4.2 Article

Machine learning-accelerated gradient-based Markov chain Monte Carlo inversion applied to electrical resistivity tomography

Related references

Note: Only part of the references are listed.
Article Environmental Sciences

Deep Convolutional Autoencoders for Robust Flow Model Calibration Under Uncertainty in Geologic Continuity

Anyue Jiang et al.

Summary: This paper introduces a deep learning architecture called variational auto-encoder for robust dimension-reduced parameterization of spatially distributed aquifer properties under uncertain geostatistical models.

WATER RESOURCES RESEARCH (2021)

Article Geosciences, Multidisciplinary

A geoelectrical pre-study of Alvkarleby test embankment dam: 3D forward modelling and effects of structural constraints on the 3D inversion model of zoned embankment dams

Reyhaneh Norooz et al.

Summary: Electrical resistivity tomography has potential as a long-term monitoring method in embankment dams, but interpreting 3D geometry can be challenging. This study used prior information and laboratory measurements to enhance defect detection. Applying L1 and L2 methods with region control improved the accuracy of inversion, allowing for detection of small defects and their proximity.

JOURNAL OF APPLIED GEOPHYSICS (2021)

Article Computer Science, Interdisciplinary Applications

Deep generative models in inversion: The impact of the generator's nonlinearity and development of a new approach based on a variational autoencoder

Jorge Lopez-Alvis et al.

Summary: In this study, the authors review the conceptual framework of inversion with DGMs and point out that the nonlinearity in generative mapping between latent and original representations is mainly caused by changes in topology and curvature. They identify a conflict between the accuracy of generated patterns and the feasibility of gradient-based inversion, and propose a method that achieves a tradeoff between these two goals for better inversion results.

COMPUTERS & GEOSCIENCES (2021)

Article Geochemistry & Geophysics

Solving the frequency-domain acoustic VTI wave equation using physics-informed neural networks

Chao Song et al.

Summary: Frequency-domain wavefield solutions for the anisotropic acoustic wave equation can help describe the anisotropic nature of the Earth, but inverting the impedance matrix for such solutions can be computationally expensive. To address this challenge, the study proposes using physics-informed neural networks (PINNs) to obtain wavefield solutions for an acoustic wave equation in transversely isotropic (TI) media with a vertical axis of symmetry (VTI). By utilizing automatic differentiation in PINNs, numerical dispersion artefacts can be avoided, providing more accurate solutions.

GEOPHYSICAL JOURNAL INTERNATIONAL (2021)

Article Geochemistry & Geophysics

A geostatistical Markov chain Monte Carlo inversion algorithm for electrical resistivity tomography

Mattia Aleardi et al.

Summary: Electrical resistivity tomography inversion is commonly solved using deterministic gradient-based methods, but accurate uncertainty assessments are impeded by local linearization of the inverse operator. Numerical Markov chain Monte Carlo algorithms provide accurate uncertainty appraisals, but require appropriate recipes to reduce computational effort for field data applications. The key to probabilistic inversion is defining an appropriate prior distribution of model parameters that incorporate spatial constraints, Gaussian priors oversimplify the parameter distribution in the presence of multimodality.

NEAR SURFACE GEOPHYSICS (2021)

Article Geochemistry & Geophysics

Bayesian Elastic Full-Waveform Inversion Using Hamiltonian Monte Carlo

Lars Gebraad et al.

JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH (2020)

Article Geochemistry & Geophysics

The inversion of data from very large three-dimensional electrical resistivity tomography mobile surveys

M. H. Loke et al.

GEOPHYSICAL PROSPECTING (2020)

Article Geochemistry & Geophysics

Deep learning for fast simulation of seismic waves in complex media

Ben Moseley et al.

SOLID EARTH (2020)

Review Computer Science, Interdisciplinary Applications

Gradient-based deterministic inversion of geophysical data with generative adversarial networks: Is it feasible?

Eric Laloy et al.

COMPUTERS & GEOSCIENCES (2019)

Article Geochemistry & Geophysics

Hamiltonian Monte Carlo solution of tomographic inverse problems

Andreas Fichtner et al.

GEOPHYSICAL JOURNAL INTERNATIONAL (2019)

Article Geosciences, Multidisciplinary

Hamiltonian Nullspace Shuttles

Andreas Fichtner et al.

GEOPHYSICAL RESEARCH LETTERS (2019)

Article Geochemistry & Geophysics

Hamiltonian Monte Carlo Inversion of Seismic Sources in Complex Media

Andreas Fichtner et al.

JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH (2018)

Article Computer Science, Interdisciplinary Applications

Markov chain Monte Carlo simulation using the DREAM software package: Theory, concepts, and MATLAB implementation

Jasper A. Vrugt

ENVIRONMENTAL MODELLING & SOFTWARE (2016)

Article Geosciences, Multidisciplinary

Interpolation of landslide movements to improve the accuracy of 4D geoelectrical monitoring

Sebastian Uhlemann et al.

JOURNAL OF APPLIED GEOPHYSICS (2015)

Article Geochemistry & Geophysics

A Parallel Tempering algorithm for probabilistic sampling and multimodal optimization

Malcolm Sambridge

GEOPHYSICAL JOURNAL INTERNATIONAL (2014)

Article Geosciences, Multidisciplinary

Probabilistic electrical resistivity tomography of a CO2 sequestration analog

Tobias Lochbuehler et al.

JOURNAL OF APPLIED GEOPHYSICS (2014)

Article Computer Science, Interdisciplinary Applications

IP4DI: A software for time-lapse 2D/3D DC-resistivity and induced polarization tomography

M. Karaoulis et al.

COMPUTERS & GEOSCIENCES (2013)

Article Mathematics, Interdisciplinary Applications

Approximate Bayesian computation with differential evolution

Brandon M. Turner et al.

JOURNAL OF MATHEMATICAL PSYCHOLOGY (2012)

Article Mathematics, Applied

A STOCHASTIC NEWTON MCMC METHOD FOR LARGE-SCALE STATISTICAL INVERSE PROBLEMS WITH APPLICATION TO SEISMIC INVERSION

James Martin et al.

SIAM JOURNAL ON SCIENTIFIC COMPUTING (2012)

Article Geosciences, Multidisciplinary

Environmental monitoring of leaks using time-lapsed long electrode electrical resistivity

Dale F. Rucker et al.

JOURNAL OF APPLIED GEOPHYSICS (2011)

Article Mathematics, Applied

PARAMETER AND STATE MODEL REDUCTION FOR LARGE-SCALE STATISTICAL INVERSE PROBLEMS

Chad Lieberman et al.

SIAM JOURNAL ON SCIENTIFIC COMPUTING (2010)

Article Computer Science, Theory & Methods

DRAM: Efficient adaptive MCMC

Heikki Haario et al.

STATISTICS AND COMPUTING (2006)

Review Geochemistry & Geophysics

A review of the adjoint-state method for computing the gradient of a functional with geophysical applications

R. -E. Plessix

GEOPHYSICAL JOURNAL INTERNATIONAL (2006)

Review Geochemistry & Geophysics

Monte Carlo methods in geophysical inverse problems

M Sambridge et al.

REVIEWS OF GEOPHYSICS (2002)

Article Geosciences, Multidisciplinary

Direct sequential simulation and cosimulation

A Soares

MATHEMATICAL GEOLOGY (2001)

Article Statistics & Probability

An adaptive Metropolis algorithm

H Haario et al.

BERNOULLI (2001)

Article Geochemistry & Geophysics

Prior information, sampling distributions, and the curse of dimensionality

A Curtis et al.

GEOPHYSICS (2001)