基于交互注意力分解融合的地震速度建模

doi:10.3969/j.issn.1006-2475.2025.01.002

摘要/Abstract

摘要： 地震波传播速度参数贯穿于整个地震勘探过程，对于地震成像至关重要。传统的地震速度建模方法存在计算效率低等问题，本文提出一种基于交互注意力分解融合的地震速度建模网络，即IADMU模型。本文网络提出分解融合卷积（DMUC）和交互注意力模块（IAB）这2个组件。原始地震炮记录经过分解融合卷积模块，从全局和局部维度提取其高级特征信息，送入反卷积和交互注意力模块，在跨通道交互的帮助下，预测对应的速度模型。在模拟数据和SEG salt data数据集上进行大量实验，消融实验验证了本文提出的DMUC和IAB的有效性；对比实验结果显示，相比U-Net、Res-UNet和DeepLabV3网络，本文网络在这2种数据集上都有更好的性能，验证了本文所提网络的优越性。

关键词: 地震速度建模, 分解融合, 交互注意力, 跨通道交互

Abstract: The velocity parameter of seismic wave runs through the whole seismic exploration process and is very important for seismic imaging. Due to the low computational efficiency of traditional seismic velocity building methods， this paper proposes a seismic velocity building based on interaction attention DeMulti unite， namely IADMU model. Two parts of the network are proposed: DeMulti Unite Convolution （DMUC） and Interactive Attention Block（IAB）. The original seismic shot record passes through the DMUC to extract its advanced feature information from the global and local dimensions. The deconvolution and interactive attention modules are then fed to directly predict the corresponding velocity models with the help of cross-channel interactions. This paper conducts a lot of experiments on simulated data and SEG salt data sets， ablation experiment proves the effectiveness of the proposed DMUC and IAB； Comparative experiments demonstrated that， compared to U-Net， Res-UNet， and DeepLabV3 networks， this network exhibited superior performance on both datasets， validating the superiority of the proposed network in this paper.

Key words: seismic velocity building, DeMulti unite, interaction attention, cross-channel interactions ,

中图分类号:

TP391

李灿伟, 吴春雷, 路静, 王春霖, 朱明飞. 基于交互注意力分解融合的地震速度建模[J]. 计算机与现代化, 2025, 0(01): 7-14.

LI Canwei, WU Chunlei, LU Jing, WANG Chunlin, ZHU Mingfei. Seismic Velocity Building Based on Interactive Attention DeMulti Unite [J]. Computer and Modernization, 2025, 0(01): 7-14.

参考文献

［1］ ZHANG C， FROGNER C， ARAYA-POLO M， et al. Machine
-learning based automated fault detection in seismic traces［C］// The 76th EAGE Conference and Exhibition 2014. EAGE， 2014:1-5.
［2］ EVGENIOU T， PONTIL M， POGGIO T. Regularization networks and support vector machines［J］. Advances in Computational Mathematics， 2000，13:1-50.
［3］ WANG W L， YANG F S， MA J W. Automatic salt detection with machine learning［C］// The 80th EAGE Conference and Exhibition 2018. EAGE， 2018:1-5.
［4］ LAILLY P. The seismic inverse problem as a sequence of before stack migrations ［C］// Conference on Inverse Scattering， Theory and Applications. SIAM， 1983:206-220.
［5］ NOWACK R L， AKI K. Iterative inversion for velocity using waveform data［J］. Geophysical Journal International， 1986，87（3）:701-730.
［6］ MORA P. Nonlinear two-dimensional elastic inversion of multioffset seismic data［J］. Geophysics， 1987，52（9）:1211-1228.
［7］ MORA P. Inversion = migration + tomography［J］. Geophysics， 1989，54（12）:1575-1586.
［8］ SEN M K， STOFFA P L. Nonlinear one-dimensional seismic waveform inversion using simulated annealing［J］. Geophysics， 1991，56（10）:1624-1638.
［9］ BUNKS C， SALECK F M， ZALESKI S， et al. Multiscale seismic waveform inversion［J］. Geophysics， 1995，60（5）:1457-1473.
［10］张生强，刘春成，韩立国，等. 基于 L-BFGS 算法和同时激发震源的频率多尺度全波形反演［J］.吉林大学学报（地球科学版）， 2013，43（3）:1004-1012.
［11］ RÖTH G， TARANTOLA A. Neural networks and inversion of seismic data［J］. Journal of Geophysical Research: Solid Earth， 1994，99（B4）:6753-6768.
［12］ MOSSER L， DUBRULE O， BLUNT M J. Stochastic seismic waveform inversion using generative adversarial networks as a geological prior［J］. Mathematical Geosciences， 2020，52:53-79.
［13］ RICHARDSON A. Generative adversarial networks for model order reduction in seismic full-waveform inversion［J］. arXiv preprint arXiv:1806.00828， 2018.
［14］ ARAYA-POLO M， JENNINGS J， ADLER A， et al. Deep-learning tomography［J］. The Leading Edge， 2018，37（1）:58-66.
［15］ YANG F S， MA J W. Deep-learning inversion: A next-generation seismic velocity model building method［J］. Geophysics， 2019，84（4）:R583-R599.
［16］ WU Y， LIN Y Z. InversionNet: A real-time and accurate full waveform inversion with CNNs and continuous CRFs［J］. arXiv preprint arXiv:1811.07875， 2018.
［17］ WANG W L， MA J W. Velocity model building in a crosswell acquisition geometry with image-trained artificial neural networks ［J］. Geophysics， 2020，85（2）:U31-U46.
［18］ ZHANG Z P， LIN Y Z. Data-driven seismic waveform inversion: A study on the robustness and generalization［J］. IEEE Transactions on Geoscience and Remote sensing， 2020，58（10）:6900-6913.
［19］ LI S C， LIU B， REN Y X， et al. Deep-learning inversion of seismic data［J］. arXiv preprint arXiv:1901.07733， 2019.
［20］ LIU B， YANG S L， REN Y X， et al. Deep-learning seismic full-waveform inversion for realistic structural models［J］. Geophysics， 2021，86（1）:R31-R44.
［21］ REN Y X， XU X J， YANG S L， et al. A physics-based neural-network way to perform seismic full waveform inversion［J］. IEEE Access， 2020，8:112266-112277.
［22］ GENG Z C， ZHAO Z Y， SHI Y Z， et al. Deep learning for velocity model building with common-image gather volumes［J］. Geophysical Journal International， 2022，228（2）:1054-1070.
［23］ ZHANG Z D， ALKHALIFAH T. Regularized elastic full-waveform inversion using deep learning［M］// Advances in Subsurface Data Analytics. Elsevier， 2022:219-250.
［24］ YANG S L， ALKHALIFAH T， REN Y X， et al. Well-log information-assisted high-resolution waveform inversion based on deep learning［J］. IEEE Geoscience and Remote Sensing Letters， 2023，20. DOI: 10.1109/LGRS.2023.3234211.
［25］ MULLER A P O， BOM C R， COSTA J C， et al. Deep-Tomography: Iterative velocity model building with deep learning［J］. Geophysical Journal International， 2023，232（2）:975-989.
［26］ LIU B， JIANG P， WANG Q Y， et al. Physics-driven self-supervised learning system for seismic velocity inversion［J］. Geophysics， 2023，88（2）:R145-R161.
［27］ PÉREZ C H B， LIU Y. Three-dimensional initial salt body building for full-waveform inversion assisted by deep learning［J］. IEEE Geo-science and Remote Sensing Letters， 2023，20. DOI: 10.1109/LGRS.2023.3287553.
［28］ RUSMANUGROHO H， LI J X， MUHAMMED M D D， et al. 3D velocity model building based upon hybrid neural network［C］// The 2nd International Meeting for Applied Geoscience & Energy. Society of Exploroction Geephysicists， 2022. DOI: 10.1190/image2022-3745433.1.
［29］董良国，马在田，曹景忠，等. 一阶弹性波方程交错网格高阶差分解法［J］. 地球物理学报， 2000，43（3）:411-419.
［30］ RONNEBERGER O， FISCHER P， BROX T. U-Net: Convolutional networks for biomedical image segmentation［C］// Proceedings of the 2015 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer， 2015:234-241.
［31］ DIAKOGIANNIS F I， WALDNER F， CACCETTA P， et al. ResUNet-a: A deep learning frame-work for semantic segmentation of remotely sensed data［J］. ISPRS Journal of Photo-grammetry and Remote Sensing， 2020，162:94-114.
［32］ CHEN L C， PAPANDREOU G， SCHROFF F， et al. Rethinking atrous convolution for semantic image segmentation［J］. arXiv preprint arXiv:1706.05587， 2017.