Leveraging prior mean models for faster Bayesian optimization of particle accelerators

Tuning particle accelerators is a challenging and time-consuming task that can be automated and carried out efficiently using suitable optimization algorithms, such as model-based Bayesian optimization techniques. One of the major advantages of Bayesian algorithms is the ability to incorporate prior...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Scientific reports Jg. 15; H. 1; S. 12232 - 14
Hauptverfasser: Boltz, Tobias, Martinez, Jose L., Xu, Connie, Baker, Kathryn R. L., Zhu, Zihan, Morgan, Jenny, Roussel, Ryan, Ratner, Daniel, Mustapha, Brahim, Edelen, Auralee L.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 10.04.2025
Nature Publishing Group
Nature Portfolio
Schlagworte:
639/624/1020/1087
639/766
639/766/259
639/766/419/1131
Algorithms
Bayesian analysis
Convergence
Experimental particle physics
Free-electron lasers
Humanities and Social Sciences
Information theory and computation
Mathematical models
MATHEMATICS AND COMPUTING
multidisciplinary
Neural networks
Optimization algorithms
Optimization techniques
PARTICLE ACCELERATORS
Particle Accelerators, Bayesian Optimization
Physics
Science
Science (multidisciplinary)
ISSN:2045-2322, 2045-2322
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Tuning particle accelerators is a challenging and time-consuming task that can be automated and carried out efficiently using suitable optimization algorithms, such as model-based Bayesian optimization techniques. One of the major advantages of Bayesian algorithms is the ability to incorporate prior information about beam physics and historical behavior into the model used to make control decisions. In this work, we examine incorporating prior accelerator physics information into Bayesian optimization algorithms by utilizing fast executing, neural network models trained on simulated or historical datasets as prior mean functions in Gaussian process models. We show that in ideal cases, this technique substantially increases convergence speed to optimal solutions in high-dimensional tuning parameter spaces. Additionally, we demonstrate that even in non-ideal cases, where prior models of beam dynamics do not exactly match experimental conditions, the use of this technique can still enhance convergence speed. Finally, we demonstrate how these methods can be used to improve optimization in practical applications, such as transferring information gained from beam dynamics simulations to online control of the LCLS injector, and transferring knowledge gained from experimental measurements across different operating modes, such as accelerating different ion species at the ATLAS heavy ion accelerator.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)
AC02-76SF00515; AC02-06CH11357
USDOE Office of Science (SC), Nuclear Physics (NP)
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-025-95297-z