| 注册
首页|期刊导航|煤田地质与勘探|动校正域CNN法压制自由表面多次波

动校正域CNN法压制自由表面多次波

黄柱富 刘剑锋 方文倩 付丽华

煤田地质与勘探2024,Vol.52Issue(11):160-170,11.
煤田地质与勘探2024,Vol.52Issue(11):160-170,11.DOI:10.12363/issn.1001-1986.24.07.0482

动校正域CNN法压制自由表面多次波

Surfaced-related multiple attenuation using the CNN method in the NMO domain

黄柱富 1刘剑锋 1方文倩 1付丽华1

作者信息

  • 1. 中国地质大学(武汉)数学与物理学院,湖北 武汉 430074
  • 折叠

摘要

Abstract

[Objective]The presence of surface-related multiples results in a lower accuracy in seismic data interpreta-tions,and the effective multiple attenuation is a key step in seismic data processing.Multiples are coherent noise signals with similar characteristics to effective signals.It is difficult impossible to distinguish multiple signals from full-wave field data using a traditional convolutional neural network(CNN).Additionally,since the surface-related multiples vary significantly with surveyed areas,the CNN method will face more severe challenges when being transferred to other net-works.[Methods]This study developed a CNN method based on the normal moveout correction(NMO)domain by in-troducing physical priors.The CNN was trained using the differences in curvature characteristics between the primary waves and multiples in the NMO domain,aiming to achieve effective multiple identification and attenuation.The per-formance of this method was tested using simulations and practical data.[Results and Conclusions]Experimental res-ults indicate that the CNN trained in the NMO domain can effectively identify and attenuate multiples while protecting the reflected signals of primary waves.Compared to the traditional Radon algorithm,the proposed method exhibits re-duced manual parameter adjustments and calculation complexity,along with less leakage of effective signals.Compared to direct end-to-end CNN-based methods for surface-related multiple attenuation,the novel method is more adaptable to new data.The results of this study can provide a new philosophy for improving the accuracy of seismic data interpreta-tions and reducing the calculation cost.

关键词

自由表面多次波/卷积神经网络/动校正/相干噪声/多次波压制

Key words

surface-related multiples/convolutional neural network(CNN)/normal moveout correction(NMO)/coherent noise/multiple attenuation

分类

天文与地球科学

引用本文复制引用

黄柱富,刘剑锋,方文倩,付丽华..动校正域CNN法压制自由表面多次波[J].煤田地质与勘探,2024,52(11):160-170,11.

基金项目

国家自然科学基金项目(42274172) (42274172)

重庆市自然科学基金项目(2023NSCQ-MSX0207) (2023NSCQ-MSX0207)

广东省自然科学基金项目(2024A1515011680) (2024A1515011680)

煤田地质与勘探

OA北大核心CSTPCD

1001-1986

访问量0
|
下载量0
段落导航相关论文