By the same authors

Automation and control of laser wakefield accelerators using Bayesian optimisation

Research output: Contribution to journalArticle


  • R. J. Shalloo
  • S. J. D. Dann
  • J. -N. Gruse
  • C. I. D. Underwood
  • A. F. Antoine
  • M. Backhouse
  • C. D. Baird
  • M. D. Balcazar
  • N. Bourgeois
  • J. A. Cardarelli
  • P. Hatfield
  • J. Kang
  • K. Krushelnick
  • S. P. D. Mangles
  • N. Lu
  • J. Osterhoff
  • K. Põder
  • P. P. Rajeev
  • S. Rozario
  • M. P. Selwood
  • A. J. Shahani
  • D. R. Symes
  • A. G. R. Thomas
  • C. Thornton
  • Z. Najmudin
  • M. J. V. Streeter


Publication details

DatePublished - 28 Jul 2020
Original languageEnglish


Laser wakefield accelerators promise to revolutionise many areas of accelerator science. However, one of the greatest challenges to their widespread adoption is the difficulty in control and optimisation of the accelerator outputs due to coupling between input parameters and the dynamic evolution of the accelerating structure. Here, we use machine learning techniques to automate a 100 MeV-scale accelerator, which optimised its outputs by simultaneously varying up to 6 parameters including the spectral and spatial phase of the laser and the plasma density and length. This led to significant improvements over manual optimisation, enhancing the electron and x-ray yields by factors of 3 or more, using only a few tens of measurements. Most notably, the model built by the algorithm enabled optimisation of the laser evolution that might otherwise have been missed in single-variable scans. Subtle tuning of the laser pulse shape caused a dramatic 80% increase in electron beam charge, despite the pulse length changing by just 1%.

Bibliographical note

8 pages, 5 figures

    Research areas

  • physics.acc-ph, physics.plasm-ph

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations