{"title":"DNN-based workflow for attenuating seismic interference noise and its application to marine towed streamer data from the Northern Viking Graben","authors":"Jing Sun, Song Hou, Alaa Triki","doi":"arxiv-2409.07890","DOIUrl":null,"url":null,"abstract":"To separate seismic interference (SI) noise while ensuring high signal\nfidelity, we propose a deep neural network (DNN)-based workflow applied to\ncommon shot gathers (CSGs). In our design, a small subset of the entire\nto-be-processed data set is first processed by a conventional algorithm to\nobtain an estimate of the SI noise (from now on called the SI noise model). By\nmanually blending the SI noise model with SI-free CSGs and a set of simulated\nrandom noise, we obtain training inputs for the DNN. The SI-free CSGs can be\neither real SI-free CSGs from the survey or SI-attenuated CSGs produced in\nparallel with the SI noise model from the conventional algorithm depending on\nthe specific project. To enhance the DNN's output signal fidelity, adjacent\nshots on both sides of the to-be-processed shot are used as additional channels\nof the input. We train the DNN to output the SI noise into one channel and the\nSI-free shot along with the intact random noise into another. Once trained, the\nDNN can be applied to the entire data set contaminated by the same types of SI\nin the training process, producing results efficiently. For demonstration, we\napplied the proposed DNN-based workflow to 3D seismic field data acquired from\nthe Northern Viking Graben (NVG) of the North Sea, and compared it with a\nconventional algorithm. The studied area has a challenging SI contamination\nproblem with no sail lines free from SI noise during the acquisition. The\ncomparison shows that the proposed DNN-based workflow outperformed the\nconventional algorithm in processing quality with less noise residual and\nbetter signal preservation. This validates its feasibility and value for real\nprocessing projects.","PeriodicalId":501270,"journal":{"name":"arXiv - PHYS - Geophysics","volume":"63 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Geophysics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07890","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
To separate seismic interference (SI) noise while ensuring high signal
fidelity, we propose a deep neural network (DNN)-based workflow applied to
common shot gathers (CSGs). In our design, a small subset of the entire
to-be-processed data set is first processed by a conventional algorithm to
obtain an estimate of the SI noise (from now on called the SI noise model). By
manually blending the SI noise model with SI-free CSGs and a set of simulated
random noise, we obtain training inputs for the DNN. The SI-free CSGs can be
either real SI-free CSGs from the survey or SI-attenuated CSGs produced in
parallel with the SI noise model from the conventional algorithm depending on
the specific project. To enhance the DNN's output signal fidelity, adjacent
shots on both sides of the to-be-processed shot are used as additional channels
of the input. We train the DNN to output the SI noise into one channel and the
SI-free shot along with the intact random noise into another. Once trained, the
DNN can be applied to the entire data set contaminated by the same types of SI
in the training process, producing results efficiently. For demonstration, we
applied the proposed DNN-based workflow to 3D seismic field data acquired from
the Northern Viking Graben (NVG) of the North Sea, and compared it with a
conventional algorithm. The studied area has a challenging SI contamination
problem with no sail lines free from SI noise during the acquisition. The
comparison shows that the proposed DNN-based workflow outperformed the
conventional algorithm in processing quality with less noise residual and
better signal preservation. This validates its feasibility and value for real
processing projects.
为了在分离地震干扰(SI)噪声的同时确保高信号保真度,我们提出了一种基于深度神经网络(DNN)的工作流程,应用于普通震源采集(CSG)。在我们的设计中,首先用传统算法处理整个待处理数据集的一小部分,以获得 SI 噪声的估计值(以下称为 SI 噪声模型)。通过将 SI 噪声模型与无 SI CSG 和一组模拟随机噪声进行手动混合,我们获得了 DNN 的训练输入。无 SI CSG 可以是来自调查的真实无 SI CSG,也可以是与传统算法的 SI 噪声模型并行生成的 SI 减弱 CSG,具体取决于具体项目。为了提高 DNN 输出信号的保真度,待处理镜头两侧的邻近镜头被用作额外的输入通道。我们训练 DNN 将 SI 噪声输出到一个通道,将无 SI 的镜头和完整的随机噪声输出到另一个通道。训练完成后,DNN 即可应用于受训练过程中相同类型 SI 污染的整个数据集,从而高效地生成结果。为了进行演示,我们将所提出的基于 DNN 的工作流程应用于从北海北维京海湾(NVG)获取的三维地震现场数据,并与传统算法进行了比较。研究区域的 SI 污染问题极具挑战性,在采集过程中没有一条帆线不受 SI 噪声的影响。比较结果表明,所提出的基于 DNN 的工作流程在处理质量上优于传统算法,噪声残留更少,信号保存更好。这验证了它在实际处理项目中的可行性和价值。