A two-stage seismic data denoising network based on deep learning

IF 0.5 4区 地球科学 Q4 GEOCHEMISTRY & GEOPHYSICS Studia Geophysica et Geodaetica Pub Date : 2024-06-08 DOI:10.1007/s11200-023-0320-8
Yan Zhang, Chi Zhang, Liwei Song
{"title":"A two-stage seismic data denoising network based on deep learning","authors":"Yan Zhang,&nbsp;Chi Zhang,&nbsp;Liwei Song","doi":"10.1007/s11200-023-0320-8","DOIUrl":null,"url":null,"abstract":"<div><p>Seismic data with a high signal-to-noise ratio is beneficial in the inversion and interpretation. Thus, denoising is an indispensable step in the seismic data processing. Traditional denoising methods based on prior knowledge are susceptible to the influence of the hypothesis model and parameters. In contrast, deep learning-based denoising methods can extract deep features from the data autonomously and generate a sophisticated denoising model through adaptive learning. However, these methods generally learn a specific model for each noise level, which results in poor representation ability and suboptimal denoising efficacy when applied to seismic data with different noise levels. To address this issue, we propose a denoising method based on a two-stage convolutional neural network (TSCNN). The TSCNN comprises an estimation subnet (ES) and a denoising subnet (DS). The ES employs a multilayer CNN to estimate noise levels, and the DS performs noise suppression on noisy seismic data based on the ES estimation of the noise distribution. In addition, attention mechanisms are implemented in the proposed network to efficiently extract noise information hidden in complex backgrounds. The TSCNN also adopts the L<sub>1</sub> loss function to enhance the generalization ability and denoising outcome of the model, and a residual learning scheme is utilized to solve the problem of network degradations. Experimental results demonstrate that the proposed method can preserve event features more accurately and outperforms existing methods in terms of signal-to-noise ratio and generalization ability.</p></div>","PeriodicalId":22001,"journal":{"name":"Studia Geophysica et Geodaetica","volume":null,"pages":null},"PeriodicalIF":0.5000,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Studia Geophysica et Geodaetica","FirstCategoryId":"89","ListUrlMain":"https://link.springer.com/article/10.1007/s11200-023-0320-8","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
引用次数: 0

Abstract

Seismic data with a high signal-to-noise ratio is beneficial in the inversion and interpretation. Thus, denoising is an indispensable step in the seismic data processing. Traditional denoising methods based on prior knowledge are susceptible to the influence of the hypothesis model and parameters. In contrast, deep learning-based denoising methods can extract deep features from the data autonomously and generate a sophisticated denoising model through adaptive learning. However, these methods generally learn a specific model for each noise level, which results in poor representation ability and suboptimal denoising efficacy when applied to seismic data with different noise levels. To address this issue, we propose a denoising method based on a two-stage convolutional neural network (TSCNN). The TSCNN comprises an estimation subnet (ES) and a denoising subnet (DS). The ES employs a multilayer CNN to estimate noise levels, and the DS performs noise suppression on noisy seismic data based on the ES estimation of the noise distribution. In addition, attention mechanisms are implemented in the proposed network to efficiently extract noise information hidden in complex backgrounds. The TSCNN also adopts the L1 loss function to enhance the generalization ability and denoising outcome of the model, and a residual learning scheme is utilized to solve the problem of network degradations. Experimental results demonstrate that the proposed method can preserve event features more accurately and outperforms existing methods in terms of signal-to-noise ratio and generalization ability.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于深度学习的两级地震数据去噪网络
信噪比高的地震数据有利于反演和解释。因此,去噪是地震数据处理中不可或缺的一步。传统的基于先验知识的去噪方法容易受到假设模型和参数的影响。相比之下,基于深度学习的去噪方法可以自主地从数据中提取深层特征,并通过自适应学习生成复杂的去噪模型。然而,这些方法通常会针对每种噪声水平学习特定的模型,这就导致在应用于不同噪声水平的地震数据时,表征能力较差,去噪效果不理想。为解决这一问题,我们提出了一种基于两级卷积神经网络(TSCNN)的去噪方法。TSCNN 包括一个估计子网 (ES) 和一个去噪子网 (DS)。ES 采用多层 CNN 估算噪声水平,DS 根据 ES 估算的噪声分布对噪声地震数据进行噪声抑制。此外,该网络还采用了注意力机制,以有效提取隐藏在复杂背景中的噪声信息。TSCNN 还采用 L1 损失函数来增强模型的泛化能力和去噪结果,并利用残差学习方案来解决网络退化问题。实验结果表明,所提出的方法能更准确地保留事件特征,在信噪比和泛化能力方面优于现有方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Studia Geophysica et Geodaetica
Studia Geophysica et Geodaetica 地学-地球化学与地球物理
CiteScore
1.90
自引率
0.00%
发文量
8
审稿时长
6-12 weeks
期刊介绍: Studia geophysica et geodaetica is an international journal covering all aspects of geophysics, meteorology and climatology, and of geodesy. Published by the Institute of Geophysics of the Academy of Sciences of the Czech Republic, it has a long tradition, being published quarterly since 1956. Studia publishes theoretical and methodological contributions, which are of interest for academia as well as industry. The journal offers fast publication of contributions in regular as well as topical issues.
期刊最新文献
Present-day crustal deformation based on an interpolated GPS velocity field in the collision zone of the Arabia-Eurasia tectonic plates Effect of the 2021 Cumbre Vieja eruption on precipitable water vapor and atmospheric particles analysed using GNSS and remote sensing Geophysical structure of a local area in the lunar Oceanus Procellarum region investigated using the gravity gradient method Estimation of the minimal detectable horizontal acceleration of GNSS CORS The area of rhumb polygons
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1