi, E .I. ( 2023 ) A multi-data training method for a deep neural network to improve the separation effect of simultaneous-source data. Geophysical Prospecting , 71, 63 – 84 . https://doi.org/10.1111/1365-2478.13276 https://doi.org/10.1111/1365-2478.13276

Alert me when the article has been cited

Submit

The spatiotemporal attention logging parameter prediction model based on historical feature separation of prior knowledge

Related Author

Chenguang Zhu College of Geophysics and Petroleum Resources Yangtze University

Related Institution

College of Geophysics and Petroleum Resources Yangtze University

⁰