Beyond optimization—supervised learning applications in relativistic laser-plasma experiments

Lin, Jinpu; Qian, Qian; Murphy, Jon; Hsu, Abigail; Hero, Alfred; Ma, Yong; Thomas, Alexander G.  R.; Krushelnick, Karl

doi:10.1063/5.0047940

Title: Beyond optimization—supervised learning applications in relativistic laser-plasma experiments

Journal Article · 04 August 2021 · Physics of Plasmas

DOI: https://doi.org/10.1063/5.0047940 · OSTI ID:1850410

^[1]; Qian, Qian ^[2]; Murphy, Jon ^[2];

^[3];

^[4];

^[2];

^[2]

Univ. of Michigan, Ann Arbor, MI (United States). Gerard Mourou Center for Ultrafast Optical Science; Univ. of Michigan, Ann Arbor, MI (United States)
Univ. of Michigan, Ann Arbor, MI (United States). Gerard Mourou Center for Ultrafast Optical Science
Stony Brook Univ., NY (United States). Dept. of Applied Mathematics and Statistics
Univ. of Michigan, Ann Arbor, MI (United States). Dept. of Electrical Engineering and Computer Science

We explore the applications of machine learning techniques in relativistic laser-plasma experiments beyond optimization purposes. We predict the beam charge of electrons produced in a laser wakefield accelerator given the laser wavefront change caused by a deformable mirror. Machine learning enables feature analysis beyond merely searching for an optimal beam charge, showing that specific aberrations in the laser wavefront are favored in generating higher beam charges. Supervised learning models allow characterizing the measured data quality as well as recognizing irreproducible data and potential outliers. Furthermore, we also include virtual measurement errors in the experimental data to examine the model robustness under these conditions. This work demonstrates how machine learning methods can benefit data analysis and physics interpretation in a highly nonlinear problem of relativistic laser-plasma interaction.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Georgia Institute of Technology, Atlanta, GA (United States); Univ. of Michigan, Ann Arbor, MI (United States)

Sponsoring Organization:: US Air Force Office of Scientific Research (AFOSR); USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: NA0003921; SC0016804

OSTI ID:: 1850410

Journal Information:: Physics of Plasmas, Journal Name: Physics of Plasmas Journal Issue: 8 Vol. 28; ISSN 1070-664X

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

Country of Publication:: United States

Language:: English

References (62)

Monoenergetic beams of relativistic electrons from intense laser–plasma interactions Mangles, S. P. D.; Murphy, C. D.; Najmudin, Z. Nature, Vol. 431, Issue 7008 https://doi.org/10.1038/nature02939	journal	September 2004
A laser–plasma accelerator producing monoenergetic electron beams Faure, J.; Glinec, Y.; Pukhov, A. Nature, Vol. 431, Issue 7008 https://doi.org/10.1038/nature02963	journal	September 2004
Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas Piccione, A.; Berkery, J. W.; Sabbagh, S. A. Nuclear Fusion, Vol. 60, Issue 4 https://doi.org/10.1088/1741-4326/ab7597	journal	March 2020
Physics of laser-driven plasma-based electron accelerators Esarey, E.; Schroeder, C. B.; Leemans, W. P. Reviews of Modern Physics, Vol. 81, Issue 3 https://doi.org/10.1103/revmodphys.81.1229	journal	August 2009
Deep Neural Network Initialization With Decision Trees Humbird, Kelli D.; Peterson, J. Luc; Mcclarren, Ryan G. IEEE Transactions on Neural Networks and Learning Systems, Vol. 30, Issue 5 https://doi.org/10.1109/tnnls.2018.2869694	journal	May 2019
Electron Acceleration by a Wake Field Forced by an Intense Ultrashort Laser Pulse Malka, V. Science, Vol. 298, Issue 5598 https://doi.org/10.1126/science.1076782	journal	November 2002
Automatic model construction with Gaussian processes Duvenaud, David Apollo - University of Cambridge Repository https://doi.org/10.17863/cam.14087	text	January 2014
Classification of Solar Wind With Machine Learning Camporeale, Enrico; Carè, Algo; Borovsky, Joseph E. Journal of Geophysical Research: Space Physics, Vol. 122, Issue 11 https://doi.org/10.1002/2017JA024383	journal	November 2017
Parameter inference with deep jointly informed neural networks Humbird, Kelli D.; Peterson, J. Luc; McClarren, Ryan G. Statistical Analysis and Data Mining: The ASA Data Science Journal, Vol. 12, Issue 6 https://doi.org/10.1002/sam.11435	journal	July 2019
Phase control algorithms and filamentation of ultrashort laser pulses in a scattering medium Lefebvre, Simon; Belmouaddine, Hakim; Morris, Denis Applied Physics B, Vol. 124, Issue 11 https://doi.org/10.1007/s00340-018-7083-x	journal	October 2018
Approximation capabilities of multilayer feedforward networks Hornik, Kurt Neural Networks, Vol. 4, Issue 2 https://doi.org/10.1016/0893-6080(91)90009-T	journal	January 1991
A bremsstrahlung gamma-ray source based on stable ionization injection of electrons into a laser wakefield accelerator Döpp, A.; Guillaume, E.; Thaury, C. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 830 https://doi.org/10.1016/j.nima.2016.01.086	journal	September 2016
Controlling laser driven protons acceleration using a deformable mirror at a high repetition rate Noaman-ul-Haq, M.; Sokollik, T.; Ahmed, H. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 883 https://doi.org/10.1016/j.nima.2017.11.075	journal	March 2018
Focus optimization at relativistic intensity with high numerical aperture and adaptive optics Lin, Jinpu; Easter, James H.; Krushelnick, Karl Optics Communications, Vol. 421 https://doi.org/10.1016/j.optcom.2018.03.075	journal	August 2018
Filament-induced breakdown spectroscopy signal enhancement using optical wavefront control Finney, L. A.; Lin, J.; Skrodzki, P. J. Optics Communications, Vol. 490 https://doi.org/10.1016/j.optcom.2021.126902	journal	July 2021
A laser-induced breakdown spectroscopy multi-component quantitative analytical method based on a deep convolutional neural network Li, Lu-Ning; Liu, Xiang-Feng; Xu, Wei-Ming Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 169 https://doi.org/10.1016/j.sab.2020.105850	journal	July 2020
Targets for high repetition rate laser facilities: needs, challenges and perspectives Prencipe, I.; Fuchs, J.; Pascarelli, S. High Power Laser Science and Engineering, Vol. 5 https://doi.org/10.1017/hpl.2017.18	journal	January 2017
Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters Chen, Yang; Manchester, Ward B.; Hero, Alfred O. Space Weather, Vol. 17, Issue 10 https://doi.org/10.1029/2019SW002214	journal	October 2019
Solar Flare Intensity Prediction With Machine Learning Models Jiao, Zhenbang; Sun, Hu; Wang, Xiantong Space Weather, Vol. 18, Issue 7 https://doi.org/10.1029/2020SW002440	journal	July 2020
High-quality electron beams from a laser wakefield accelerator using plasma-channel guiding Geddes, C. G. R.; Toth, Cs.; van Tilborg, J. Nature, Vol. 431, Issue 7008 https://doi.org/10.1038/nature02900	journal	September 2004
Monoenergetic beams of relativistic electrons from intense laser–plasma interactions Mangles, S. P. D.; Murphy, C. D.; Najmudin, Z. Nature, Vol. 431, Issue 7008 https://doi.org/10.1038/nature02939	journal	September 2004
A laser–plasma accelerator producing monoenergetic electron beams Faure, J.; Glinec, Y.; Pukhov, A. Nature, Vol. 431, Issue 7008 https://doi.org/10.1038/nature02963	journal	September 2004
Coherent control of plasma dynamics He, Z. -H.; Hou, B.; Lebailly, V. Nature Communications, Vol. 6, Issue 1 https://doi.org/10.1038/ncomms8156	journal	May 2015
Relativistic electron beams driven by kHz single-cycle light pulses Guénot, D.; Gustas, D.; Vernier, A. Nature Photonics, Vol. 11, Issue 5 https://doi.org/10.1038/nphoton.2017.46	journal	April 2017
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
Stable multi-GeV electron accelerator driven by waveform-controlled PW laser pulses Kim, Hyung Taek; Pathak, V. B.; Hong Pae, Ki Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-09267-1	journal	August 2017
Employing machine learning for theory validation and identification of experimental conditions in laser-plasma physics Gonoskov, A.; Wallin, E.; Polovinkin, A. Scientific Reports, Vol. 9, Issue 1 https://doi.org/10.1038/s41598-019-43465-3	journal	May 2019
Capturing Structural Dynamics in Crystalline Silicon Using Chirped Electrons from a Laser Wakefield Accelerator He, Z. -H.; Beaurepaire, B.; Nees, J. A. Scientific Reports, Vol. 6, Issue 1 https://doi.org/10.1038/srep36224	journal	November 2016
Production of a MeV proton with 30 mJ laser energy by optimizing the focusing spot using a deformable mirror Nayuki, Takuya; Fujii, Takashi; Oishi, Yuji Review of Scientific Instruments, Vol. 76, Issue 7 https://doi.org/10.1063/1.1942527	journal	July 2005
Control of quasi-monoenergetic electron beams from laser-plasma accelerators with adjustable shock density profile Tsai, Hai-En; Swanson, Kelly K.; Barber, Sam K. Physics of Plasmas, Vol. 25, Issue 4 https://doi.org/10.1063/1.5023694	journal	April 2018
Temporal feedback control of high-intensity laser pulses to optimize ultrafast heating of atomic clusters Streeter, M. J. V.; Dann, S. J. D.; Scott, J. D. E. Applied Physics Letters, Vol. 112, Issue 24 https://doi.org/10.1063/1.5027297	journal	June 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
Analysis of NIF scaling using physics informed machine learning Hsu, Abigail; Cheng, Baolian; Bradley, Paul A. Physics of Plasmas, Vol. 27, Issue 1 https://doi.org/10.1063/1.5130585	journal	January 2020
Optimization and stabilization of a kilohertz laser-plasma accelerator Rovige, L.; Huijts, J.; Andriyash, I. A. Physics of Plasmas, Vol. 28, Issue 3 https://doi.org/10.1063/5.0040926	journal	March 2021
Plasma channels during filamentation of a femtosecond laser pulse with wavefront astigmatism in air Dergachev, A. A.; Ionin, A. A.; Kandidov, V. P. Quantum Electronics, Vol. 44, Issue 12 https://doi.org/10.1070/QE2014v044n12ABEH015472	journal	December 2014
Electron radiography using a table-top laser-cluster plasma accelerator Bussolino, G. C.; Faenov, A.; Giulietti, A. Journal of Physics D: Applied Physics, Vol. 46, Issue 24 https://doi.org/10.1088/0022-3727/46/24/245501	journal	May 2013
Applications of laser wakefield accelerator-based light sources Albert, Félicie; Thomas, Alec G. R. Plasma Physics and Controlled Fusion, Vol. 58, Issue 10 https://doi.org/10.1088/0741-3335/58/10/103001	journal	September 2016
Disruption prediction investigations using Machine Learning tools on DIII-D and Alcator C-Mod Rea, C.; Granetz, R. S.; Montes, K. Plasma Physics and Controlled Fusion, Vol. 60, Issue 8 https://doi.org/10.1088/1361-6587/aac7fe	journal	June 2018
Sim-to-real transfer reinforcement learning for control of thermal effects of an atmospheric pressure plasma jet Witman, Matthew; Gidon, Dogan; Graves, David B. Plasma Sources Science and Technology, Vol. 28, Issue 9 https://doi.org/10.1088/1361-6595/ab3c15	journal	September 2019
High repetition-rate wakefield electron source generated by few-millijoule, 30 fs laser pulses on a density downramp He, Z-H; Hou, B.; Nees, J. A. New Journal of Physics, Vol. 15, Issue 5 https://doi.org/10.1088/1367-2630/15/5/053016	journal	May 2013
Optimizing laser–plasma interactions for ion acceleration using particle-in-cell simulations and evolutionary algorithms Smith, Joseph R.; Orban, Chris; Morrison, John T. New Journal of Physics, Vol. 22, Issue 10 https://doi.org/10.1088/1367-2630/abbfce	journal	October 2020
Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas Piccione, A.; Berkery, J. W.; Sabbagh, S. A. Nuclear Fusion, Vol. 60, Issue 4 https://doi.org/10.1088/1741-4326/ab7597	journal	March 2020
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
Sample-efficient reinforcement learning for CERN accelerator control Kain, Verena; Hirlander, Simon; Goddard, Brennan Physical Review Accelerators and Beams, Vol. 23, Issue 12 https://doi.org/10.1103/PhysRevAccelBeams.23.124801	journal	December 2020
Petawatt Laser Guiding and Electron Beam Acceleration to 8 GeV in a Laser-Heated Capillary Discharge Waveguide Gonsalves, A. J.; Nakamura, K.; Daniels, J. Physical Review Letters, Vol. 122, Issue 8 https://doi.org/10.1103/PhysRevLett.122.084801	journal	February 2019
Polarized Laser-WakeField-Accelerated Kiloampere Electron Beams Wen, Meng; Tamburini, Matteo; Keitel, Christoph H. Physical Review Letters, Vol. 122, Issue 21 https://doi.org/10.1103/PhysRevLett.122.214801	journal	May 2019
Laser Electron Accelerator Tajima, T.; Dawson, J. M. Physical Review Letters, Vol. 43, Issue 4 https://doi.org/10.1103/PhysRevLett.43.267	journal	July 1979
Generating multi-GeV electron bunches using single stage laser wakefield acceleration in a 3D nonlinear regime Lu, W.; Tzoufras, M.; Joshi, C. Physical Review Special Topics - Accelerators and Beams, Vol. 10, Issue 6 https://doi.org/10.1103/PhysRevSTAB.10.061301	journal	June 2007
Decoding Sources of Energy Variability in a Laser-Plasma Accelerator Maier, Andreas R.; Delbos, Niels M.; Eichner, Timo Physical Review X, Vol. 10, Issue 3 https://doi.org/10.1103/PhysRevX.10.031039	journal	August 2020
Physics of laser-driven plasma-based electron accelerators Esarey, E.; Schroeder, C. B.; Leemans, W. P. Reviews of Modern Physics, Vol. 81, Issue 3 https://doi.org/10.1103/RevModPhys.81.1229	journal	August 2009
Deep Neural Network Initialization With Decision Trees Humbird, Kelli D.; Peterson, J. Luc; Mcclarren, Ryan G. IEEE Transactions on Neural Networks and Learning Systems, Vol. 30, Issue 5 https://doi.org/10.1109/TNNLS.2018.2869694	journal	May 2019
Using Sparse Gaussian Processes for Predicting Robust Inertial Confinement Fusion Implosion Yields Hatfield, Peter; Rose, Steven; Scott, Robbie IEEE Transactions on Plasma Science https://doi.org/10.1109/TPS.2019.2944416	journal	January 2019
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
Electron Acceleration by a Wake Field Forced by an Intense Ultrashort Laser Pulse Malka, V. Science, Vol. 298, Issue 5598 https://doi.org/10.1126/science.1076782	journal	November 2002
Control of the configuration of multiple femtosecond filaments in air by adaptive wavefront manipulation Englesbe, Alexander C.; He, Zhaohan; Nees, John A. Optics Express, Vol. 24, Issue 6 https://doi.org/10.1364/OE.24.006071	journal	January 2016
Enhancement of THz generation by feedback-optimized wavefront manipulation Hah, J.; Jiang, W.; He, Z-H. Optics Express, Vol. 25, Issue 15 https://doi.org/10.1364/OE.25.017271	journal	January 2017
Adaptive control of laser-wakefield accelerators driven by mid-IR laser pulses Lin, J.; Ma, Y.; Schwartz, R. Optics Express, Vol. 27, Issue 8 https://doi.org/10.1364/OE.27.010912	journal	January 2019
Control of multiple filamentation in air Fibich, Gadi; Eisenmann, Shmuel; Ilan, Boaz Optics Letters, Vol. 29, Issue 15 https://doi.org/10.1364/OL.29.001772	journal	January 2004
Adaptive-feedback spectral-phase control for interactions with transform-limited ultrashort high-power laser pulses Liu, Cheng; Zhang, Jun; Chen, Shouyuan Optics Letters, Vol. 39, Issue 1 https://doi.org/10.1364/OL.39.000080	journal	December 2013
MeV electron acceleration at 1 kHz with <10 mJ laser pulses Salehi, F.; Goers, A. J.; Hine, G. A. Optics Letters, Vol. 42, Issue 2 https://doi.org/10.1364/OL.42.000215	journal	January 2017
Workshop on Opportunities, Challenges, and Best Practices for Basic Plasma Science User Facilities. Final Report--Conference Proposal Milchberg, Howard; Scime, Earl https://doi.org/10.2172/1615521	report	April 2020

Similar Records

Coherent control of plasma dynamics by feedback-optimized wavefront manipulation

Journal Article · 2015 · Physics of Plasmas · OSTI ID:22410419

He, Z. -H.; Hou, B.; Gao, G.; +5 more

Optimization of microwave emission from laser filamentation with a machine learning algorithm

Journal Article · 2021 · Applied Optics · OSTI ID:1808003

Englesbe, Alexander; Lin, Jinpu; Nees, John; +3 more

Failure Analysis of a Complex Learning Framework Incorporating Multi-Modal and Semi-Supervised Learning

Conference · 2011 · OSTI ID:1032815

Pullum, Laura L; Symons, Christopher T

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
Gaussian processes
Physics
adaptive optics
artificial neural networks
laser plasma interactions
machine learning
plasma acceleration
regression analysis
statistical analysis

Title: Beyond optimization—supervised learning applications in relativistic laser-plasma experiments

Citation Formats

References (62)

Similar Records

Related Subjects