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

Serino, Daniel A.; Klasky, Marc Louis; Nadiga, Balasubramanya T.; Xu, Xiaojian; Wilcox, Trevor

doi:10.1364/oe.538495

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

Journal Article · 13 November 2024 · Optics Express

DOI: https://doi.org/10.1364/oe.538495 · OSTI ID:2511271

^[1];

^[1]; Xu, Xiaojian ^[2];

^[1]

Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Univ. of Michigan, Ann Arbor, MI (United States)

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 hydrodynamic simulations wherein the parameters related to material properties and initial conditions are varied. The new method can robustly recover the complex topologies given by the Richtmyer-Meshkoff instability (RMI) from a sequence of hydrodynamic features derived from radiographic images corrupted with blur, scatter, and noise. A noise model is developed to characterize errors in extracting features from synthetic radiographs of the simulated density field. The key component of the network is a transformer encoder that acts on a sequence of features extracted from noisy radiographs. This encoder includes numerous self-attention layers that act to learn temporal dependencies in the input sequences and increase the expressiveness of the model. This approach is shown to exhibit an excellent ability to accurately recover the RMI growth rates, despite the gas-metal interface being greatly obscured by radiographic noise. Our approach can be applied in a broad array of fields involving shock physics and material science.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 2511271

Report Number(s):: LA-UR--24-28305

Journal Information:: Optics Express, Journal Name: Optics Express Journal Issue: 24 Vol. 32; ISSN 1094-4087

Publisher:: Optical Society of America (OSA)Copyright Statement

Country of Publication:: United States

Language:: English

References (45)

Instability of the interface of two gases accelerated by a shock wave Meshkov, E. E. Fluid Dynamics, Vol. 4, Issue 5 https://doi.org/10.1007/BF01015969	journal	January 1972
Enabling machine learning in X-ray-based procedures via realistic simulation of image formation Unberath, Mathias; Zaech, Jan-Nico; Gao, Cong International Journal of Computer Assisted Radiology and Surgery, Vol. 14, Issue 9 https://doi.org/10.1007/s11548-019-02011-2	journal	June 2019
Estimation of Metal Strength at Very High Rates Using Free-Surface Richtmyer–Meshkov Instabilities Prime, Michael B.; Buttler, William T.; Buechler, Miles A. Journal of Dynamic Behavior of Materials, Vol. 3, Issue 2 https://doi.org/10.1007/s40870-017-0103-9	journal	March 2017
An overview of Rayleigh-Taylor instability Sharp, D. H. Physica D: Nonlinear Phenomena, Vol. 12, Issue 1-3 https://doi.org/10.1016/0167-2789(84)90510-4	journal	July 1984
The effectiveness of deep learning vs. traditional methods for lung disease diagnosis using chest X-ray images: A systematic review Sajed, Samira; Sanati, Amir; Garcia, Jorge Esparteiro Applied Soft Computing, Vol. 147 https://doi.org/10.1016/j.asoc.2023.110817	journal	November 2023
Premixed flame stability and transition to detonation in a supersonic combustor Goodwin, Gabriel B.; Oran, Elaine S. Combustion and Flame, Vol. 197 https://doi.org/10.1016/j.combustflame.2018.07.008	journal	November 2018
A matrix-free hyperviscosity formulation for high-order ALE hydrodynamics Bello-Maldonado, Pedro D.; Kolev, Tzanio V.; Rieben, Robert N. Computers & Fluids, Vol. 205 https://doi.org/10.1016/j.compfluid.2020.104577	journal	June 2020
Rayleigh–Taylor and Richtmyer–Meshkov instabilities: A journey through scales Zhou, Ye; Williams, Robin J. R.; Ramaprabhu, Praveen Physica D: Nonlinear Phenomena, Vol. 423 https://doi.org/10.1016/j.physd.2020.132838	journal	September 2021
Rayleigh–Taylor and Richtmyer–Meshkov instability induced flow, turbulence, and mixing. II Zhou, Ye Physics Reports, Vol. 723-725 https://doi.org/10.1016/j.physrep.2017.07.008	journal	December 2017
The ASTRA Toolbox: A platform for advanced algorithm development in electron tomography van Aarle, Wim; Palenstijn, Willem Jan; De Beenhouwer, Jan Ultramicroscopy, Vol. 157 https://doi.org/10.1016/j.ultramic.2015.05.002	journal	October 2015
Experimental and numerical investigation of the Richtmyer–Meshkov instability under re-shock conditions Leinov, E.; Malamud, G.; Elbaz, Y. Journal of Fluid Mechanics, Vol. 626 https://doi.org/10.1017/S0022112009005904	journal	May 2009
Kelvin–Helmholtz instability of finite amplitude Drazin, P. G. Journal of Fluid Mechanics, Vol. 42, Issue 2 https://doi.org/10.1017/S0022112070001295	journal	June 1970
Richtmyer–Meshkov instability growth: experiment, simulation and theory Holmes, Richard L.; Dimonte, Guy; Fryxell, Bruce Journal of Fluid Mechanics, Vol. 389 https://doi.org/10.1017/S0022112099004838	journal	June 1999
Attentional Ptycho-Tomography (APT) for three-dimensional nanoscale X-ray imaging with minimal data acquisition and computation time Kang, Iksung; Wu, Ziling; Jiang, Yi Light: Science & Applications, Vol. 12, Issue 1 https://doi.org/10.1038/s41377-023-01181-8	journal	May 2023
Representation of a Function by Its Line Integrals, with Some Radiological Applications Cormack, A. M. Journal of Applied Physics, Vol. 34, Issue 9 https://doi.org/10.1063/1.1729798	journal	September 1963
Absolute Hugoniot measurements from a spherically convergent shock using x-ray radiography Swift, Damian C.; Kritcher, Andrea L.; Hawreliak, James A. Review of Scientific Instruments, Vol. 89, Issue 5 https://doi.org/10.1063/1.5032142	journal	May 2018
Experimental study of energy transfer in double shell implosions Merritt, E. C.; Sauppe, J. P.; Loomis, E. N. Physics of Plasmas, Vol. 26, Issue 5 https://doi.org/10.1063/1.5086674	journal	May 2019
Hydrodynamic target response to an induced spatial incoherence‐smoothed laser beam Emery, M. H.; Gardner, J. H.; Lehmberg, R. H. Physics of Fluids B: Plasma Physics, Vol. 3, Issue 9 https://doi.org/10.1063/1.859976	journal	September 1991
A numerical study of Richtmyer–Meshkov instability driven by cylindrical shocks Zhang, Qiang; Graham, Mary Jane Physics of Fluids, Vol. 10, Issue 4 https://doi.org/10.1063/1.869624	journal	April 1998
Progress toward Ignition and Burn Propagation in Inertial Confinement Fusion Lindl, John D.; McCrory, Robert L.; Campbell, E. Michael Physics Today, Vol. 45, Issue 9 https://doi.org/10.1063/1.881318	journal	September 1992
An Evaluation of the Richtmyer‐Meshkov Instability in Supernova Remnant Formation Kane, J.; Drake, R. P.; Remington, B. A. The Astrophysical Journal, Vol. 511, Issue 1 https://doi.org/10.1086/306685	journal	January 1999
Improved scatter correction using adaptive scatter kernel superposition Sun, M.; Star-Lack, J. M. Physics in Medicine and Biology, Vol. 55, Issue 22 https://doi.org/10.1088/0031-9155/55/22/007	journal	October 2010
The instability of liquid surfaces when accelerated in a direction perpendicular to their planes. I Taylor, Geoffrey Ingram Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences, Vol. 201, Issue 1065, p. 192-196 https://doi.org/10.1098/rspa.1950.0052	journal	March 1950
Tantalum strength at extreme strain rates from impact-driven Richtmyer-Meshkov instabilities Prime, Michael B.; Buttler, William T.; Fensin, Saryu J. Physical Review E, Vol. 100, Issue 5 https://doi.org/10.1103/PhysRevE.100.053002	journal	November 2019
Surface-wave instabilities, period doubling, and an approximate universal boundary of bubble stability at the upper threshold of sonoluminescence Holzfuss, Joachim Physical Review E, Vol. 77, Issue 6 https://doi.org/10.1103/PhysRevE.77.066309	journal	June 2008
2D X-Ray Radiography of Imploding Capsules at the National Ignition Facility Rygg, J. R.; Jones, O. S.; Field, J. E. Physical Review Letters, Vol. 112, Issue 19 https://doi.org/10.1103/PhysRevLett.112.195001	journal	May 2014
Propagation of a Rippled Shock Wave Driven by Nonuniform Laser Ablation Ishizaki, R.; Nishihara, K. Physical Review Letters, Vol. 78, Issue 10 https://doi.org/10.1103/PhysRevLett.78.1920	journal	March 1997
Saturation of Laser Imprint on Ablatively Driven Plastic Targets Taylor, R. J.; Velikovich, A. L.; Dahlburg, J. P. Physical Review Letters, Vol. 79, Issue 10 https://doi.org/10.1103/PhysRevLett.79.1861	journal	September 1997
Validation of an Instability Growth Model Using Particle Image Velocimetry Measurements Prestridge, K.; Vorobieff, P.; Rightley, P. M. Physical Review Letters, Vol. 84, Issue 19 https://doi.org/10.1103/PhysRevLett.84.4353	journal	May 2000
Statistical image reconstruction for polyenergetic X-ray computed tomography Elbakri, I. A.; Fessler, J. A. IEEE Transactions on Medical Imaging, Vol. 21, Issue 2 https://doi.org/10.1109/42.993128	journal	January 2002
Edge-preserving tomographic reconstruction with nonlocal regularization Yu, D. F.; Fessler, J. A. IEEE Transactions on Medical Imaging, Vol. 21, Issue 2 https://doi.org/10.1109/42.993134	journal	January 2002
Globally convergent edge-preserving regularized reconstruction: an application to limited-angle tomography Delaney, A. H.; Bresler, Y. IEEE Transactions on Image Processing, Vol. 7, Issue 2 https://doi.org/10.1109/83.660997	journal	January 1998
Dynamic X-ray computed tomography Bonnet, S.; Koenig, A.; Roux, S. Proceedings of the IEEE, Vol. 91, Issue 10 https://doi.org/10.1109/JPROC.2003.817868	journal	October 2003
Image Reconstruction: From Sparsity to Data-Adaptive Methods and Machine Learning Ravishankar, Saiprasad; Ye, Jong Chul; Fessler, Jeffrey A. Proceedings of the IEEE, Vol. 108, Issue 1 https://doi.org/10.1109/JPROC.2019.2936204	journal	January 2020
Investigation of the Character of the Equilibrium of an Incompressible Heavy Fluid of Variable Density Proceedings of the London Mathematical Society, Vol. s1-14, Issue 1 https://doi.org/10.1112/plms/s1-14.1.170	journal	November 1882
T HE R ICHTMYER -M ESHKOV I NSTABILITY Brouillette, Martin Annual Review of Fluid Mechanics, Vol. 34, Issue 1 https://doi.org/10.1146/annurev.fluid.34.090101.162238	journal	January 2002
Physics-driven learning of Wasserstein GAN for density reconstruction in dynamic tomography Huang, Zhishen; Klasky, Marc; Wilcox, Trevor Applied Optics, Vol. 61, Issue 10 https://doi.org/10.1364/AO.446188	journal	March 2022
Dynamic tomography with a priori information Myers, Glenn R.; Kingston, Andrew M.; Varslot, Trond K. Applied Optics, Vol. 50, Issue 20 https://doi.org/10.1364/AO.50.003685	journal	January 2011
Practical cone-beam algorithm Feldkamp, L. A.; Davis, L. C.; Kress, J. W. Journal of the Optical Society of America A, Vol. 1, Issue 6 https://doi.org/10.1364/JOSAA.1.000612	journal	January 1984
Local models for scatter estimation and descattering in polyenergetic X-ray tomography McCann, Michael T.; Klasky, Marc L.; Schei, Jennifer L. Optics Express, Vol. 29, Issue 18 https://doi.org/10.1364/OE.433993	journal	January 2021
High-precision inversion of dynamic radiography using hydrodynamic features Hossain, Maliha; Nadiga, Balasubramanya T.; Korobkin, Oleg Optics Express, Vol. 30, Issue 9 https://doi.org/10.1364/OE.457497	journal	April 2022
Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits Kang, Iksung; Jiang, Yi; Holler, Mirko Optica, Vol. 10, Issue 8 https://doi.org/10.1364/OPTICA.492666	journal	July 2023
A computational framework for edge-preserving regularization in dynamic inverse problems Pasha, Mirjeta; Saibaba, Arvind K.; Gazzola, Silvia ETNA - Electronic Transactions on Numerical Analysis, Vol. 58 https://doi.org/10.1553/etna_vol58s486	journal	January 2023
Dynamic Tomographic Reconstruction of Deforming Volumes Jailin, Clément; Roux, Stéphane Materials, Vol. 11, Issue 8 https://doi.org/10.3390/ma11081395	journal	August 2018
Degradation-Aware Deep Learning Framework for Sparse-View CT Reconstruction Sun, Chang; Liu, Yitong; Yang, Hongwen Tomography, Vol. 7, Issue 4 https://doi.org/10.3390/tomography7040077	journal	December 2021

Similar Records

Direct simulation Monte Carlo investigation of the Richtmyer-Meshkov instability

Journal Article · 2015 · Physics of Fluids · OSTI ID:1235325

Gallis, Michail A.; Koehler, Timothy P.; Torczynski, John R.; +1 more

Suppression of Richtmyer-Meshkov Instability via Special Pairs of Shocks and Phase Transitions

Journal Article · 2024 · Physical Review Letters · OSTI ID:2406150

Schill, W. J.; Armstrong, M. R.; Nguyen, J. H.; +9 more

Synchrotron radiography of Richtmyer–Meshkov instability driven by exploding wire arrays

Journal Article · 2023 · Physics of Fluids · OSTI ID:2565091

Strucka, J.; Lukic, B.; Koerner, M.; +10 more

Related Subjects

47 OTHER INSTRUMENTATION

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

Citation Formats

References (45)

Similar Records

Related Subjects