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.

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.

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

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.

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.

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

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

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

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.