Journal
GEOPHYSICAL JOURNAL INTERNATIONAL
Volume 230, Issue 2, Pages 916-931Publisher
OXFORD UNIV PRESS
DOI: 10.1093/gji/ggac100
Keywords
Inverse theory; Neural networks; fuzzy logic; Probability distributions; Statistical methods; Machine learning
Categories
Funding
- Australian National University
- CSIRO Deep Earth Imaging Future Science Platform
- Australian Research Council (ARC) [DP200100053, DE180100040]
- Australian Government
- Australian Research Council [DE180100040, DP200100053] Funding Source: Australian Research Council
Ask authors/readers for more resources
This paper discusses the use of generative models to overcome challenges in the application of Monte Carlo methods in geophysics. Generative models can learn probability distributions from given samples and generate new samples, which allows for compression of data and faster computation. The use of generative models opens up new possibilities for improving storage and communication of results, enhancing numerical integration calculation, and assessing the convergence of Monte Carlo procedures.
Monte Carlo methods are widespread in geophysics and have proved to be powerful in non-linear inverse problems. However, they are associated with significant practical challenges, including long calculation times, large output ensembles of Earth models, and difficulties in the appraisal of the results. This paper addresses some of these challenges using generative models, a family of tools that have recently attracted much attention in the machine learning literature. Generative models can, in principle, learn a probability distribution from a set of given samples and also provide a means for rapid generation of new samples which follow that approximated distribution. These two features make them well suited for application to the outputs of Monte Carlo algorithms. In particular, training a generative model on the posterior distribution of a Bayesian inference problem provides two main possibilities. First, the number of parameters in the generative model is much smaller than the number of values stored in the ensemble, leading to large compression rates. Secondly, once trained, the generative model can be used to draw any number of samples, thereby eliminating the dependence on an often large and unwieldy ensemble. These advantages pave new pathways for the use of Monte Carlo ensembles, including improved storage and communication of the results, enhanced calculation of numerical integrals, and the potential for convergence assessment of the Monte Carlo procedure. Here, these concepts are initially demonstrated using a simple synthetic example that scales into higher dimensions. They are then applied to a large ensemble of shear wave velocity models of the core-mantle boundary, recently produced in a Monte Carlo study. These examples demonstrate the effectiveness of using generative models to approximate posterior ensembles, and indicate directions to address various challenges in Monte Carlo inversion.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available