.png){kind=icon}
返回
Deep Learning Reparameterized FWI Using a Frequency-Normalized Gradient
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2025.3624703.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
High-precision full-waveform inversion is a key method for subsurface parameter modeling. Enhancing the contribution of weak low-frequency signals to low-wavenumber components is crucial for inversion. Existing frequency normalization schemes can significantly leverage low-frequency contributions in inversion, but their discrete normalization approach produces pronounced high-wavenumber noise. We propose a deep-learning-parameterized frequency normalization scheme that effectively enhancing low-frequency contribution and suppressing high-wavenumber artifacts. By innovatively constructing a deep-learning-driven inversion framework with frequency-normalized adjoint gradients: it uses a deep learning (DL) network to parameterize model parameters, solves the time-domain solver with a normalized source, builds a gradient without frequency crosstalk, and forms a cyclic network parameter update process. Through a multiscale learning optimization scheme, the final inversion result is output via the deep network. Synthetic data results demonstrate that the proposed method enhances low-wavenumber modeling capability and suppresses high-wavenumber noise; its application to land data confirms its ability to bridge the medium-wavenumber gap between the initial background model and migration imaging.
Keyword:
Time-frequency analysis
Artificial neural networks
Numerical models
Mathematical models
Linear programming
Time-domain analysis
Deep learning
Accuracy
Symbols
Propagation
Deep learning (DL)
full-waveform inversion (FWI)
time-frequency domain
期刊
I
IF:
4.4
论文数:
629
被引数:
0
机构
引用论文
Transfer Learning Fourier Neural Operator for Solving Parametric Frequency-Domain Wave Equations
PREAI
分享收藏
Optimal Space-Variant Anisotropic Tikhonov Regularization for Full Waveform Inversion of Sparse Data稀疏数据全波形反演的最优空间变异各向异性Tikhonov正则化
OAAI
OAAI分享收藏分享收藏Source-independent time-domain waveform inversion using convolved wavefields: Application to the encoded multisource waveform inversion.png)
GEOPHYSICS
GEOPHYSICSIF3.2
PREAI
分享收藏Multiscale Deep Learning Reparameterized Full Waveform Inversion With the Adjoint Method基于伴随方法的多尺度深度学习重参数化全波形反演
PREAI
分享收藏
查看更多内容