Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published November 2017 | Supplemental Material + Submitted
Journal Article Open

Hierarchical Bayesian level set inversion

Abstract

The level set approach has proven widely successful in the study of inverse problems for interfaces, since its systematic development in the 1990s. Recently it has been employed in the context of Bayesian inversion, allowing for the quantification of uncertainty within the reconstruction of interfaces. However, the Bayesian approach is very sensitive to the length and amplitude scales in the prior probabilistic model. This paper demonstrates how the scale-sensitivity can be circumvented by means of a hierarchical approach, using a single scalar parameter. Together with careful consideration of the development of algorithms which encode probability measure equivalences as the hierarchical parameter is varied, this leads to well-defined Gibbs-based MCMC methods found by alternating Metropolisā€“Hastings updates of the level set function and the hierarchical parameter. These methods demonstrably outperform non-hierarchical Bayesian level set methods.

Additional Information

Ā© 2016 Springer Science+Business Media New York. Received: 13 January 2016; Accepted: 09 September 2016; First Online: 21 September 2016. AMS is grateful to DARPA, EPSRC and ONR for financial support. MMD is supported by the EPSRC-funded MASDOC graduate training program. The authors are grateful to Dan Simpson for helpful discussions. The authors are also grateful for discussions with Omiros Papaspiliopoulos about links with probit. The authors would also like to the two anonymous referees for their comments that have helped improve the quality of the paper. This research utilized Queen Mary's MidPlus computational facilities, supported by QMUL Research-IT and funded by EPSRC grant EP/K000128/1.

Attached Files

Submitted - 1601.03605v2.pdf

Supplemental Material - 11222_2016_9704_MOESM1_ESM.pdf

Files

1601.03605v2.pdf
Files (7.3 MB)
Name Size Download all
md5:0a7c21e2dd9ac4c92ca4852d3575a32d
6.6 MB Preview Download
md5:64527dafaacaf5a5d052cefc297f24ff
691.4 kB Preview Download

Additional details

Created:
August 21, 2023
Modified:
March 5, 2024