Home > Research > Publications & Outputs > Building robust surrogate models of laser-plasm...

Research

Associated organisational unit

Links

Text available via DOI:

Keywords

View graph of relations

Building robust surrogate models of laser-plasma interactions using large scale PIC simulation

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Building robust surrogate models of laser-plasma interactions using large scale PIC simulation. / Smith, Nathan; Lancaster, Kate; Morris, Stuart et al.
In: Plasma Physics and Controlled Fusion, Vol. 67, No. 2, 025013, 10.01.2025.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Smith, N, Lancaster, K, Morris, S, Arran, C & Ridgers, C 2025, 'Building robust surrogate models of laser-plasma interactions using large scale PIC simulation', Plasma Physics and Controlled Fusion, vol. 67, no. 2, 025013. https://doi.org/10.1088/1361-6587/ada1f5

APA

Smith, N., Lancaster, K., Morris, S., Arran, C., & Ridgers, C. (2025). Building robust surrogate models of laser-plasma interactions using large scale PIC simulation. Plasma Physics and Controlled Fusion, 67(2), Article 025013. https://doi.org/10.1088/1361-6587/ada1f5

Vancouver

Smith N, Lancaster K, Morris S, Arran C, Ridgers C. Building robust surrogate models of laser-plasma interactions using large scale PIC simulation. Plasma Physics and Controlled Fusion. 2025 Jan 10;67(2):025013. doi: 10.1088/1361-6587/ada1f5

Author

Smith, Nathan ; Lancaster, Kate ; Morris, Stuart et al. / Building robust surrogate models of laser-plasma interactions using large scale PIC simulation. In: Plasma Physics and Controlled Fusion. 2025 ; Vol. 67, No. 2.

Bibtex

@article{d18ca7b787324a99b95748d4613e2060,
title = "Building robust surrogate models of laser-plasma interactions using large scale PIC simulation",
abstract = "As the repetition rates of ultra-high intensity lasers increase, simulations used for the prediction of experimental results may need to be augmented with machine learning to keep up. In this paper, the usage of Gaussian process regression in producing surrogate models of laser-plasma interactions from particle-in-cell (PIC) simulations is investigated. Such a model retains the characteristic behaviour of the simulations but allows for faster on-demand results and estimation of statistical noise. A demonstrative model of Bremsstrahlung emission by hot electrons from a femtosecond timescale laser pulse in the 10 20 − 10 23 Wcm − 2 intensity range is produced using 800 simulations of such a laser-solid interaction from 1D hybrid-PIC. While the simulations required 84 000 CPU-hours to generate, subsequent training occurs on the order of a minute on a single core and prediction takes only a fraction of a second. The model trained on this data is then compared against analytical expectations. The efficiency of training the model and its subsequent ability to distinguish types of noise within the data are analysed, and as a result error bounds on the model are defined.",
keywords = "Bremsstrahlung, Gaussian process regression, laser-plasma interactions, laser-solid interactions, machine learning",
author = "Nathan Smith and Kate Lancaster and Stuart Morris and Chris Arran and Chris Ridgers",
year = "2025",
month = jan,
day = "10",
doi = "10.1088/1361-6587/ada1f5",
language = "English",
volume = "67",
journal = "Plasma Physics and Controlled Fusion",
issn = "0741-3335",
publisher = "IOP Publishing Ltd",
number = "2",

}

RIS

TY - JOUR

T1 - Building robust surrogate models of laser-plasma interactions using large scale PIC simulation

AU - Smith, Nathan

AU - Lancaster, Kate

AU - Morris, Stuart

AU - Arran, Chris

AU - Ridgers, Chris

PY - 2025/1/10

Y1 - 2025/1/10

N2 - As the repetition rates of ultra-high intensity lasers increase, simulations used for the prediction of experimental results may need to be augmented with machine learning to keep up. In this paper, the usage of Gaussian process regression in producing surrogate models of laser-plasma interactions from particle-in-cell (PIC) simulations is investigated. Such a model retains the characteristic behaviour of the simulations but allows for faster on-demand results and estimation of statistical noise. A demonstrative model of Bremsstrahlung emission by hot electrons from a femtosecond timescale laser pulse in the 10 20 − 10 23 Wcm − 2 intensity range is produced using 800 simulations of such a laser-solid interaction from 1D hybrid-PIC. While the simulations required 84 000 CPU-hours to generate, subsequent training occurs on the order of a minute on a single core and prediction takes only a fraction of a second. The model trained on this data is then compared against analytical expectations. The efficiency of training the model and its subsequent ability to distinguish types of noise within the data are analysed, and as a result error bounds on the model are defined.

AB - As the repetition rates of ultra-high intensity lasers increase, simulations used for the prediction of experimental results may need to be augmented with machine learning to keep up. In this paper, the usage of Gaussian process regression in producing surrogate models of laser-plasma interactions from particle-in-cell (PIC) simulations is investigated. Such a model retains the characteristic behaviour of the simulations but allows for faster on-demand results and estimation of statistical noise. A demonstrative model of Bremsstrahlung emission by hot electrons from a femtosecond timescale laser pulse in the 10 20 − 10 23 Wcm − 2 intensity range is produced using 800 simulations of such a laser-solid interaction from 1D hybrid-PIC. While the simulations required 84 000 CPU-hours to generate, subsequent training occurs on the order of a minute on a single core and prediction takes only a fraction of a second. The model trained on this data is then compared against analytical expectations. The efficiency of training the model and its subsequent ability to distinguish types of noise within the data are analysed, and as a result error bounds on the model are defined.

KW - Bremsstrahlung

KW - Gaussian process regression

KW - laser-plasma interactions

KW - laser-solid interactions

KW - machine learning

U2 - 10.1088/1361-6587/ada1f5

DO - 10.1088/1361-6587/ada1f5

M3 - Journal article

AN - SCOPUS:85214782851

VL - 67

JO - Plasma Physics and Controlled Fusion

JF - Plasma Physics and Controlled Fusion

SN - 0741-3335

IS - 2

M1 - 025013

ER -