14–18 Sept 2026
Europe/Vienna timezone

Application of Machine Learning to Collision Parameter Tuning in the SuperKEKB Accelerator

17 Sept 2026, 12:10
20m

Speaker

Riku Takizawa (UTokyo)

Description

SuperKEKB is an electron–positron collider operating at a center-of-mass energy of 10.58 GeV and has achieved the world’s highest instantaneous luminosity. At present, collision parameters are optimized manually through a procedure known as an interaction-point (IP) knob tuning. This study aims to improve the efficiency and reproducibility of IP knob tuning, and ultimately automate the process using machine-learning techniques.
During the 2025-2026 operation period, we actually conducted several optimization approaches: (1) simultaneous multidimensional tuning based on Bayesian optimization, (2) optimization assisted by a luminosity regression model for stability of the optimization, and (3) optimization assisted by an encoder model trained on historical machine-operation data. In this presentation, we report a comparison of these methods and discuss their applicability to automated IP knob tuning.

Author

Co-authors

Dr Hiroyuki Nakayama (KEK IPNS / SOKENDAI) Dr Kazutaka Sumisawa (KEK IPNS / SOKENDAI /Nara Woman’s University) Dr Koji Hara (KEK IPNS / SOKENDAI) Prof. Yutaka Ushiroda (KEK IPNS / University of Tokyo / SOKENDAI)

Presentation materials

There are no materials yet.