%0 Conference Paper
%A Appel, Sabrina
%A Oeftiger, Adrian
%A Kazantseva, Erika
%A Weick, Helmut
%A Madysa, Nico
%A Boine-Frankenheim, Oliver
%A Pietri, Stephane
%A Isensee, Victoria
%Y Pilat, Fulvia
%Y Fischer, Wolfram
%Y Saethre, Robert
%Y Anisimov, Petr
%Y Andrian, Ivan
%T Automated optimization of accelerator settings at GSI
%C Geneva, Switzerland
%I JACoW Publishing
%M GSI-2025-00535
%P 882 - 885
%D 2024
%Z Published by JACoW Publishing under the terms of the Creative Commons Attribution 4.0 license.
%X The complexity of the GSI/FAIR accelerator facility demands a high level of automation in order to maximize time for physics experiments. Accelerator laboratories world-wide are exploring a large variety of techniques to achieve this, from classical optimization to reinforcement learning. This paper reports on the first results of using Geoff at GSI for automatic optimization of various beam manipulations. Geoff (Generic Optimization Framework </td><td width="150">
%X  Frontend) is an open-source framework that harmonizes access to the above automation techniques and simplifies the transition towards and between them. It is maintained as part of the EURO-LABS project in cooperation between CERN and GSI. In dedicated beam experiments, the beam loss of the multi-turn injection into the SIS18 synchrotron has been reduced from 40
%B 15th International Particle Accelerator Conference
%C 19 May 2024 - 24 May 2024, Nashville, Tennessee (USA)
Y2 19 May 2024 - 24 May 2024
M2 Nashville, Tennessee, USA
%K Accelerator Physics (Other)
%K mc5-beam-dynamics-and-em-fields - MC5: Beam Dynamics and EM Fields (Other)
%K MC5.D13 - MC5.D13 Machine Learning (Other)
%F PUB:(DE-HGF)8
%9 Contribution to a conference proceedings
%R 10.18429/JACOW-IPAC2024-MOPS68
%U https://repository.gsi.de/record/358351