Bayesian geophysical inversion with Gaussian process machine learning and trans-D Markov chain Monte Carlo
Open Access
- 11 November 2019
- journal article
- research article
- Published by Taylor & Francis in ASEG Extended Abstracts
- Vol. 2019 (1) , 1-5
Abstract
A key aspect of geophysical inversion is the ability to model the earth with a low dimensional representation. There exist various approaches to solve the inverse problem. However, most methods do not automatically adapt inverse model complexity or the number of active model parameters as dictated by data noise and sparse receiver coverage, do not quantify inverse model uncertainty or do not work equally well for 1D, 2D or 3D earth models. Low frequency electromagnetic (EM) inversion for example, can require for 3D problems upward of 106 cells to forward model. Only a small fraction of these cells is effectively resolvable and there are significant trade-offs between them. To address these limitations, we present a novel approach to earth model parametrization by using a Gaussian Processes (GP) machine learning (ML) technique, coupled with a parsimonious Bayesian trans-dimensional (trans-D) Markov chain Monte Carlo (McMC) sampling scheme. One aspect that sets our approach apart from recent spatial dimension agnostic algorithms in the trans-D or ML literature is the ability to specify inversion property priors directly, as opposed to doing so in a transform domain of the property. Finally, we note that our method falls in the category of ML approaches that do not attempt to learn the physics of the process, but instead learn the representation of parameter values through a misfit function. We apply the trans-D-GP method to a 1D controlled source electromagnetic (CSEM) and 2D non-linear regression problem, using actual field data from the Northwest Australian Shelf for the former. The key advantages in using our method are the simplicity of prior specification, parsimonious low dimensional representations, and ease of representing large-scale models in 1D, 2D or even 3D with the same parametrization and computer code.Keywords
This publication has 32 references indexed in Scilit:
- Bayesian geophysical inversion with Gaussian process machine learning and trans-D Markov chain Monte CarloASEG Extended Abstracts, 2019
- Inverse problems: From regularization to Bayesian inferenceWIREs Computational Statistics, 2018
- Probabilistic surface reconstruction from multiple data sets: An example for the Australian MohoJournal of Geophysical Research, 2012
- Inference of abrupt changes in noisy geochemical records using transdimensional changepoint modelsEarth and Planetary Science Letters, 2011
- Gaussian Processes for Machine Learning2005
- Parsimonious Bayesian Markov chain Monte Carlo inversion in a nonlinear geophysical problemGeophysical Journal International, 2002
- Use of marine controlled‐source electromagnetic sounding for sub‐basalt explorationGeophysical Prospecting, 2000
- Three-dimensional magnetotelluric inversion using non-linear conjugate gradientsGeophysical Journal International, 2000
- Controlled electromagnetic sources for measuring electrical conductivity beneath the oceans: 1. Forward problem and model studyJournal of Geophysical Research, 1982
- Electromagnetic active source sounding near the East Pacific RiseGeophysical Research Letters, 1981