Laser wakefield accelerator modelling with variational neural networks

M. J. V. Streeter; C. Colgan; C. C. Cobo; C. Arran; E. E. Los; R. Watt; N. Bourgeois; L. Calvin; J. Carderelli; N. Cavanagh; S. J. D. Dann; R. Fitzgarrald; E. Gerstmayr; A. S. Joglekar; B. Kettle; P. Mckenna; C. D.  Murphy; Z. Najmudin; P. Parsons; Q. Qian; P. P. Rajeev; C. P. Ridgers; D. R. Symes; A. G. R. Thomas; G. Sarri; S. P. D. Mangles

doi:10.1017/hpl.2022.47

Laser wakefield accelerator modelling with variational neural networks

M. J. V. Streeter^*, C. Colgan, C. C. Cobo, C. Arran, E. E. Los, R. Watt, N. Bourgeois, L. Calvin, J. Carderelli, N. Cavanagh, S. J. D. Dann, R. Fitzgarrald, E. Gerstmayr, A. S. Joglekar, B. Kettle, P. Mckenna, C. D. Murphy, Z. Najmudin, P. Parsons, Q. QianP. P. Rajeev, C. P. Ridgers, D. R. Symes, A. G. R. Thomas, G. Sarri, S. P. D. Mangles

^*Corresponding author for this work

School of Mathematics and Physics

Research output: Contribution to journal › Article › peer-review

12 Downloads (Pure)

Abstract

A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator. The model was constructed from variational convolutional neural networks, which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum. An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam. In addition, the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.

Original language	English
Article number	e9
Number of pages	8
Journal	High Power Laser Science and Engineering
Volume	11
DOIs	https://doi.org/10.1017/hpl.2022.47
Publication status	Published - 06 Jan 2023

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics
Nuclear and High Energy Physics
Nuclear Energy and Engineering

Access to Document

10.1017/hpl.2022.47Licence: CC BY

Laser wakefield accelerator modelling with variational neural networks
Copyright 2023 The Authors. This is an open access article published under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Final published version, 3.04 MBLicence: CC BY

Cite this

Streeter, M. J. V., Colgan, C., Cobo, C. C., Arran, C., Los, E. E., Watt, R., Bourgeois, N., Calvin, L., Carderelli, J., Cavanagh, N., Dann, S. J. D., Fitzgarrald, R., Gerstmayr, E., Joglekar, A. S., Kettle, B., Mckenna, P., Murphy, C. D., Najmudin, Z., Parsons, P., ... Mangles, S. P. D. (2023). Laser wakefield accelerator modelling with variational neural networks. High Power Laser Science and Engineering, 11, [e9]. https://doi.org/10.1017/hpl.2022.47

@article{5116ad6df981441a9966adc43545f550,

title = "Laser wakefield accelerator modelling with variational neural networks",

abstract = "A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator. The model was constructed from variational convolutional neural networks, which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum. An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam. In addition, the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.",

author = "Streeter, {M. J. V.} and C. Colgan and Cobo, {C. C.} and C. Arran and Los, {E. E.} and R. Watt and N. Bourgeois and L. Calvin and J. Carderelli and N. Cavanagh and Dann, {S. J. D.} and R. Fitzgarrald and E. Gerstmayr and Joglekar, {A. S.} and B. Kettle and P. Mckenna and Murphy, {C. D.} and Z. Najmudin and P. Parsons and Q. Qian and Rajeev, {P. P.} and Ridgers, {C. P.} and Symes, {D. R.} and Thomas, {A. G. R.} and G. Sarri and Mangles, {S. P. D.}",

year = "2023",

month = jan,

day = "6",

doi = "10.1017/hpl.2022.47",

language = "English",

volume = "11",

journal = "High Power Laser Science and Engineering",

issn = "2095-4719",

publisher = "Cambridge University Press",

}

Streeter, MJV, Colgan, C, Cobo, CC, Arran, C, Los, EE, Watt, R, Bourgeois, N, Calvin, L, Carderelli, J, Cavanagh, N, Dann, SJD, Fitzgarrald, R, Gerstmayr, E, Joglekar, AS, Kettle, B, Mckenna, P, Murphy, CD, Najmudin, Z, Parsons, P, Qian, Q, Rajeev, PP, Ridgers, CP, Symes, DR, Thomas, AGR, Sarri, G & Mangles, SPD 2023, 'Laser wakefield accelerator modelling with variational neural networks', High Power Laser Science and Engineering, vol. 11, e9. https://doi.org/10.1017/hpl.2022.47

TY - JOUR

T1 - Laser wakefield accelerator modelling with variational neural networks

AU - Streeter, M. J. V.

AU - Colgan, C.

AU - Cobo, C. C.

AU - Arran, C.

AU - Los, E. E.

AU - Watt, R.

AU - Bourgeois, N.

AU - Calvin, L.

AU - Carderelli, J.

AU - Cavanagh, N.

AU - Dann, S. J. D.

AU - Fitzgarrald, R.

AU - Gerstmayr, E.

AU - Joglekar, A. S.

AU - Kettle, B.

AU - Mckenna, P.

AU - Murphy, C. D.

AU - Najmudin, Z.

AU - Parsons, P.

AU - Qian, Q.

AU - Rajeev, P. P.

AU - Ridgers, C. P.

AU - Symes, D. R.

AU - Thomas, A. G. R.

AU - Sarri, G.

AU - Mangles, S. P. D.

PY - 2023/1/6

Y1 - 2023/1/6

N2 - A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator. The model was constructed from variational convolutional neural networks, which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum. An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam. In addition, the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.

AB - A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator. The model was constructed from variational convolutional neural networks, which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum. An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam. In addition, the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.

U2 - 10.1017/hpl.2022.47

DO - 10.1017/hpl.2022.47

M3 - Article

AN - SCOPUS:85146162769

VL - 11

JO - High Power Laser Science and Engineering

JF - High Power Laser Science and Engineering

SN - 2095-4719

M1 - e9

ER -

Laser wakefield accelerator modelling with variational neural networks

Abstract

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this