Preprint PUBDB-2024-01950

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png
Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations

 ;  ;  ;

2024

This record in other databases:  

Please use a persistent id in citations: doi:

Report No.: arXiv:2401.05815

Abstract: Machine learning has emerged as a powerful solution to the modern challenges in accelerator physics. However, the limited availability of beam time, the computational cost of simulations, and the high dimensionality of optimization problems pose significant challenges in generating the required data for training state-of-the-art machine learning models. In this work, we introduce cheetah, a pytorch-based high-speed differentiable linear beam dynamics code. cheetah enables the fast collection of large datasets by reducing computation times by multiple orders of magnitude and facilitates efficient gradient-based optimization for accelerator tuning and system identification. This positions cheetah as a user-friendly, readily extensible tool that integrates seamlessly with widely adopted machine learning tools. We showcase the utility of cheetah through five examples, including reinforcement learning training, gradient-based beamline tuning, gradient-based system identification, physics-informed Bayesian optimization priors, and modular neural network surrogate modeling of space charge effects. The use of such a high-speed differentiable simulation code will simplify the development of machine learning-based methods for particle accelerators and fast-track their integration into everyday operations of accelerator facilities.

Keyword(s): space charge ; accelerator ; machine learning ; optimization ; reinforcement learning ; modular ; Bayesian ; neural network

Classification:

Note: Phys. Rev. Accel. Beams 27 (2024) 054601. 16 pages, 9 figures, 3 tables

Contributing Institute(s):
  1. Strahlkontrollen (MSK)
Research Program(s):
  1. 621 - Accelerator Research and Development (POF4-621) (POF4-621)
  2. InternLabs-0011 - HIR3X - Helmholtz International Laboratory on Reliability, Repetition, Results at the most advanced X-ray Sources (2020_InternLabs-0011) (2020_InternLabs-0011)
  3. ZT-I-PF-5-6 - Autonomous Accelerator (AA) (2020_ZT-I-PF-5-6) (2020_ZT-I-PF-5-6)
Experiment(s):
  1. Accelerator Research Experiment at SINBAD

Appears in the scientific report 2024
Database coverage:
Creative Commons Attribution CC BY 4.0 ; OpenAccess ; Published
Click to display QR Code for this record

The record appears in these collections:
Private Collections > >DESY > >M > MSK
Document types > Reports > Preprints
Public records
Publications database
OpenAccess


Linked articles:

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Journal Article  ;  ;  ;
Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations
Physical review accelerators and beams 27(5), 054601 () [10.1103/PhysRevAccelBeams.27.054601]  GO OpenAccess  Download fulltext Files  Download fulltextFulltext by arXiv.org BibTeX | EndNote: XML, Text | RIS


 Record created 2024-05-31, last modified 2025-01-15


OpenAccess:
Download fulltext PDF Download fulltext PDF (PDFA)
External link:
Download fulltextFulltext by arXiv.org
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)