Re-visible blind block network: An unsupervised seismic data random noise attenuation method

IF 1.8 3区 地球科学 Q3 GEOCHEMISTRY & GEOPHYSICS Geophysical Prospecting Pub Date : 2024-07-17 DOI:10.1111/1365-2478.13559
Jing Wang, Bangyu Wu, Hui Yang, Bo Li
{"title":"Re-visible blind block network: An unsupervised seismic data random noise attenuation method","authors":"Jing Wang,&nbsp;Bangyu Wu,&nbsp;Hui Yang,&nbsp;Bo Li","doi":"10.1111/1365-2478.13559","DOIUrl":null,"url":null,"abstract":"<p>Noise is inevitable when acquiring seismic data, and effective random noise attenuation is crucial for seismic data processing and interpretation. Training and inferencing two-stage deep learning-based denoising methods typically require massive noisy–clean or noisy–noisy pairs to train the network. In this paper, we propose an unsupervised seismic data denoising framework called a re-visible blind block network. It is a training-as-inferencing one-stage method and utilizes only single noisy data for denoising, thereby eliminating the effort to prepare training data pairs. First, we introduce a global masker and a corresponding mask mapper to obtain the denoised result containing all blind block information, enabling simultaneous optimization of all blind blocks via the loss function. The global masker consists of two complementary block-wise masks. It is utilized to mask noisy data to obtain two corrupted data, which are then input into the denoising network for noise attenuation. The mask mapper samples the value of blind blocks in the denoised data and projects it onto the same channel to gather the denoised results of all blind blocks together. Second, the original noisy data are incorporated into the network training process to prevent information loss, and a hybrid loss function is employed for updating the network parameters. Synthetic and field seismic data experiments demonstrate that our proposed method can protect seismic signals while suppressing random noise compared with traditional methods and several state-of-the-art unsupervised deep learning denoising techniques.</p>","PeriodicalId":12793,"journal":{"name":"Geophysical Prospecting","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geophysical Prospecting","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/1365-2478.13559","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
引用次数: 0

Abstract

Noise is inevitable when acquiring seismic data, and effective random noise attenuation is crucial for seismic data processing and interpretation. Training and inferencing two-stage deep learning-based denoising methods typically require massive noisy–clean or noisy–noisy pairs to train the network. In this paper, we propose an unsupervised seismic data denoising framework called a re-visible blind block network. It is a training-as-inferencing one-stage method and utilizes only single noisy data for denoising, thereby eliminating the effort to prepare training data pairs. First, we introduce a global masker and a corresponding mask mapper to obtain the denoised result containing all blind block information, enabling simultaneous optimization of all blind blocks via the loss function. The global masker consists of two complementary block-wise masks. It is utilized to mask noisy data to obtain two corrupted data, which are then input into the denoising network for noise attenuation. The mask mapper samples the value of blind blocks in the denoised data and projects it onto the same channel to gather the denoised results of all blind blocks together. Second, the original noisy data are incorporated into the network training process to prevent information loss, and a hybrid loss function is employed for updating the network parameters. Synthetic and field seismic data experiments demonstrate that our proposed method can protect seismic signals while suppressing random noise compared with traditional methods and several state-of-the-art unsupervised deep learning denoising techniques.

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
再可见盲块网络:一种无监督地震数据随机噪声衰减方法
在获取地震数据时,噪声是不可避免的,有效的随机噪声衰减对地震数据处理和解释至关重要。基于深度学习的两阶段去噪方法的训练和推理通常需要大量的噪声-清洁或噪声-噪声对来训练网络。在本文中,我们提出了一种无监督地震数据去噪框架,称为重可见盲块网络。它是一种训练即推理的单阶段方法,只利用单个噪声数据进行去噪,从而省去了准备训练数据对的工作。首先,我们引入了全局掩码器和相应的掩码映射器,以获得包含所有盲区信息的去噪结果,从而通过损失函数同时优化所有盲区。全局掩码器由两个互补的区块掩码组成。它用于屏蔽噪声数据,以获得两个损坏数据,然后将其输入去噪网络进行噪声衰减。掩码映射器对去噪数据中盲区块的值进行采样,并将其投射到同一通道上,从而将所有盲区块的去噪结果集合在一起。其次,将原始噪声数据纳入网络训练过程,以防止信息丢失,并采用混合损失函数更新网络参数。合成和野外地震数据实验证明,与传统方法和几种最先进的无监督深度学习去噪技术相比,我们提出的方法能在抑制随机噪声的同时保护地震信号。
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
Geophysical Prospecting
Geophysical Prospecting 地学-地球化学与地球物理
CiteScore
4.90
自引率
11.50%
发文量
118
审稿时长
4.5 months
期刊介绍: Geophysical Prospecting publishes the best in primary research on the science of geophysics as it applies to the exploration, evaluation and extraction of earth resources. Drawing heavily on contributions from researchers in the oil and mineral exploration industries, the journal has a very practical slant. Although the journal provides a valuable forum for communication among workers in these fields, it is also ideally suited to researchers in academic geophysics.
期刊最新文献
Issue Information Simultaneous inversion of four physical parameters of hydrate reservoir for high accuracy porosity estimation A mollifier approach to seismic data representation Analytic solutions for effective elastic moduli of isotropic solids containing oblate spheroid pores with critical porosity An efficient pseudoelastic pure P-mode wave equation and the implementation of the free surface boundary condition
×
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