Speaker
Frida Brogren
(MLS (Laser fuer Plasmabeschleunigung))
Description
Laser-plasma accelerators are promising candidates for driving compact undulator radiation sources. Future applications would greatly benefit from optimization by data-driven modelling of the acceleration process, but intrinsic noise and large parameter spaces poses a problem for conventional modelling methods. At LUX beamline we use an ensemble of neural networks and bootstrap aggregation to extract a model robust to noise and outliers.
Primary author
Frida Brogren
(MLS (Laser fuer Plasmabeschleunigung))
Co-authors
Paul Viktor Winkler
(MLS (Laser fuer Plasmabeschleunigung))
Lars Hübner
(University of Hamburg)
Philipp Messner
(MLS (Laser fuer Plasmabeschleunigung))
Maximilian Trunk
(MLS (Laser fuer Plasmabeschleunigung))
Christian Werle
(UNI/EXP (Uni Hamburg, Institut fur Experimentalphysik))
Wim Leemans
(M (Beschleuniger))
Andreas Maier
(MLS (Laser fuer Plasmabeschleunigung))
Soeren Jalas
(UNI/EXP (Uni Hamburg, Institut fur Experimentalphysik))
Manuel Kirchen
(MLS (Laser fuer Plasmabeschleunigung))
