CaltechAUTHORS
  A Caltech Library Service

HypoSVI: Hypocentre inversion with Stein variational inference and physics informed neural networks

Smith, Jonthan D. and Ross, Zachary E. and Azizzadenesheli, Kamyar and Muir, Jack B. (2022) HypoSVI: Hypocentre inversion with Stein variational inference and physics informed neural networks. Geophysical Journal International, 228 (1). pp. 698-710. ISSN 0956-540X. doi:10.1093/gji/ggab309. https://resolver.caltech.edu/CaltechAUTHORS:20220105-592865000

[img] PDF - Published Version
See Usage Policy.

9MB
[img] Archive (ZIP) (Supplementary data) - Supplemental Material
See Usage Policy.

880kB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20220105-592865000

Abstract

We introduce a scheme for probabilistic hypocentre inversion with Stein variational inference. Our approach uses a differentiable forward model in the form of a physics informed neural network, which we train to solve the Eikonal equation. This allows for rapid approximation of the posterior by iteratively optimizing a collection of particles against a kernelized Stein discrepancy. We show that the method is well-equipped to handle highly multimodal posterior distributions, which are common in hypocentral inverse problems. A suite of experiments is performed to examine the influence of the various hyperparameters. Once trained, the method is valid for any seismic network geometry within the study area without the need to build traveltime tables. We show that the computational demands scale efficiently with the number of differential times, making it ideal for large-N sensing technologies like Distributed Acoustic Sensing. The techniques outlined in this manuscript have considerable implications beyond just ray tracing procedures, with the work flow applicable to other fields with computationally expensive inversion procedures such as full waveform inversion.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1093/gji/ggab309DOIArticle
https://scedc.caltech.eduRelated ItemSouthern California Earthquake Data Center
https://github.com/Ulvetanna/HypoSVIRelated ItemHypoSVI
ORCID:
AuthorORCID
Smith, Jonthan D.0000-0002-1684-1344
Ross, Zachary E.0000-0002-6343-8400
Azizzadenesheli, Kamyar0000-0001-8507-1868
Muir, Jack B.0000-0003-2617-3420
Additional Information:© The Author(s) 2021. Published by Oxford University Press on behalf of The Royal Astronomical Society. This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model). Published: 11 August 2021. This project was partly supported by a grant from the United States Geological Survey (USGS). We would like to thank Jack Wilding and Bing Q. Li for interesting discussions about the implementation and software usage. We would like to thank our reviewers, Anya M. Reading and Anandaroop Ray, as well as the editor Andrew Valentine, for useful comments/corrections during the review process. Data Availability: The earthquake phase arrival and station locations can be downloaded from the Southern California Earthquake Data Center https://scedc.caltech.eduhttps://scedc.caltech.edu. HypoSVI is available at the Github repository https://github.com/Ulvetanna/HypoSVI, with additional runable Colab code supplied at this Github url. The NonLinLoc control file used to generate the manuscript earthquake catalogue can be found in the Supporting Information.
Group:Seismological Laboratory
Funders:
Funding AgencyGrant Number
USGSUNSPECIFIED
Subject Keywords:Computational seismology; Statistical Seismology; Theoretical Seismology
Issue or Number:1
DOI:10.1093/gji/ggab309
Record Number:CaltechAUTHORS:20220105-594930200
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20220105-592865000
Official Citation:Jonthan D Smith, Zachary E Ross, Kamyar Azizzadenesheli, Jack B Muir, HypoSVI: Hypocentre inversion with Stein variational inference and physics informed neural networks, Geophysical Journal International, Volume 228, Issue 1, January 2022, Pages 698–710, https://doi.org/10.1093/gji/ggab309
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:112718
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:08 Jan 2022 22:06
Last Modified:09 Jan 2022 21:46

Repository Staff Only: item control page