Physics model-informed Gaussian process for online optimization of particle accelerators
Open Access
- 8 July 2021
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Accelerators and Beams
- Vol. 24 (7) , 072802
Abstract
High-dimensional optimization is a critical challenge for operating large-scale scientific facilities. We apply a physics-informed Gaussian process (GP) optimizer to tune a complex system. Typical GP models learn from past observations to make predictions, but this reduces their applicability to systems where there is limited relevant archive data. Instead, here we use a fast approximate model from physics simulations to design the GP model. The GP is then employed to make inferences from sequential online observations in order to optimize the system. Simulation and experimental studies were carried out to demonstrate the method for online control of a storage ring. Our method is a simple prescription to construct a custom GP model, including correlations between the high-dimensional input space, while encoding the physical response of a system. The ability to inform the machine-learning model with physics, without relying on the availability and range of prior data, may have wide applications in science.Keywords
All Related Versions
Funding Information
- U.S. Department of Energy (DE-AC02-76SF00515)
- Laboratory Directed Research and Development
- SLAC National Accelerator Laboratory
- Basic Energy Sciences (FWP 100637)
- Advanced Scientific Computing Research (FWP 2018-SLAC-100469ASCR)
This publication has 22 references indexed in Scilit:
- Robust simplex algorithm for online optimizationPhysical Review Accelerators and Beams, 2018
- Demonstration of Model-Independent Control of the Longitudinal Phase Space of Electron Beams in the Linac-Coherent Light Source with Femtosecond ResolutionPhysical Review Letters, 2018
- Physics-aware Gaussian processes in remote sensingApplied Soft Computing, 2018
- Manifold Gaussian Processes for regression2016
- Taking the Human Out of the Loop: A Review of Bayesian OptimizationProceedings of the IEEE, 2015
- PHYSICS-BASED COVARIANCE MODELS FOR GAUSSIAN PROCESSES WITH MULTIPLE OUTPUTSInternational Journal for Uncertainty Quantification, 2013
- Experimental determination of storage ring optics using orbit response measurementsNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 1997
- Every good regulator of a system must be a model of that system †International Journal of Systems Science, 1970
- A Simplex Method for Function MinimizationThe Computer Journal, 1965
- Generalized harmonic analysisActa Mathematica, 1930