利用卷积神经网络进行海洋地震数据的近偏移重建

IF 1.8 3区 地球科学 Q3 GEOCHEMISTRY & GEOPHYSICS
Owen Rohwer Huff, Vemund Stenbekk Thorkildsen, Thomas Larsen Greiner, Jan Erik Lie, Andreas Kjelsrud Evensen, Aina Juell Bugge, Jan Inge Faleide
{"title":"利用卷积神经网络进行海洋地震数据的近偏移重建","authors":"Owen Rohwer Huff,&nbsp;Vemund Stenbekk Thorkildsen,&nbsp;Thomas Larsen Greiner,&nbsp;Jan Erik Lie,&nbsp;Andreas Kjelsrud Evensen,&nbsp;Aina Juell Bugge,&nbsp;Jan Inge Faleide","doi":"10.1111/1365-2478.13505","DOIUrl":null,"url":null,"abstract":"<p>Marine seismic data is often missing near offset information due to separation between the source and receiver cables. To solve this problem, a convolutional neural network is trained on synthetic seismic data to reconstruct the near offset gap. The synthetic data is created using a two-dimensional finite difference method within a heterogeneous velocity model. These synthetics are generated with a source-over-receiver acquisition geometry so that they contain complete near offset data. The convolutional neural network is then trained on input-target synthetic pairs where the inputs are common midpoint gathers with the near offset section removed, and the targets are the same gathers with the near offset section retained. Following training, the robustness of the method is investigated with regards to common midpoint data sorting, normal moveout correction and changes in the velocity model. It is found that training on common midpoint-sorted data results in 2.8 times lower error than training on shot gathers, that normal moveout correction of the training data makes no significant difference in error levels, and that the model can reconstruct realistic near offsets on synthetic data generated 10 km away within the heterogeneous velocity model. In field data testing, first a dataset with source-over-cable acquisition geometry from the Barents Sea is used to compare the reconstructed wavefields to ground truth values. Although the reconstructed amplitudes require minor scaling to match the true values, predictions on this dataset yield 2.5 times lower near offset reconstruction error compared to a simple Radon transform interpolation method. Furthermore, amplitude versus offset gradient and intercept sections from the Barents Sea dataset are estimated with half the error when including the convolutional neural network-predicted near offset data, compared to only using the conventionally-acquirable portion of the data (beyond 112.5 m of offset). In a secondary field data test, a conventional northern North Sea dataset is used to demonstrate how the method may be applied in practice. Here, the convolutional neural network generates more realistic predictions than the Radon method, and the gradient and intercept sections calculated using the convolutional neural network-predicted traces have higher signal-to-noise ratios than the sections calculated using only the original data. The combination of high-quality synthetic training data and interpolation in the common midpoint domain enables near offset reconstruction at significant depth (1 s of two-way traveltime or more), which is demonstrated in both synthetic and field examples.</p>","PeriodicalId":12793,"journal":{"name":"Geophysical Prospecting","volume":"72 6","pages":"2164-2185"},"PeriodicalIF":1.8000,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/1365-2478.13505","citationCount":"0","resultStr":"{\"title\":\"Near offset reconstruction for marine seismic data using a convolutional neural network\",\"authors\":\"Owen Rohwer Huff,&nbsp;Vemund Stenbekk Thorkildsen,&nbsp;Thomas Larsen Greiner,&nbsp;Jan Erik Lie,&nbsp;Andreas Kjelsrud Evensen,&nbsp;Aina Juell Bugge,&nbsp;Jan Inge Faleide\",\"doi\":\"10.1111/1365-2478.13505\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Marine seismic data is often missing near offset information due to separation between the source and receiver cables. To solve this problem, a convolutional neural network is trained on synthetic seismic data to reconstruct the near offset gap. The synthetic data is created using a two-dimensional finite difference method within a heterogeneous velocity model. These synthetics are generated with a source-over-receiver acquisition geometry so that they contain complete near offset data. The convolutional neural network is then trained on input-target synthetic pairs where the inputs are common midpoint gathers with the near offset section removed, and the targets are the same gathers with the near offset section retained. Following training, the robustness of the method is investigated with regards to common midpoint data sorting, normal moveout correction and changes in the velocity model. It is found that training on common midpoint-sorted data results in 2.8 times lower error than training on shot gathers, that normal moveout correction of the training data makes no significant difference in error levels, and that the model can reconstruct realistic near offsets on synthetic data generated 10 km away within the heterogeneous velocity model. In field data testing, first a dataset with source-over-cable acquisition geometry from the Barents Sea is used to compare the reconstructed wavefields to ground truth values. Although the reconstructed amplitudes require minor scaling to match the true values, predictions on this dataset yield 2.5 times lower near offset reconstruction error compared to a simple Radon transform interpolation method. Furthermore, amplitude versus offset gradient and intercept sections from the Barents Sea dataset are estimated with half the error when including the convolutional neural network-predicted near offset data, compared to only using the conventionally-acquirable portion of the data (beyond 112.5 m of offset). In a secondary field data test, a conventional northern North Sea dataset is used to demonstrate how the method may be applied in practice. Here, the convolutional neural network generates more realistic predictions than the Radon method, and the gradient and intercept sections calculated using the convolutional neural network-predicted traces have higher signal-to-noise ratios than the sections calculated using only the original data. The combination of high-quality synthetic training data and interpolation in the common midpoint domain enables near offset reconstruction at significant depth (1 s of two-way traveltime or more), which is demonstrated in both synthetic and field examples.</p>\",\"PeriodicalId\":12793,\"journal\":{\"name\":\"Geophysical Prospecting\",\"volume\":\"72 6\",\"pages\":\"2164-2185\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2024-03-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1111/1365-2478.13505\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Geophysical Prospecting\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/1365-2478.13505\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geophysical Prospecting","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/1365-2478.13505","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

摘要

由于震源和接收电缆之间的分离,海洋地震数据往往缺少近偏移信息。为解决这一问题,我们在合成地震数据上训练了一个卷积神经网络,以重建近偏移间隙。合成数据是在异质速度模型中使用二维有限差分法创建的。这些合成数据采用震源-接收器采集几何形状生成,因此包含完整的近偏移数据。然后在输入-目标合成对上对卷积神经网络进行训练,其中输入是去除近偏移部分的普通中点采集,目标是保留近偏移部分的相同采集。训练结束后,对该方法的鲁棒性进行了研究,包括共同中点数据排序、正常偏移校正和速度模型的变化。结果发现,在普通中点分类数据上进行训练,误差比在射电采集数据上进行训练低 2.8 倍;对训练数据进行正常偏移校正,误差水平没有显著差异;在异质速度模型内,该模型可以在 10 公里外生成的合成数据上重建真实的近偏移。在实地数据测试中,首先使用巴伦支海的源过电缆采集几何数据集,将重建的波场与地面真实值进行比较。虽然重建的振幅需要稍作缩放才能与真实值相匹配,但与简单的拉顿变换插值法相比,该数据集的预测结果将近偏移重建误差降低了 2.5 倍。此外,巴伦支海数据集的振幅与偏移梯度和截距剖面的估算,如果包括卷积神经网络预测的近偏移数据,误差要比只使用传统获取的数据部分(偏移 112.5 米以外)小一半。在二次实地数据测试中,使用了北海北部的一个常规数据集,以演示如何在实践中应用该方法。在这里,卷积神经网络生成的预测结果比 Radon 方法更真实,使用卷积神经网络预测的轨迹计算的梯度和截距断面比仅使用原始数据计算的断面具有更高的信噪比。高质量的合成训练数据与共同中点域插值相结合,可在较大深度(1 秒或更长的双向走时)实现近偏移重建,这在合成和野外示例中都得到了验证。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Near offset reconstruction for marine seismic data using a convolutional neural network

Near offset reconstruction for marine seismic data using a convolutional neural network

Marine seismic data is often missing near offset information due to separation between the source and receiver cables. To solve this problem, a convolutional neural network is trained on synthetic seismic data to reconstruct the near offset gap. The synthetic data is created using a two-dimensional finite difference method within a heterogeneous velocity model. These synthetics are generated with a source-over-receiver acquisition geometry so that they contain complete near offset data. The convolutional neural network is then trained on input-target synthetic pairs where the inputs are common midpoint gathers with the near offset section removed, and the targets are the same gathers with the near offset section retained. Following training, the robustness of the method is investigated with regards to common midpoint data sorting, normal moveout correction and changes in the velocity model. It is found that training on common midpoint-sorted data results in 2.8 times lower error than training on shot gathers, that normal moveout correction of the training data makes no significant difference in error levels, and that the model can reconstruct realistic near offsets on synthetic data generated 10 km away within the heterogeneous velocity model. In field data testing, first a dataset with source-over-cable acquisition geometry from the Barents Sea is used to compare the reconstructed wavefields to ground truth values. Although the reconstructed amplitudes require minor scaling to match the true values, predictions on this dataset yield 2.5 times lower near offset reconstruction error compared to a simple Radon transform interpolation method. Furthermore, amplitude versus offset gradient and intercept sections from the Barents Sea dataset are estimated with half the error when including the convolutional neural network-predicted near offset data, compared to only using the conventionally-acquirable portion of the data (beyond 112.5 m of offset). In a secondary field data test, a conventional northern North Sea dataset is used to demonstrate how the method may be applied in practice. Here, the convolutional neural network generates more realistic predictions than the Radon method, and the gradient and intercept sections calculated using the convolutional neural network-predicted traces have higher signal-to-noise ratios than the sections calculated using only the original data. The combination of high-quality synthetic training data and interpolation in the common midpoint domain enables near offset reconstruction at significant depth (1 s of two-way traveltime or more), which is demonstrated in both synthetic and field examples.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 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.
×
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