Search

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.

Accelerator physics relies on numerical algorithms to solve optimization problems in online accelerator control and tasks such as experimental design and model calibration in simulations. The effectiveness of optimization algorithms in discovering ideal solutions for complex challenges with limited resources often determines the problem complexity these methods can address. The accelerator physics community has recognized the advantages of Bayesian optimization algorithms, which leverage statistical surrogate models of objective functions to effectively address complex optimization challenges, especially in the presence of noise during accelerator operation and in resource-intensive physics simulations. In this review article, we offer a conceptual overview of applying Bayesian optimization techniques towards solving optimization problems in accelerator physics. We begin by providing a straightforward explanation of the essential components that make up Bayesian optimization techniques. We then give an overview of current and previous work applying and modifying these techniques to solve accelerator physics challenges. Finally, we explore practical implementation strategies for Bayesian optimization algorithms to maximize their performance, enabling users to effectively address complex optimization challenges in real-time beam control and accelerator design.

Los Alamos is currently developing novel particle accelerator controls and diagnostics algorithms to enable higher quality beams with lower beam losses than is currently possible. The purpose of this workshop was to consider tuning and optimization challenges of a wide range of particle accelerators including linear proton accelerators such as the Los Alamos Neutron Science Center (LANSCE), rings such as the Advanced Photon Source (APS) synchrotron, free electron lasers (FEL) such as the Linac Coherent Light Source (LCLS) and LCLS-II, the European X-ray Free Electron Laser (EuXFEL), the Swiss FEL, and the planned MaRIE FEL, and plasma wake-field accelerators such as FACET, FACET-II, and AWAKE at CERN. One major challenge is an the ability to quickly create very high quality, extremely intense, custom current and energy profile beams while working with limited real time non-invasive diagnostics and utilizing time-varying uncertain initial beam distributions and accelerator components. Currently, a few individual accelerator labs have been developing and applying their own diagnostics tools and custom control and ML algorithms for automated machine tuning and optimization. The goal of this workshop was to bring together a group of accelerator physicists and accelerator related control and ML experts in order to define which controls and diagnostics would be most useful for existing and future accelerators and to create a plan for developing a new family of algorithms that can be shared and maintained by the community.