Skip to content

WISER: multimodal variational inference for full-waveform inversion without dimensionality reduction

License

Notifications You must be signed in to change notification settings

slimgroup/WISER.jl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

WISER: multimodal variational inference for full-waveform inversion without dimensionality reduction

Code to reproduce results in Ziyi Yin, Rafael Orozco, Felix J. Herrmann, "WISER: multimodal variational inference for full-waveform inversion without dimensionality reduction". Preprint on ArXiv. DOI: 10.48550/arXiv.2405.10327

WISER is an extension to WISE, published in Geophysics.

Software descriptions

All of the software packages used in this paper are fully open source, scalable, interoperable, and differentiable. The readers are welcome to learn about our software design principles from this open-access article.

Wave modeling

We use JUDI.jl for wave modeling and inversion, which calls the highly optimized propagators of Devito.

Conditional normalizing flows

We use InvertibleNetworks.jl to train the conditional normalizing flows (CNFs). This package implements memory-efficient invertible networks via hand-written derivatives. This ensures that these invertible networks are scalable to realistic 3D problems.

Installation

First, install Julia and Python. The scripts will contain package installation commands at the beginning so the packages used in the experiments will be automatically installed.

Scripts

wiser.jl runs the WISER algorithm in the paper to perform physics-based latent space correction.

The script utils.jl parses the input as keywords for each experiment.

The following keyword arguments can be used to reproduce the results in the WISER paper:

  • Case 1: julia wiser.jl --lr_wiser=0.004
  • Case 2: julia wiser.jl --test_snr=0.0 --amplitude=0.2 --lambda=10.0 --lr_pre=0.0004

LICENSE

The software used in this repository can be modified and redistributed according to MIT license.

Reference

If you use our software for your research, we appreciate it if you cite us following the bibtex in CITATION.bib.

Authors

This repository is written by Ziyi Yin and Rafael Orozco from the Seismic Laboratory for Imaging and Modeling (SLIM) at the Georgia Institute of Technology.

If you have any question, we welcome your contributions to our software by opening issue or pull request.

SLIM Group @ Georgia Institute of Technology, https://slim.gatech.edu.
SLIM public GitHub account, https://github.com/slimgroup.