Physics model-informed Gaussian process for online optimization of particle accelerators
| Autor: | Vidhi Lalchand, Joseph Duris, Adi Hanuka, Zhen Zhang, Xiaobiao Huang, J. Shtalenkova, Daniel Ratner, Auralee Edelen, D. Kennedy |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Accelerator Physics (physics.acc-ph)
FOS: Computer and information sciences Computer Science - Machine Learning Nuclear and High Energy Physics Physics and Astronomy (miscellaneous) Complex system FOS: Physical sciences QC770-798 Machine Learning (cs.LG) law.invention symbols.namesake law Simple (abstract algebra) Nuclear and particle physics. Atomic energy. Radioactivity Encoding (memory) Gaussian process Particle accelerator Surfaces and Interfaces Construct (python library) Computational Physics (physics.comp-ph) Range (mathematics) Computer engineering Online optimization symbols Physics - Accelerator Physics Physics - Computational Physics |
| Zdroj: | Physical Review Accelerators and Beams, Vol 24, Iss 7, p 072802 (2021) |
| ISSN: | 2469-9888 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|