☆ 4.7 Article

Adaptive Feedback Convolutional-Neural-Network-Based High-Resolution Reflection-Waveform Inversion

JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH (2022)

Related references

Note: Only part of the references are listed.

Article Geochemistry & Geophysics

Integrating deep neural networks with full-waveform inversion: Reparameterization, regularization, and uncertainty quantification

Weiqiang Zhu et al.

Summary: Full-waveform inversion (FWI) is an accurate imaging method for modeling the velocity structure. However, its strong nonlinearity can lead to optimization being trapped in local minima. In this study, we propose a neural-network-based FWI method that integrates deep neural networks and FWI to overcome this issue.

GEOPHYSICS (2022)

Add to Collection

Article Geochemistry & Geophysics

Deep-learning seismic full-waveform inversion for realistic structural models

Bin Liu et al.

Summary: Velocity model inversion, an important task in seismic exploration, has seen advancements with the development of deep learning methods. A method for constructing realistic structural models has been proposed to improve inversion results and provide practical guidance for optimal strategies in realistic situations.

GEOPHYSICS (2021)

Add to Collection

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)

Add to Collection

Article Geochemistry & Geophysics

Frequency-domain reflection waveform inversion with generalized internal multiple imaging

Guanchao Wang et al.

Summary: Traditional reflection waveform inversion methods often involve smearing of data during migration, but the new GIMI-RWI approach avoids this by directly updating the primary reflection kernel. This improves the accuracy and smoothness of tomographic velocity updates, demonstrating reliable performance in the synthetic example from the Sigsbee2A model.

GEOPHYSICS (2021)

Add to Collection

Article Geochemistry & Geophysics

Mapping full seismic waveforms to vertical velocity profiles by deep learning

Vladimir Kazei et al.

Summary: Building realistic and reliable models of the subsurface through seismic imaging is achieved by using an ensemble of convolutional neural networks (CNNs) that can map gathers of neighboring common midpoints (CMPs) to vertical 1D velocity logs. This approach, which integrates well-logging data and accommodates larger dips, improves inversion accuracy and efficiency. Despite being computationally expensive, training the CNNs allows for faster inversion of data sets with similar acquisition parameters compared to conventional full-waveform inversion (FWI).

GEOPHYSICS (2021)

Add to Collection

Article Geochemistry & Geophysics

Velocity model building in a crosswell acquisition geometry with image-trained artificial neural networks

Wenlong Wang et al.

GEOPHYSICS (2020)

Add to Collection

Review Energy & Fuels

A review on reflection-waveform inversion

Gang Yao et al.

PETROLEUM SCIENCE (2020)

Add to Collection

Article Geochemistry & Geophysics

Extraction of the tomography mode with nonstationary smoothing for full-waveform inversion

Gang Yao et al.

GEOPHYSICS (2019)

Add to Collection

Article Geochemistry & Geophysics

Deep-learning inversion: A next-generation seismic velocity model building method

Fangshu Yang et al.

GEOPHYSICS (2019)

Add to Collection

Article Geochemistry & Geophysics

Parametric convolutional neural network-domain full-waveform inversion

Yulang Wu et al.

GEOPHYSICS (2019)

Add to Collection

Article Geosciences, Multidisciplinary

Enhancing low-wavenumber components of full-waveform inversion using an improved wavefield decomposition method in the time-space domain

Shijie Lian et al.

JOURNAL OF APPLIED GEOPHYSICS (2018)

Add to Collection

Article Geochemistry & Geophysics

Efficient scattering-angle enrichment for a nonlinear inversion of the background and perturbations components of a velocity model

Zedong Wu et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2017)

Add to Collection

Article Geosciences, Multidisciplinary

Reflection full waveform inversion

Gang Yao et al.

SCIENCE CHINA-EARTH SCIENCES (2017)

Add to Collection

Review Mathematical & Computational Biology

Ten quick tips for machine learning in computational biology

Davide Chicco

BIODATA MINING (2017)

Add to Collection

Article Geochemistry & Geophysics

Removing false images in reverse time migration: The concept of de-primary

Tong W. Fei et al.

GEOPHYSICS (2015)

Add to Collection

Article Geochemistry & Geophysics

Simultaneous inversion of the background velocity and the perturbation in full-waveform inversion

Zedong Wu et al.

GEOPHYSICS (2015)

Add to Collection

Article Geochemistry & Geophysics

Scattering-angle based filtering of the waveform inversion gradients

Tariq Alkhalifah

GEOPHYSICAL JOURNAL INTERNATIONAL (2015)

Add to Collection

Article Geochemistry & Geophysics

Blocky regularization schemes for Full-Waveform Inversion

Antoine Guitton

GEOPHYSICAL PROSPECTING (2012)

Add to Collection

Article Geochemistry & Geophysics

Image-guided sparse-model full waveform inversion

Yong Ma et al.

GEOPHYSICS (2012)

Add to Collection

Article Geochemistry & Geophysics

An effective imaging condition for reverse-time migration using wavefield decomposition

Faqi Liu et al.

GEOPHYSICS (2011)

Add to Collection

Review Geochemistry & Geophysics

An overview of full-waveform inversion in exploration geophysics

J. Virieux et al.

GEOPHYSICS (2009)

Add to Collection

© Peeref 2019-2024. All rights reserved.