Seismic velocity model building using neural networks: Training data design and learning generalization

Article Geochemistry & Geophysics

Reparameterized full-waveform inversion using deep neural networks

Qinglong He et al.

Summary: The deep-learning inversion method reparameterizes physical parameters using DNN weights, serving as an iterative regularization method for solving ill-posed nonlinear problems. It offers good computational efficiency and can easily be accelerated, showing effectiveness in recovering sharp boundaries and capturing salient features of the model when compared to total-variation regularized FWI.

GEOPHYSICS (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Automatic velocity picking from semblances with a new deep-learning regression strategy: Comparison with a classification approach

Wenlong Wang et al.

Summary: This study introduces the application of machine learning in root-mean-square (rms) velocity estimation, designing and evaluating classification and regression neural networks for extracting velocity trajectories from semblance data. Testing with synthetic data shows that the regression network achieves higher accuracy compared to the classification network.

GEOPHYSICS (2021)

添加到收藏夹

Article Geochemistry & Geophysics