Stochastic Seismic Waveform Inversion Using Generative Adversarial Networks As A Geological Prior

Mosser, Lukas; Dubrule, Olivier; Blunt, Martin J.

doi:10.3997/2214-4609.201803018

Cited by 43 publications

(23 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a clearly Using the same type of network with a training set of smoothed velocities, we obtain e mean velocities and i standard deviations advantageous strategy for the future of neural network tomography is to invest effort in finding and using more sophisticated and correct prior information [40]. Recent efforts in this direction include [41] who use expert elicitation to constrain prior multipoint geostatistics, Mosser et al [42] who use neural networks to parametrise geological prior information and Nawaz and Curtis [30][31][32] who use Markovian models and variational methods with embedded neural and mixture density networks to combine geological and geophysical information; these various directions appear to be strategically important for the future of this field. We illustrate the differences in the KL divergence values in Fig.…”

Section: Discussionmentioning

confidence: 99%

Probabilistic neural network-based 2D travel-time tomography

Earp

Curtis

2020

Neural Comput & Applic

View full text Add to dashboard Cite

Travel-time tomography for the velocity structure of a medium is a highly nonlinear and nonunique inverse problem. Monte Carlo methods are becoming increasingly common choices to provide probabilistic solutions to tomographic problems but those methods are computationally expensive. Neural networks can often be used to solve highly nonlinear problems at a much lower computational cost when multiple inversions are needed from similar data types. We present the first method to perform fully nonlinear, rapid and probabilistic Bayesian inversion of travel-time data for 2D velocity maps using a mixture density network. We compare multiple methods to estimate probability density functions that represent the tomographic solution, using different sets of prior information and different training methodologies. We demonstrate the importance of prior information in such high-dimensional inverse problems due to the curse of dimensionality: unrealistically informative prior probability distributions may result in better estimates of the mean velocity structure; however, the uncertainties represented in the posterior probability density functions then contain less information than is obtained when using a less informative prior. This is illustrated by the emergence of uncertainty loops in posterior standard deviation maps when inverting travel-time data using a less informative prior, which are not observed when using networks trained on prior information that includes (unrealistic) a priori smoothness constraints in the velocity models. We show that after an expensive program of network training, repeated high-dimensional, probabilistic tomography is possible on timescales of the order of a second on a standard desktop computer.

show abstract

Section: Discussionmentioning

confidence: 99%

Probabilistic neural network-based 2D travel-time tomography

Earp

Curtis

2020

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…In particular, [39] uses earthquake data to accurately predict 1-D velocity models, and applications in [5,34,27,53] employ data collected in seismic surveys for structural model building with interest in hydrocarbon exploration. In addition, the study in [37] applies a ANN to infer the prior distribution of acoustic properties of a geological model, that is later improved by full waveform inversion. This work includes promising applications to a synthetic reservoir-scale dataset of channel bodies.…”

Section: Machine Learning Applications To Earthquake Datamentioning

confidence: 99%

Artificial Neural Networks as Emerging Tools for Earthquake Detection

Rojas

Otero

Alvarado

et al. 2019

CyS

View full text Add to dashboard Cite

As seismic networks continue to spread and monitoring sensors become more efficient, the abundance of data highly surpasses the processing capabilities of earthquake interpretation analysts. Earthquake catalogs are fundamental for fault system studies, event modellings, seismic hazard assessment, forecasting, and ultimately, for mitigating the seismic risk. These have fueled the research for the automation of interpretation tasks such as event detection, event identification, hypocenter location, and source mechanism analysis. Over the last forty years, traditional algorithms based on quantitative analyses of seismic traces in the time or frequency domain, have been developed to assist interpretation. Alternatively, recent advances are related to the application of Artificial Neural Networks (ANNs), a subset of machine learning techniques that is pushing the state-of-the-art forward in many areas. Appropriated trained ANN can mimic the interpretation abilities of best human analysts, avoiding the individual weaknesses of most traditional algorithms, and spending modest computational resources at the operational stage. In this paper, we will survey the latest ANN applications to the automatic interpretation of seismic data, with a special focus on earthquake detection, and the estimation of onset times. For a comparative framework, we give an insight into the labor of human interpreters, who may face uncertainties in the case of small magnitude earthquakes.

show abstract

“…Moreover, solving (2) can effectively regularize the solution of the compressed sensing problem, significantly outperforming sparsity-based algorithms in the low measurements regime. Generative network based inversion algorithms have been subsequently developed for a variety of signal recovery problems, demonstrating their potential to outperform inversion algorithms based on non-learned (hand-crafted) priors [12,24,23,15,26,21]. For a recent overview see [25].…”

Section: Introductionmentioning

confidence: 99%

Signal Recovery with Non-Expansive Generative Network Priors

Cocola¹

2022

Preprint

View full text Add to dashboard Cite

We study compressive sensing with a deep generative network prior. Initial theoretical guarantees for efficient recovery from compressed linear measurements have been developed for signals in the range of a ReLU network with Gaussian weights and logarithmic expansivity: that is when each layer is larger than the previous one by a logarithmic factor. It was later shown that constant expansivity is sufficient for recovery. It has remained open whether the expansivity can be relaxed allowing for networks with contractive layers, as often the case of real generators. In this work we answer this question, proving that a signal in the range of a Gaussian generative network can be recovered from a few linear measurements provided that the width of the layers is proportional to the input layer size (up to log factors). This condition allows the generative network to have contractive layers. Our result is based on showing that Gaussian matrices satisfy a matrix concentration inequality, which we term Range Restricted Weight Distribution Condition (R2WDC), and weakens the Weight Distribution Condition (WDC) upon which previous theoretical guarantees were based. The WDC has also been used to analyze other signal recovery problems with generative network priors. By replacing the WDC with the R2WDC, we are able to extend previous results for signal recovery with expansive generative network priors to non-expansive ones. We discuss these extensions for phase retrieval, denoising, and spiked matrix recovery.

show abstract

Stochastic Seismic Waveform Inversion Using Generative Adversarial Networks As A Geological Prior

Cited by 43 publications

References 0 publications

Probabilistic neural network-based 2D travel-time tomography

Probabilistic neural network-based 2D travel-time tomography

Artificial Neural Networks as Emerging Tools for Earthquake Detection

Signal Recovery with Non-Expansive Generative Network Priors

Contact Info

Product

Resources

About