A convolutional neural network approach to deblending seismic data

Jing Sun, Sigmund Slang, Thomas Elboth, Thomas Larsen Greiner, Steven McDonald, Leiv-J Gelius
{"title":"A convolutional neural network approach to deblending seismic data","authors":"Jing Sun, Sigmund Slang, Thomas Elboth, Thomas Larsen Greiner, Steven McDonald, Leiv-J Gelius","doi":"arxiv-2409.07930","DOIUrl":null,"url":null,"abstract":"For economic and efficiency reasons, blended acquisition of seismic data is\nbecoming more and more commonplace. Seismic deblending methods are always\ncomputationally demanding and normally consist of multiple processing steps.\nBesides, the parameter setting is not always trivial. Machine learning-based\nprocessing has the potential to significantly reduce processing time and to\nchange the way seismic deblending is carried out. We present a data-driven deep\nlearning-based method for fast and efficient seismic deblending. The blended\ndata are sorted from the common source to the common channel domain to\ntransform the character of the blending noise from coherent events to\nincoherent distributions. A convolutional neural network (CNN) is designed\naccording to the special character of seismic data, and performs deblending\nwith comparable results to those obtained with conventional industry deblending\nalgorithms. To ensure authenticity, the blending was done numerically and only\nfield seismic data were employed, including more than 20000 training examples.\nAfter training and validation of the network, seismic deblending can be\nperformed in near real time. Experiments also show that the initial signal to\nnoise ratio (SNR) is the major factor controlling the quality of the final\ndeblended result. The network is also demonstrated to be robust and adaptive by\nusing the trained model to firstly deblend a new data set from a different\ngeological area with a slightly different delay time setting, and secondly\ndeblend shots with blending noise in the top part of the data.","PeriodicalId":501270,"journal":{"name":"arXiv - PHYS - Geophysics","volume":"17 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-2409.07930","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

For economic and efficiency reasons, blended acquisition of seismic data is becoming more and more commonplace. Seismic deblending methods are always computationally demanding and normally consist of multiple processing steps. Besides, the parameter setting is not always trivial. Machine learning-based processing has the potential to significantly reduce processing time and to change the way seismic deblending is carried out. We present a data-driven deep learning-based method for fast and efficient seismic deblending. The blended data are sorted from the common source to the common channel domain to transform the character of the blending noise from coherent events to incoherent distributions. A convolutional neural network (CNN) is designed according to the special character of seismic data, and performs deblending with comparable results to those obtained with conventional industry deblending algorithms. To ensure authenticity, the blending was done numerically and only field seismic data were employed, including more than 20000 training examples. After training and validation of the network, seismic deblending can be performed in near real time. Experiments also show that the initial signal to noise ratio (SNR) is the major factor controlling the quality of the final deblended result. The network is also demonstrated to be robust and adaptive by using the trained model to firstly deblend a new data set from a different geological area with a slightly different delay time setting, and secondly deblend shots with blending noise in the top part of the data.
卷积神经网络去叠加地震数据的方法
出于经济和效率方面的考虑,地震数据的混合采集越来越普遍。地震除错方法对计算要求一直很高,通常包括多个处理步骤。基于机器学习的处理方法有可能大大缩短处理时间,并改变地震排错的方式。我们提出了一种基于数据驱动的深度学习方法,用于快速高效的地震排错。混合数据从共源域到共道域进行排序,将混合噪声的特征从相干事件转变为不相干分布。根据地震数据的特殊性设计了一个卷积神经网络(CNN),其去噪效果与传统工业去噪算法相当。为确保其真实性,混合是通过数值方法完成的,并且只采用了野外地震数据,包括超过 20000 个训练实例。实验还表明,初始信号信噪比(SNR)是控制最终排错结果质量的主要因素。通过使用训练有素的模型,首先对来自不同地质区域、延迟时间设置略有不同的新数据集进行排错,其次对数据顶部有混合噪声的镜头进行排错,也证明了该网络的鲁棒性和适应性。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信