Neural‐network‐based regularization methods for inverse problems in imaging

A Habring, M Holler - GAMM‐Mitteilungen, 2024 - Wiley Online Library
This review provides an introduction to—and overview of—the current state of the art in
neural‐network based regularization methods for inverse problems in imaging. It aims to …

Solution of physics-based Bayesian inverse problems with deep generative priors

DV Patel, D Ray, AA Oberai - Computer Methods in Applied Mechanics and …, 2022 - Elsevier
Inverse problems are ubiquitous in nature, arising in almost all areas of science and
engineering ranging from geophysics and climate science to astrophysics and …

Trustworthy AI for human-centric smart manufacturing: A survey

D Li, S Liu, B Wang, C Yu, P Zheng, W Li - Journal of Manufacturing …, 2025 - Elsevier
Human-centric smart manufacturing (HCSM) envisions a symbiotic relationship between
humans and machines, leveraging human capability and Artificial Intelligence (AI)'s …

Bayesian geophysical inversion using invertible neural networks

X Zhang, A Curtis - Journal of Geophysical Research: Solid …, 2021 - Wiley Online Library
Constraining geophysical models with observed data usually involves solving nonlinear and
nonunique inverse problems. Neural mixture density networks (MDNs) provide an efficient …

Reliable amortized variational inference with physics-based latent distribution correction

A Siahkoohi, G Rizzuti, R Orozco, FJ Herrmann - Geophysics, 2023 - library.seg.org
Bayesian inference for high-dimensional inverse problems is computationally costly and
requires selecting a suitable prior distribution. Amortized variational inference addresses …

WISE: Full-waveform variational inference via subsurface extensions

Z Yin, R Orozco, M Louboutin, FJ Herrmann - Geophysics, 2024 - library.seg.org
We introduce a probabilistic technique for full-waveform inversion, using variational
inference and conditional normalizing flows to quantify uncertainty in migration-velocity …

Preconditioned training of normalizing flows for variational inference in inverse problems

A Siahkoohi, G Rizzuti, M Louboutin, PA Witte… - arXiv preprint arXiv …, 2021 - arxiv.org
Obtaining samples from the posterior distribution of inverse problems with expensive
forward operators is challenging especially when the unknowns involve the strongly …

The efficacy and generalizability of conditional GANs for posterior inference in physics-based inverse problems

D Ray, H Ramaswamy, DV Patel, AA Oberai - arXiv preprint arXiv …, 2022 - arxiv.org
In this work, we train conditional Wasserstein generative adversarial networks to effectively
sample from the posterior of physics-based Bayesian inference problems. The generator is …

Deep Bayesian inference for seismic imaging with tasks

A Siahkoohi, G Rizzuti, FJ Herrmann - Geophysics, 2022 - library.seg.org
We use techniques from Bayesian inference and deep neural networks to translate
uncertainty in seismic imaging to uncertainty in tasks performed on the image, such as …

Using convolutional neural networks to develop starting models for near-surface 2-D full waveform inversion

JP Vantassel, K Kumar, BR Cox - Geophysical Journal …, 2022 - academic.oup.com
Non-invasive subsurface imaging using full waveform inversion (FWI) has the potential to
fundamentally change near-surface (< 30 m) site characterization by enabling the recovery …