Physics model-informed Gaussian process for online optimization of particle accelerators

Hanuka, Adi; Huang, Xiaobiao; Shtalenkova, J.; Kennedy, Dylan; Edelen, Auralee; Zhang, Z.; Lalchand, Vidhi; Ratner, Daniel; Duris, J.

doi:10.1103/physrevaccelbeams.24.072802

Cited by 36 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As this is an initial implementation of this algorithm tested during SECAR commissioning operations, several improvements are being explored. For instance, the extensive database of accelerator historical data as well as physics simulations of SECAR and the accelerator may be used in implementing physics-informed optimizations of incoming beam parameters [20]. Additionally, beam specific priors can be developed by establishing a relationship between beam species, beam rigidity, and the GP kernel hyperparameters.…”

Section: Discussionmentioning

confidence: 99%

Online Bayesian Optimization for a Recoil Mass Separator

Miskovich,

Montes,

Berg

et al. 2022

Preprint

View full text Add to dashboard Cite

The SEparator for CApture Reactions (SECAR) is a next-generation recoil separator system at the Facility for Rare Isotope Beams (FRIB) designed for the direct measurement of capture reactions on unstable nuclei in inverse kinematics. To maximize the performance of this system, stringent requirements on the beam alignment to the central beam axis and on the ion-optical settings need to be achieved. These can be difficult to attain through manual tuning by human operators without potentially leaving the system in a sub-optimal and irreproducible state. In this work, we present the first development of online Bayesian optimization with a Gaussian process model to tune an ion beam through a nuclear astrophysics recoil separator. We show that this method achieves small incoming angular deviations (<1 mrad) in an efficient and reproducible manner that is at least three times faster than standard hand-tuning. Additionally, we present a Bayesian method for experimental optimization of the ion optics, and show that it validates the nominal theoretical ion-optical settings of the device, and improves the mass separation by 32% for some beams.

show abstract

Section: Discussionmentioning

confidence: 99%

Online Bayesian Optimization for a Recoil Mass Separator

Miskovich,

Montes,

Berg

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This makes these methods ideal for optimizing the accelerator incrementally during early commissioning. Information from physics simulations generated during the design process can also be used to help inform Bayesian optimization and speed up its convergence [48,49]. Data gathered during commissioning can then be used for automatic calibration of physics models to better match machine measurements and potentially identify early sources of systematic mis-match between the two that can be corrected either on the machine or in the physics simulation [50], as well as adapted over time to make model predictions more robust to time-varying sources of error [51].…”

Section: Artificial Intelligence and Machine Learning (Ai/ml)mentioning

confidence: 99%

C$^3$ Demonstration Research and Development Plan

Nanni¹,

Breidenbach²,

Vernieri³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…A GP is a Bayesian nonparametric machine learning technique that provides a flexible prior distribution over functions, enjoys analytical tractability, defines kernels for encoding domain structure, and has a fully probabilistic workflow for principled uncertainty reasoning [26,27]. For these reasons GPs are used widely in scientific modeling, with several recent methods more directly encoding physics into GP models: Numerical GPs have covariance functions resulting from temporal discretization of time-dependent partial differential equations (PDEs) which describe the physics [28,29], modified Matérn GPs can be defined to represent the solution to stochastic partial differential equations [30] and extend to Riemannian manifolds to fit more complex geometries [31], and the physics-informed basis-function GP derives a GP kernel directly from the physical model [32] -the latter method we elucidate in an experiment optimization example in the surrogate modeling motif.…”

Section: Multi-physics and Multi-scale Modelingmentioning

confidence: 99%

“…For the online control of particle accelerators, Hanuka et al [32] develop the physics-informed basis-function GP.…”

Section: Examplesmentioning

confidence: 99%

“…The use of a physics-infused GP can provide robustness in the sense that the physical process being simulated is grounded as a causal surrogate -i.e., encoding causal mechanisms of said physical system -rather than a nonparametric function approximator. The several physics-infused GP methods we highlighted are Numerical GPs that have covariance functions resulting from temporal discretization of time-dependent partial differential equations (PDEs) which describe the physics [28,29], modified Matérn GPs that can be defined to represent the solution to stochastic partial differential equations [30] and extend to Riemannian manifolds to fit more complex geometries [31], and the physics-informed basis-function GP that derives a GP kernel directly from the physical model [32].…”

Section: Integrationsmentioning

confidence: 99%

See 1 more Smart Citation

Simulation Intelligence: Towards a New Generation of Scientific Methods

Lavin¹,

Zenil²,

Krakauer³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The original "Seven Motifs" set forth a roadmap of essential methods for the field of scientific computing, where a motif is an algorithmic method that captures a pattern of computation and data movement. 1 We present the Nine Motifs of Simulation Intelligence, a roadmap for the development and integration of the essential algorithms necessary for a merger of scientific computing, scientific simulation, and artificial intelligence. We call this merger simulation intelligence (SI), for short. We argue the motifs of simulation intelligence are interconnected and interdependent, much like the components within the layers of an operating system. Using this metaphor, we explore the nature of each layer of the simulation intelligence "operating system" stack (SI-stack) and the motifs therein:1. Multi-physics and multi-scale modeling 2. Surrogate modeling and emulation 3. Simulation-based inference 4. Causal modeling and inference 5. Agent-based modeling 6. Probabilistic programming 7. Differentiable programming 8. Open-ended optimization Machine programmingWe believe coordinated efforts between motifs offers immense opportunity to accelerate scientific discovery, from solving inverse problems in synthetic biology and climate science, to directing nuclear energy experiments and predicting emergent behavior in socioeconomic settings. We elaborate on each layer of the SI-stack, detailing the state-of-art methods, presenting examples to highlight challenges and opportunities, and advocating for specific ways to advance the motifs and the synergies from their combinations. Advancing and integrating these technologies can enable a robust and efficient hypothesis-simulation-analysis type of scientific method, which we introduce with several use-cases for human-machine teaming and automated science.

show abstract

Physics model-informed Gaussian process for online optimization of particle accelerators

Cited by 36 publications

References 22 publications

Online Bayesian Optimization for a Recoil Mass Separator

Online Bayesian Optimization for a Recoil Mass Separator

C$^3$ Demonstration Research and Development Plan

Simulation Intelligence: Towards a New Generation of Scientific Methods

Contact Info

Product

Resources

About