Enhanced analysis of experimental x-ray spectra through deep learning

Mariscal, D. A.; Krauland, C. M.; Djordjević, B. Z.; Scott, G. G.; Simpson, R. A.; Grace, E. S.; Swanson, K.; Ma, T.

doi:10.1063/5.0097777

Enhanced analysis of experimental x-ray spectra through deep learning

Journal Article · Fri Sep 16 00:00:00 EDT 2022 · Physics of Plasmas

DOI:https://doi.org/10.1063/5.0097777· OSTI ID:1959565

^[1]; ^[2]; ^[1]; ^[1]; ^[3]; ^[4]; ^[1]; ^[1]

Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
General Atomics, San Diego, CA (United States)
Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Georgia Institute of Technology, Atlanta, GA (United States)

X-ray spectroscopic data from high-energy-density laser-produced plasmas has long required thorough, time-consuming analysis to extract meaningful source conditions. There are often confounding factors due to rapidly evolving states and finite spatial gradients (e.g., the existence of multi-temperature, multi-density, multi-ionization states, etc.) that make spectral measurements and analysis difficult. Here, in this paper, we demonstrate how deep learning can be applied to enhance x-ray spectral data analysis in both speed and intricacy. Neural networks (NNs) are trained on ensemble atomic physics simulations so that they can subsequently construct a model capable of extracting plasma parameters directly from experimental spectra. Through deep learning, the models can extract temperature distributions as opposed to single or dual temperature/density fits from standard trial-and-error atomic modeling at a significantly reduced computational cost compared to traditional trial-and-error methods. These NNs are envisioned to be deployed with high repetition rate x-ray spectrometers in order to provide detailed real-time analysis of experimental spectra.

View Accepted Manuscript (DOE)

Research Organization:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Organization:: USDOE; USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC52-07NA27344

OSTI ID:: 1959565

Alternate ID(s):: OSTI ID: 1887934

Report Number(s):: LLNL-JRNL-842932; 1049306

Journal Information:: Physics of Plasmas, Journal Name: Physics of Plasmas Journal Issue: 9 Vol. 29; ISSN 1070-664X

Publisher:: American Institute of Physics (AIP)Copyright Statement

Country of Publication:: United States

Language:: English

References (27)

Ensemble simulations of inertial confinement fusion implosions Nora, Ryan; Peterson, Jayson Luc; Spears, Brian Keith Statistical Analysis and Data Mining: The ASA Data Science Journal, Vol. 10, Issue 4 https://doi.org/10.1002/sam.11344	journal	May 2017
VISRAD—A 3-D view factor code and design tool for high-energy density physics experiments MacFarlane, J. J. Journal of Quantitative Spectroscopy and Radiative Transfer, Vol. 81, Issue 1-4 https://doi.org/10.1016/S0022-4073(03)00081-5	journal	September 2003
Modelling K shell spectra from short pulse heated buried microdot targets Hoarty, D. J.; Sircombe, N.; Beiersdorfer, P. High Energy Density Physics, Vol. 23 https://doi.org/10.1016/j.hedp.2017.04.004	journal	June 2017
An automated design process for short pulse laser driven opacity experiments Martin, M. E.; London, R. A.; Goluoglu, S. High Energy Density Physics, Vol. 26 https://doi.org/10.1016/j.hedp.2017.12.001	journal	March 2018
Neural network surrogate models for absorptivity and emissivity spectra of multiple elements Vander Wal, Michael D.; McClarren, Ryan G.; Humbird, Kelli D. Machine Learning with Applications, Vol. 8 https://doi.org/10.1016/j.mlwa.2022.100308	journal	June 2022
Principles of Plasma Spectroscopy Griem, Hans R. https://doi.org/10.1017/CBO9780511524578	book	January 1997
Petawatt and exawatt class lasers worldwide Danson, Colin N.; Haefner, Constantin; Bromage, Jake High Power Laser Science and Engineering, Vol. 7 https://doi.org/10.1017/hpl.2019.36	journal	January 2019
Automation and control of laser wakefield accelerators using Bayesian optimization Shalloo, R. J.; Dann, S. J. D.; Gruse, J. -N. Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-20245-6	journal	December 2020
The data-driven future of high-energy-density physics Hatfield, Peter W.; Gaffney, Jim A.; Anderson, Gemma J. Nature, Vol. 593, Issue 7859 https://doi.org/10.1038/s41586-021-03382-w	journal	May 2021
Artificial neural networks for plasma x‐ray spectroscopic analysis Larsen, J. T.; Morgan, W. L.; Goldstein, W. H. Review of Scientific Instruments, Vol. 63, Issue 10 https://doi.org/10.1063/1.1143558	journal	October 1992
Deep learning: A guide for practitioners in the physical sciences Spears, Brian K.; Brase, James; Bremer, Peer-Timo Physics of Plasmas, Vol. 25, Issue 8 https://doi.org/10.1063/1.5020791	journal	August 2018
Using L-shell x-ray spectra to determine conditions of non-local thermal dynamic equilibrium plasmas Marley, E. V.; Liedahl, D. A.; Schneider, M. B. Review of Scientific Instruments, Vol. 89, Issue 10 https://doi.org/10.1063/1.5039357	journal	October 2018
Making inertial confinement fusion models more predictive Gaffney, Jim A.; Brandon, Scott T.; Humbird, Kelli D. Physics of Plasmas, Vol. 26, Issue 8 https://doi.org/10.1063/1.5108667	journal	August 2019
Inverse problem instabilities in large-scale modeling of matter in extreme conditions Kasim, M. F.; Galligan, T. P.; Topp-Mugglestone, J. Physics of Plasmas, Vol. 26, Issue 11 https://doi.org/10.1063/1.5125979	journal	November 2019
Deep learning for NLTE spectral opacities Kluth, G.; Humbird, K. D.; Spears, B. K. Physics of Plasmas, Vol. 27, Issue 5 https://doi.org/10.1063/5.0006784	journal	May 2020
High-energy-density-physics measurements in implosions using Bayesian inference Ruby, J. J.; Gaffney, J. A.; Rygg, J. R. Physics of Plasmas, Vol. 28, Issue 3 https://doi.org/10.1063/5.0040616	journal	March 2021
Neural network surrogates of Bayesian diagnostic models for fast inference of plasma parameters Pavone, A.; Svensson, J.; Krychowiak, M. Review of Scientific Instruments, Vol. 92, Issue 3 https://doi.org/10.1063/5.0043772	journal	March 2021
Development of a deep learning based automated data analysis for step-filter x-ray spectrometers in support of high-repetition rate short-pulse laser-driven acceleration experiments Simpson, R. A.; Mariscal, D.; Williams, G. J. Review of Scientific Instruments, Vol. 92, Issue 7 https://doi.org/10.1063/5.0043835	journal	July 2021
Modeling laser-driven ion acceleration with deep learning Djordjević, B. Z.; Kemp, A. J.; Kim, J. Physics of Plasmas, Vol. 28, Issue 4 https://doi.org/10.1063/5.0045449	journal	April 2021
Accelerating the rate of discovery: toward high-repetition-rate HED science Ma, T.; Mariscal, D.; Anirudh, R. Plasma Physics and Controlled Fusion, Vol. 63, Issue 10 https://doi.org/10.1088/1361-6587/ac1f67	journal	September 2021
Design of flexible proton beam imaging energy spectrometers (PROBIES) Mariscal, D. A.; Djordjevíc, B. Z.; Grace, E. S. Plasma Physics and Controlled Fusion, Vol. 63, Issue 11 https://doi.org/10.1088/1361-6587/ac234a	journal	October 2021
Building high accuracy emulators for scientific simulations with deep neural architecture search Kasim, M. F.; Watson-Parris, D.; Deaconu, L. Machine Learning: Science and Technology, Vol. 3, Issue 1 https://doi.org/10.1088/2632-2153/ac3ffa	journal	December 2021
Laser wakefield acceleration with active feedback at 5 Hz Dann, S. J. D.; Baird, C. D.; Bourgeois, N. Physical Review Accelerators and Beams, Vol. 22, Issue 4 https://doi.org/10.1103/PhysRevAccelBeams.22.041303	journal	April 2019
Bulk heating of solid-density plasmas during high-intensity-laser plasma interactions Nilson, P. M.; Theobald, W.; Myatt, J. F. Physical Review E, Vol. 79, Issue 1 https://doi.org/10.1103/PhysRevE.79.016406	journal	January 2009
Analysis of Spectra from Laser Produced Plasmas Using a Neural Network Osterheld, A. L.; Morgan, W. L.; Larsen, J. T. Physical Review Letters, Vol. 73, Issue 11 https://doi.org/10.1103/PhysRevLett.73.1505	journal	September 1994
Transfer Learning to Model Inertial Confinement Fusion Experiments Humbird, K. D.; Peterson, J. L.; Spears, B. K. IEEE Transactions on Plasma Science, Vol. 48, Issue 1 https://doi.org/10.1109/TPS.2019.2955098	journal	January 2020
A survey on Image Data Augmentation for Deep Learning Shorten, Connor; Khoshgoftaar, Taghi M. Journal of Big Data, Vol. 6, Issue 1 https://doi.org/10.1186/s40537-019-0197-0	journal	July 2019

Similar Records

Statistical data analysis of x-ray spectroscopy data enabled by neural network accelerated Bayesian inference

Journal Article · Wed Aug 21 20:00:00 EDT 2024 · Review of Scientific Instruments · OSTI ID:2438166

Probabilistic Deep Learning Approach to Automate the Interpretation of Multi-phase Diffraction Spectra

Journal Article · Tue May 25 20:00:00 EDT 2021 · Chemistry of Materials · OSTI ID:1780758

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
artificial intelligence
artificial neural networks
atomic and molecular physics
laser physics
machine learning
signal processing
x-ray spectroscopy

Enhanced analysis of experimental x-ray spectra through deep learning

Citation Formats

References (27)

Similar Records

Related Subjects