Prediction of S-wave velocity models from surface waves using deep learning

IF 1.1 4区 地球科学 Q3 GEOCHEMISTRY & GEOPHYSICS Near Surface Geophysics Pub Date : 2023-11-21 DOI:10.1002/nsg.12284
Sangin Cho, Sukjoon Pyun, Byunghoon Choi, Ganghoon Lee, Seonghyung Jang, Yunseok Choi
{"title":"Prediction of S-wave velocity models from surface waves using deep learning","authors":"Sangin Cho, Sukjoon Pyun, Byunghoon Choi, Ganghoon Lee, Seonghyung Jang, Yunseok Choi","doi":"10.1002/nsg.12284","DOIUrl":null,"url":null,"abstract":"Surface wave (SW) methods extract dispersion properties of wavefields propagating through a seismic array (1D or 2D). This is achieved by analysing the phase velocity versus frequency (or wavelength) data. Afterwards, an inversion process is performed to construct near-surface S-wave velocity models. Among the SW methods, multichannel analysis of SWs (MASW) is commonly used for engineering applications, analysing dispersion characteristics by generating a dispersion image. However, classical MASW depends on the manual picking of dispersion curves, which can lead to subjective outcomes and require time and effort to obtain precise results. To avoid these pitfalls, many studies, including deep-learning techniques, have focused on automating the process. Similarly, we propose a deep-learning-based algorithm that estimates the S-wave velocity directly from the dispersion image of SWs. This algorithm consists of a convolutional neural network (CNN) designed to directly yield S-wave velocity profiles and a fully connected network (multi-layer perceptron) added to regularize predictions. Unlike typical SW techniques, the proposed approach does not incorporate prior information such as layer count and thickness. To ensure successful training, we modified the loss function to exploit the normalized mean squared error. The training dataset was generated by modelling synthetic shot gathers and transforming them into dispersion images for various 1D stratified velocity structures. After a sample is fed to the CNN network for inversion, the inversion network's output subsequently goes through an additional simple neural network (NN) to regularize the predicted S-wave velocity model (which is the post-processing step). The combined usage of deep-learning-based SW inversion with NN-based post-processing was assessed using test data. The proposed algorithm achieved an average relative error of approximately 7.49% in predicting the S-wave velocity and was successfully applied to the field data. Additionally, we discuss its performance on noisy data as well as its applicability to out-of-training data. Numerical examples demonstrated that the proposed method is robust to noise, whereas it requires additional training to handle data beyond the distribution of the training data.","PeriodicalId":49771,"journal":{"name":"Near Surface Geophysics","volume":null,"pages":null},"PeriodicalIF":1.1000,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Near Surface Geophysics","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1002/nsg.12284","RegionNum":4,"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

Surface wave (SW) methods extract dispersion properties of wavefields propagating through a seismic array (1D or 2D). This is achieved by analysing the phase velocity versus frequency (or wavelength) data. Afterwards, an inversion process is performed to construct near-surface S-wave velocity models. Among the SW methods, multichannel analysis of SWs (MASW) is commonly used for engineering applications, analysing dispersion characteristics by generating a dispersion image. However, classical MASW depends on the manual picking of dispersion curves, which can lead to subjective outcomes and require time and effort to obtain precise results. To avoid these pitfalls, many studies, including deep-learning techniques, have focused on automating the process. Similarly, we propose a deep-learning-based algorithm that estimates the S-wave velocity directly from the dispersion image of SWs. This algorithm consists of a convolutional neural network (CNN) designed to directly yield S-wave velocity profiles and a fully connected network (multi-layer perceptron) added to regularize predictions. Unlike typical SW techniques, the proposed approach does not incorporate prior information such as layer count and thickness. To ensure successful training, we modified the loss function to exploit the normalized mean squared error. The training dataset was generated by modelling synthetic shot gathers and transforming them into dispersion images for various 1D stratified velocity structures. After a sample is fed to the CNN network for inversion, the inversion network's output subsequently goes through an additional simple neural network (NN) to regularize the predicted S-wave velocity model (which is the post-processing step). The combined usage of deep-learning-based SW inversion with NN-based post-processing was assessed using test data. The proposed algorithm achieved an average relative error of approximately 7.49% in predicting the S-wave velocity and was successfully applied to the field data. Additionally, we discuss its performance on noisy data as well as its applicability to out-of-training data. Numerical examples demonstrated that the proposed method is robust to noise, whereas it requires additional training to handle data beyond the distribution of the training data.
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
利用深度学习从表面波预测s波速度模型
面波(SW)方法提取通过地震阵列(一维或二维)传播的波场色散特性。这是通过分析相速度与频率(或波长)数据来实现的。然后进行反演,建立近地表横波速度模型。在声波分析方法中,多通道声波分析(MASW)通常用于工程应用,通过生成色散图像来分析色散特性。然而,经典的MASW依赖于人工挑选色散曲线,这可能导致主观结果,并且需要时间和精力来获得精确的结果。为了避免这些陷阱,包括深度学习技术在内的许多研究都将重点放在了自动化过程上。同样,我们提出了一种基于深度学习的算法,该算法直接从SWs的色散图像中估计s波速度。该算法由一个卷积神经网络(CNN)和一个全连接网络(多层感知器)组成,该网络旨在直接产生s波速度剖面,并添加了一个正则化预测。与典型的软件技术不同,所提出的方法不包含诸如层数和厚度之类的先验信息。为了确保训练成功,我们修改了损失函数来利用归一化均方误差。训练数据集是通过对合成射击集进行建模,并将其转换为各种一维分层速度结构的离散图像而生成的。将样本馈送到CNN网络进行反演后,反演网络的输出随后通过一个附加的简单神经网络(NN)对预测的横波速度模型进行正则化(这是后处理步骤)。使用测试数据评估了基于深度学习的SW反演与基于神经网络的后处理的结合使用。该算法预测横波速度的平均相对误差约为7.49%,并成功应用于现场数据。此外,我们还讨论了它在噪声数据上的性能以及对非训练数据的适用性。数值算例表明,该方法对噪声具有较强的鲁棒性,但在处理训练数据分布之外的数据时需要进行额外的训练。
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
Near Surface Geophysics
Near Surface Geophysics 地学-地球化学与地球物理
CiteScore
3.60
自引率
12.50%
发文量
42
审稿时长
6-12 weeks
期刊介绍: Near Surface Geophysics is an international journal for the publication of research and development in geophysics applied to near surface. It places emphasis on geological, hydrogeological, geotechnical, environmental, engineering, mining, archaeological, agricultural and other applications of geophysics as well as physical soil and rock properties. Geophysical and geoscientific case histories with innovative use of geophysical techniques are welcome, which may include improvements on instrumentation, measurements, data acquisition and processing, modelling, inversion, interpretation, project management and multidisciplinary use. The papers should also be understandable to those who use geophysical data but are not necessarily geophysicists.
期刊最新文献
High‐resolution surface‐wave‐constrained mapping of sparse dynamic cone penetrometer tests Application of iterative elastic reverse time migration to shear horizontal ultrasonic echo data obtained at a concrete step specimen Innovative imaging of iron deposits using cross‐gradient joint inversion of potential field data with petrophysical correlation A fine‐tuning workflow for automatic first‐break picking with deep learning How to promote geophysics as a standard tool for geotechnical investigations
×
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