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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Ziyi, Orozco, Rafael, Herrmann, Felix J.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909416317517824
author Yin, Ziyi
Orozco, Rafael
Herrmann, Felix J.
author_facet Yin, Ziyi
Orozco, Rafael
Herrmann, Felix J.
contents We present a semi-amortized variational inference framework designed for computationally feasible uncertainty quantification in 2D full-waveform inversion to explore the multimodal posterior distribution without dimensionality reduction. The framework is called WISER, short for full-Waveform variational Inference via Subsurface Extensions with Refinements. WISER leverages the power of generative artificial intelligence to perform approximate amortized inference that is low-cost albeit showing an amortization gap. This gap is closed through non-amortized refinements that make frugal use of acoustic wave physics. Case studies illustrate that WISER is capable of full-resolution, computationally feasible, and reliable uncertainty estimates of velocity models and imaged reflectivities.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10327
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WISER: multimodal variational inference for full-waveform inversion without dimensionality reduction
Yin, Ziyi
Orozco, Rafael
Herrmann, Felix J.
Geophysics
Computational Engineering, Finance, and Science
We present a semi-amortized variational inference framework designed for computationally feasible uncertainty quantification in 2D full-waveform inversion to explore the multimodal posterior distribution without dimensionality reduction. The framework is called WISER, short for full-Waveform variational Inference via Subsurface Extensions with Refinements. WISER leverages the power of generative artificial intelligence to perform approximate amortized inference that is low-cost albeit showing an amortization gap. This gap is closed through non-amortized refinements that make frugal use of acoustic wave physics. Case studies illustrate that WISER is capable of full-resolution, computationally feasible, and reliable uncertainty estimates of velocity models and imaged reflectivities.
title WISER: multimodal variational inference for full-waveform inversion without dimensionality reduction
topic Geophysics
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2405.10327