利用深度生成先验进行随机全波形反演以量化不确定性

Yuke Xie, Hervé Chauris, Nicolas Desassis
{"title":"利用深度生成先验进行随机全波形反演以量化不确定性","authors":"Yuke Xie, Hervé Chauris, Nicolas Desassis","doi":"arxiv-2406.04859","DOIUrl":null,"url":null,"abstract":"To obtain high-resolution images of subsurface structures from seismic data,\nseismic imaging techniques such as Full Waveform Inversion (FWI) serve as\ncrucial tools. However, FWI involves solving a nonlinear and often non-unique\ninverse problem, presenting challenges such as local minima trapping and\ninadequate handling of inherent uncertainties. In addressing these challenges,\nwe propose leveraging deep generative models as the prior distribution of\ngeophysical parameters for stochastic Bayesian inversion. This approach\nintegrates the adjoint state gradient for efficient back-propagation from the\nnumerical solution of partial differential equations. Additionally, we\nintroduce explicit and implicit variational Bayesian inference methods. The\nexplicit method computes variational distribution density using a normalizing\nflow-based neural network, enabling computation of the Bayesian posterior of\nparameters. Conversely, the implicit method employs an inference network\nattached to a pretrained generative model to estimate density, incorporating an\nentropy estimator. Furthermore, we also experimented with the Stein Variational\nGradient Descent (SVGD) method as another variational inference technique,\nusing particles. We compare these variational Bayesian inference methods with\nconventional Markov chain Monte Carlo (McMC) sampling. Each method is able to\nquantify uncertainties and to generate seismic data-conditioned realizations of\nsubsurface geophysical parameters. This framework provides insights into\nsubsurface structures while accounting for inherent uncertainties.","PeriodicalId":501215,"journal":{"name":"arXiv - STAT - Computation","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Stochastic full waveform inversion with deep generative prior for uncertainty quantification\",\"authors\":\"Yuke Xie, Hervé Chauris, Nicolas Desassis\",\"doi\":\"arxiv-2406.04859\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To obtain high-resolution images of subsurface structures from seismic data,\\nseismic imaging techniques such as Full Waveform Inversion (FWI) serve as\\ncrucial tools. However, FWI involves solving a nonlinear and often non-unique\\ninverse problem, presenting challenges such as local minima trapping and\\ninadequate handling of inherent uncertainties. In addressing these challenges,\\nwe propose leveraging deep generative models as the prior distribution of\\ngeophysical parameters for stochastic Bayesian inversion. This approach\\nintegrates the adjoint state gradient for efficient back-propagation from the\\nnumerical solution of partial differential equations. Additionally, we\\nintroduce explicit and implicit variational Bayesian inference methods. The\\nexplicit method computes variational distribution density using a normalizing\\nflow-based neural network, enabling computation of the Bayesian posterior of\\nparameters. Conversely, the implicit method employs an inference network\\nattached to a pretrained generative model to estimate density, incorporating an\\nentropy estimator. Furthermore, we also experimented with the Stein Variational\\nGradient Descent (SVGD) method as another variational inference technique,\\nusing particles. We compare these variational Bayesian inference methods with\\nconventional Markov chain Monte Carlo (McMC) sampling. Each method is able to\\nquantify uncertainties and to generate seismic data-conditioned realizations of\\nsubsurface geophysical parameters. This framework provides insights into\\nsubsurface structures while accounting for inherent uncertainties.\",\"PeriodicalId\":501215,\"journal\":{\"name\":\"arXiv - STAT - Computation\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-06-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - STAT - Computation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2406.04859\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - STAT - Computation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2406.04859","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

为了从地震数据中获得地下结构的高分辨率图像,全波形反演(FWI)等地震成像技术成为重要工具。然而,全波形反演涉及求解一个非线性且往往是非唯一的反演问题,带来了诸如局部最小值陷阱和对固有不确定性处理不当等挑战。为了应对这些挑战,我们提出利用深度生成模型作为随机贝叶斯反演的地球物理参数的先验分布。这种方法整合了从偏微分方程数值解中高效反向传播的临界状态梯度。此外,我们还引入了显式和隐式变分贝叶斯推理方法。显式方法使用基于归一化流的神经网络计算变分分布密度,从而计算参数的贝叶斯后验。与此相反,隐式推理方法采用了一个与预训练生成模型相连的推理网络来估计密度,并结合了一个熵估计器。此外,我们还试验了斯坦因变异梯度下降法(SVGD),作为另一种使用粒子的变异推理技术。我们将这些变异贝叶斯推断方法与传统的马尔可夫链蒙特卡罗(McMC)采样进行了比较。每种方法都能量化不确定性,并生成以地震数据为条件的次表层地球物理参数现实。这一框架在考虑固有不确定性的同时,提供了对次表层结构的见解。
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
Stochastic full waveform inversion with deep generative prior for uncertainty quantification
To obtain high-resolution images of subsurface structures from seismic data, seismic imaging techniques such as Full Waveform Inversion (FWI) serve as crucial tools. However, FWI involves solving a nonlinear and often non-unique inverse problem, presenting challenges such as local minima trapping and inadequate handling of inherent uncertainties. In addressing these challenges, we propose leveraging deep generative models as the prior distribution of geophysical parameters for stochastic Bayesian inversion. This approach integrates the adjoint state gradient for efficient back-propagation from the numerical solution of partial differential equations. Additionally, we introduce explicit and implicit variational Bayesian inference methods. The explicit method computes variational distribution density using a normalizing flow-based neural network, enabling computation of the Bayesian posterior of parameters. Conversely, the implicit method employs an inference network attached to a pretrained generative model to estimate density, incorporating an entropy estimator. Furthermore, we also experimented with the Stein Variational Gradient Descent (SVGD) method as another variational inference technique, using particles. We compare these variational Bayesian inference methods with conventional Markov chain Monte Carlo (McMC) sampling. Each method is able to quantify uncertainties and to generate seismic data-conditioned realizations of subsurface geophysical parameters. This framework provides insights into subsurface structures while accounting for inherent uncertainties.
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
自引率
0.00%
发文量
0
期刊最新文献
Model-Embedded Gaussian Process Regression for Parameter Estimation in Dynamical System Effects of the entropy source on Monte Carlo simulations A Robust Approach to Gaussian Processes Implementation HJ-sampler: A Bayesian sampler for inverse problems of a stochastic process by leveraging Hamilton-Jacobi PDEs and score-based generative models Reducing Shape-Graph Complexity with Application to Classification of Retinal Blood Vessels and Neurons
×
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