AI-optimized detector design for the future Electron-Ion Collider: the dual-radiator RICH case

TL;DR

This paper introduces a Bayesian optimization and machine learning-based framework to enhance detector design, demonstrated on a dual-radiator RICH detector for the Electron-Ion Collider, outperforming baseline designs.

Contribution

It presents a novel automated, parallelized approach for detector R&D that encodes requirements and optimizes designs using realistic simulations.

Findings

Optimized detector design outperforms baseline in simulations

Framework is highly parallelized and generalizable to other detectors

Applicable to any detector R&D with available realistic simulations

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.