Skeletonized Wave-Equation Refraction Inversion With Autoencoded Waveforms

Skeletonized Wave-Equation Refraction Inversion With Autoencoded Waveforms
复制标题

使用自编码波形进行骨架化波动方程折射反演

DOI:
10.1109/tgrs.2020.3046093
复制
发表时间:
2021-01
影响因子:
8.2
通讯作者:
Gerard T. Schuster
Gerard T. Schuster
中科院分区:
工程技术1区
文献类型:
--
作者:
Han Yu;Yuqing Chen;Sherif M. Hanafy;Gerard T. Schuster

文献摘要

参考文献

相似文献

我们提出了一种方法,通过机器学习对第一次到达的地震折射进行骨架化,并将它们反演出为地下速度模型。在这项研究中,通过训练良好的自动编码器提取第一到达信号的骨架特征,可以对其进行低阶压缩。实验表明,自动编码器的$1\×1$或$2\×1$潜在向量相对于输入地震数据连续变化。因此,在低维潜在空间中引入一个衡量预测数据和观测数据之间差异的失配泛函是合理的。这种方法的好处是,精心设计的自动编码神经网络不仅精炼了隐藏在折射中的内在信息,而且提高了反演的质量,从而建立了可靠的背景速度模型。对合成数据和现场数据的数值试验表明,该方法是有效的,特别是在恢复地下速度分布的中低波数部分方面。与波动方程走时(WT)反演法、包络反演法和全波形反演法(FWI)进行了比较。不出所料,由于数据空间维度的降低,跳转问题得到了缓解。该方法在分辨率上优于包络反演法,并不比小波变换差。此外,这种方法不需要仔细地人工挑选旅行时间。一般而言,该反演框架提供了一种可扩展的策略来压缩用于重建高维物理参数的任何输入数据。
We present a method that skeletonizes the first arriving seismic refractions by machine learning and inverts them for the subsurface velocity model. In this study, first arrivals can be compressed in a low-rank sense with their skeletal features extracted by a well-trained autoencoder. Empirical experiments suggest that the autoencoder’s $1\times 1$ or $2\times 1$ latent vectors vary continuously with respect to the input seismic data. It is, therefore, reasonable to introduce a misfit functional measuring the discrepancies between the predicted and the observed data in a low-dimensional latent space. The benefit of this approach is that an elaborated autoencoding neural network not only refines intrinsic information hidden in the refractions but also improves the quality of inversion for a reliable background velocity model. Numerical tests on both synthetic and field data demonstrate the effectiveness of this method, especially in recovering the low-to-intermediate wavenumber parts of the subsurface velocity distribution. Comparisons are made with the other three relevant methods, the wave-equation travel-time (WT) inversion, the envelope inversion, and the full waveform inversion (FWI). As expected, the cycle skipping problem is alleviated due to the reduction of dimensions of data space. This method outperforms the envelope inversion in resolution, and it is no worse than WT. Moreover, there is no need for careful manual travel-time picking with this methodology. In general, this inversion framework provides an extendable strategy to compress any input data for reconstructing high-dimensional physical parameters.
DOI: 10.1190/1.1649391
发表时间: 2004
期刊: Geophysics
影响因子: 3.3
作者:
L. Sirgue;R. Pratt
通讯作者: L. Sirgue;R. Pratt
DOI: 10.1111/j.1365-246x.2012.05429.x
发表时间: 2012-05-01
影响因子: 2.8
作者:
Valentine, Andrew P.;Trampert, Jeannot
通讯作者: Trampert, Jeannot
DOI: 10.1190/geo2015-0387.1
发表时间: 2014-08
期刊: Geophysics
影响因子: 3.3
作者:
M. Warner;L. Guasch
通讯作者: M. Warner;L. Guasch
DOI: 10.1007/b98874
发表时间: 2018-09
期刊: --
影响因子: --
作者:
J. Nocedal;Stephen J. Wright
通讯作者: J. Nocedal;Stephen J. Wright
DOI: 10.1190/segam2016-13850307.1
发表时间: 2016
期刊: Seg Technical Program Expanded Abstracts
影响因子: --
作者:
Zhiyang Liu;Jie Zhang
通讯作者: Zhiyang Liu;Jie Zhang