Reconstructing Richtmyer–Meshkov instabilities from noisy radiographs using low dimensional features and attention-based neural networks

DA Serino, ML Klasky, BT Nadiga, X Xu, T Wilcox - Optics Express, 2024 - opg.optica.org
We develop an ML-based approach for density reconstruction based on transformer neural
networks. This approach is demonstrated in the setting of ICF-like double shell …

Sparse-view cone beam CT reconstruction using data-consistent supervised and adversarial learning from scarce training data

A Lahiri, G Maliakal, ML Klasky… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Reconstruction of CT images from a limited set of projections through an object is important
in several applications ranging from medical imaging to industrial settings. As the number of …

Learning Robust Features for Scatter Removal and Reconstruction in Dynamic ICF X-Ray Tomography

S Gautam, ML Klasky, BT Nadiga, T Wilcox… - arxiv preprint arxiv …, 2024 - arxiv.org
Density reconstruction from X-ray projections is an important problem in radiography with
key applications in scientific and industrial X-ray computed tomography (CT). Often, such …

Learning physical unknowns from hydrodynamic shock and material interface features in ICF capsule implosions

DA Serino, E Bell, M Klasky, BS Southworth… - arxiv preprint arxiv …, 2024 - arxiv.org
In high energy density physics (HEDP) and inertial confinement fusion (ICF), predictive
modeling is complicated by uncertainty in parameters that characterize various aspects of …

Physics-driven learning of Wasserstein GAN for density reconstruction in dynamic tomography

Z Huang, M Klasky, T Wilcox, S Ravishankar - Applied Optics, 2022 - opg.optica.org
Object density reconstruction from projections containing scattered radiation and noise is of
critical importance in many applications. Existing scatter correction and density …

Improving Radiography Machine Learning Workflows via Metadata Management for Training Data Selection

M Reid, C Sweeney, O Korobkin - arxiv preprint arxiv:2408.12655, 2024 - arxiv.org
Most machine learning models require many iterations of hyper-parameter tuning, feature
engineering, and debugging to produce effective results. As machine learning models …

Stochastic parameterization of column physics using generative adversarial networks

BT Nadiga, X Sun, C Nash - Environmental Data Science, 2022 - cambridge.org
We demonstrate the use of a probabilistic machine-learning technique to develop stochastic
parameterizations of atmospheric column physics. After suitable preprocessing of NASA's …

[HTML][HTML] Using deep machine learning to interpret proton radiography data from a pulsed power experiment

VP Chiravalle - AIP Advances, 2023 - pubs.aip.org
Deep machine learning is used to analyze a proton radiograph from a tin pulsed power
experiment and determine density values for each pixel in the image. Two promising …

An End-to-End Learning Approach for Subpixel Feature Extraction

X Xu, JA Fessler, M Klasky, GS Sidharth… - Imaging Systems and …, 2023 - opg.optica.org
An End-to-End Learning Approach for Subpixel Feature Extraction Page 1 An End-to-End
Learning Approach for Subpixel Feature Extraction **aojian Xu1, *, Jeffrey A. Fessler1, Marc …

Scatter Removal in Dynamic X-Ray Tomography using Learned Robust Features

S Gautam, ML Klasky, S Ravishankar - … Optical Sensing and Imaging, 2023 - opg.optica.org
A challenging problem in industrial radiography is accurate density reconstructions from X-
ray projections corrupted by noise, scatter, etc. We propose a deep learning-based …