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

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

8 Citations (Scopus)

40 Downloads (Pure)

Abstract

A machine learning model was created to predict the electron spectrum generated by a GeVclass 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 on that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior undergoing any process which 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
Early online date	6 Jan 2023
DOIs	https://doi.org/10.1017/hpl.2022.47
Publication status	E-pub ahead of print - 6 Jan 2023

Keywords

laser Wakefield accelerator model
variational neural networks
machine learning model
convolutional neural networks

Access to Document

10.1017/hpl.2022.47Licence: CC BY 4.0

Streeter-etal-HPLSE-2022-Laser-Wakefield-accelerator-modelling-with-variationalFinal published version, 3 MBLicence: CC BY 4.0

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, Article e9. Advance online publication. https://doi.org/10.1017/hpl.2022.47

@article{13105a525e5a458c88dee573b3860b11,

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

abstract = "A machine learning model was created to predict the electron spectrum generated by a GeVclass 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 on that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior undergoing any process which 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.",

keywords = "laser Wakefield accelerator model, variational neural networks, machine learning model, convolutional neural networks",

author = "M.J.V. Streeter and C. Colgan and C.C. Cobo and C. Arran and E.E. Los 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 A.S. Joglekar and B. Kettle and P. Mckenna and C.D. Murphy and Z. Najmudin and P. Parsons and Q. Qian and P.P. Rajeev and C.P. Ridgers and D.R. Symes and A.G.R. Thomas and G. Sarri and S.P.D. Mangles",

year = "2023",

month = jan,

day = "6",

doi = "10.1017/hpl.2022.47",

language = "English",

volume = "11",

journal = "High Power Laser Science and Engineering",

issn = "2052-3289",

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 GeVclass 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 on that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior undergoing any process which 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 GeVclass 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 on that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior undergoing any process which 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.

KW - laser Wakefield accelerator model

KW - variational neural networks

KW - machine learning model

KW - convolutional neural networks

U2 - 10.1017/hpl.2022.47

DO - 10.1017/hpl.2022.47

M3 - Article

AN - SCOPUS:85146162769

SN - 2052-3289

VL - 11

JO - High Power Laser Science and Engineering

JF - High Power Laser Science and Engineering

M1 - e9

ER -

Laser Wakefield accelerator modelling with variational neural networks

Abstract

Keywords

Access to Document

Fingerprint

Cite this