AI-optimized detector design for the future Electron-Ion Collider: the dual-radiator RICH case
Abstract
Advanced detector R&D requires performing computationally intensive and detailed simulations as part of the detector-design optimization process. We propose a general approach to this process based on Bayesian optimization and machine learning that encodes detector requirements. As a case study, we focus on the design of the dual-radiator Ring Imaging Cherenkov (dRICH) detector under development as part of the particle-identification system at the future Electron-Ion Collider (EIC). The EIC is a US-led frontier accelerator project for nuclear physics, which has been proposed to further explore the structure and interactions of nuclear matter at the scale of sea quarks and gluons. We show that the detector design obtained with our automated and highly parallelized framework outperforms the baseline dRICH design within the assumptions of the current model. Our approach can be applied to any detector R&D, provided that realistic simulations are available.
Keywords
Cite
@article{arxiv.1911.05797,
title = {AI-optimized detector design for the future Electron-Ion Collider: the dual-radiator RICH case},
author = {E. Cisbani and A. Del Dotto and C. Fanelli and M. Williams and M. Alfred and F. Barbosa and L. Barion and V. Berdnikov and W. Brooks and T. Cao and M. Contalbrigo and S. Danagoulian and A. Datta and M. Demarteau and A. Denisov and M. Diefenthaler and A. Durum and D. Fields and Y. Furletova and C. Gleason and M. Grosse-Perdekamp and M. Hattawy and X. He and H. van Hecke and D. Higinbotham and T. Horn and C. Hyde and Y. Ilieva and G. Kalicy and A. Kebede and B. Kim and M. Liu and J. McKisson and R. Mendez and P. Nadel-Turonski and I. Pegg and D. Romanov and M. Sarsour and C. L. da Silva and J. Stevens and X. Sun and S. Syed and R. Towell and J. Xie and Z. W. Zhao and B. Zihlmann and C. Zorn},
journal= {arXiv preprint arXiv:1911.05797},
year = {2020}
}
Comments
22 pages, 11 figures