Conference Presentation

PUBDB-2025-05726

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Advanced Controls and Machine Learning at FLASHForward

Boulton, L. A. (Corresponding author)Extern*DESY* ; Beinortaite, J.Extern*DESY* ; Björklund Svensson, J. H.Extern*DESY* ; Burghart, P.Extern* ; D'Arcy, R.Extern* ; Ferran Pousa, A.Extern*DESY* ; Foster, B.Extern*DESY* ; Gonzalez Caminal, P.Extern*DESY* ; Huck, M.DESY* ; Jones, H.Extern* ; Kanekar, A.Extern*DESY* ; Lindstroem, C. A.DESY* ; Loisch, G.Extern*DESY* ; Long, T.XFEL.EU*DESY* ; Maier, A.Extern*DESY* ; Mewes, S. M.DESY* ; Osterhoff, J.Extern*DESY* ; Pena Asmus, F. L.Extern* ; Schröder, S.DESY* ; Thévenet, M.DESY* ; Wesch, S.DESY* ; Wing, M.Extern* ; Wood, J. C.DESY*

2025

Abstract: Plasma accelerators often constitute a high-noise environment with multiple, non-linear dependencies that make the setup and operation of such devices a difficult task. To address these challenges, Machine Learning methods have gained popularity in the field of plasma acceleration. In this contribution, we summarise the application of such techniques to the beam-driven plasma acceleration experiment FLASHForward at DESY, Hamburg. Examples include the automated tuning of the plasma stage via Bayesian Optimisation and the development of non-destructive, neural-network-based predictions of the resulting accelerated trailing-bunch spectra.

---

Contributing Institute(s):

1. Plasma Acceleration and Laser Group (MPL)
2. FTX Fachgruppe AST (HH_FH_FTX_AS)

Research Program(s):

1. 621 - Accelerator Research and Development (POF4-621) (POF4-621)
2. 6G2 - FLASH (DESY) (POF4-6G2) (POF4-6G2)

Experiment(s):

1. FLASHForward

Appears in the scientific report 2025

---