基于物理驱动和信号可解释性的隧道电阻率深度学习反演方法

IF 1.1 4区 地球科学 Q3 GEOCHEMISTRY & GEOPHYSICS Near Surface Geophysics Pub Date : 2024-03-09 DOI:10.1002/nsg.12294
Benchao Liu, Yuting Tang, Yongheng Zhang, Peng Jiang, Fengkai Zhang
{"title":"基于物理驱动和信号可解释性的隧道电阻率深度学习反演方法","authors":"Benchao Liu, Yuting Tang, Yongheng Zhang, Peng Jiang, Fengkai Zhang","doi":"10.1002/nsg.12294","DOIUrl":null,"url":null,"abstract":"Data-driven deep learning technology has a strong non-linear mapping ability and has good development potential in geophysical inversion problems. Traditional inversion techniques offer broad generality, but they can remain trapped in local minima, particularly for three-dimensional tunnelling resistivity inversion. In this work, we present an inversion methodology that combines traditional physics-driven and deep learning data-driven inversion approaches. To further support deep neural networks' dependability on unseen data, the interpretability of their working mechanism is explored. We execute migration learning based on small sample data after identifying the critical parameters that restrict the effectiveness of inversion by analysing the feature maps of various model data. We demonstrate, using both synthetic examples and field data, that the proposed method can improve the accuracy in detecting water-bearing anomalies (caves and faults), which are typically encountered during tunnel excavation.","PeriodicalId":49771,"journal":{"name":"Near Surface Geophysics","volume":"2 1","pages":""},"PeriodicalIF":1.1000,"publicationDate":"2024-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Tunnel resistivity deep learning inversion method based on physics-driven and signal interpretability\",\"authors\":\"Benchao Liu, Yuting Tang, Yongheng Zhang, Peng Jiang, Fengkai Zhang\",\"doi\":\"10.1002/nsg.12294\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Data-driven deep learning technology has a strong non-linear mapping ability and has good development potential in geophysical inversion problems. Traditional inversion techniques offer broad generality, but they can remain trapped in local minima, particularly for three-dimensional tunnelling resistivity inversion. In this work, we present an inversion methodology that combines traditional physics-driven and deep learning data-driven inversion approaches. To further support deep neural networks' dependability on unseen data, the interpretability of their working mechanism is explored. We execute migration learning based on small sample data after identifying the critical parameters that restrict the effectiveness of inversion by analysing the feature maps of various model data. We demonstrate, using both synthetic examples and field data, that the proposed method can improve the accuracy in detecting water-bearing anomalies (caves and faults), which are typically encountered during tunnel excavation.\",\"PeriodicalId\":49771,\"journal\":{\"name\":\"Near Surface Geophysics\",\"volume\":\"2 1\",\"pages\":\"\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2024-03-09\",\"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.12294\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Near Surface Geophysics","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1002/nsg.12294","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

摘要

数据驱动的深度学习技术具有很强的非线性绘图能力,在地球物理反演问题上具有很好的发展潜力。传统反演技术具有广泛的通用性,但可能会陷入局部最小值的困境,尤其是在三维隧道电阻率反演方面。在这项工作中,我们提出了一种结合传统物理驱动和深度学习数据驱动的反演方法。为了进一步支持深度神经网络对未知数据的依赖性,我们探索了其工作机制的可解释性。我们通过分析各种模型数据的特征图,确定了限制反演有效性的关键参数,然后基于小样本数据执行迁移学习。我们利用合成示例和实地数据证明,所提出的方法可以提高探测含水异常(洞穴和断层)的准确性,而这些异常通常是在隧道挖掘过程中遇到的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Tunnel resistivity deep learning inversion method based on physics-driven and signal interpretability
Data-driven deep learning technology has a strong non-linear mapping ability and has good development potential in geophysical inversion problems. Traditional inversion techniques offer broad generality, but they can remain trapped in local minima, particularly for three-dimensional tunnelling resistivity inversion. In this work, we present an inversion methodology that combines traditional physics-driven and deep learning data-driven inversion approaches. To further support deep neural networks' dependability on unseen data, the interpretability of their working mechanism is explored. We execute migration learning based on small sample data after identifying the critical parameters that restrict the effectiveness of inversion by analysing the feature maps of various model data. We demonstrate, using both synthetic examples and field data, that the proposed method can improve the accuracy in detecting water-bearing anomalies (caves and faults), which are typically encountered during tunnel excavation.
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
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 A fine‐tuning workflow for automatic first‐break picking with deep learning Experimental and numerical analysis of dielectric polarization effects in near‐surface earth materials in the 100 Hz–10 MHz frequency range: First interpretation paths Bayesian inversion and uncertainty analysis
×
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