AI4EIC Hackathon: PID with the ePIC dRICH

¹ Brookhaven National Lab, Upton, NY, 33973, USA
² Catholic University of America, Washington, DC, 20064, USA
³ INFN Trieste and University of Trieste, Department of Physics, Trieste, 34127, Italy
⁴ Istituto Superiore di Sanitá, INFN, viale Regina Elena 299, Rome, 00161, Italy
⁵ Thomas Jefferson National Accelerator Center, Newport News, VA, 23606, USA
⁶ University of Manitoba, Physics, Winnipeg, MB, R3T 2Ns, Canada
⁷ William and Mary, Williamsburg, VA, 23185, USA

^* e-mail: {cfanelli@wm.edu}

Published online: 6 May 2024

Abstract

The inaugural AI4EIC Hackathon unfolded as a high-point satellite event during the second AI4EIC Workshop at William & Mary. The workshop itself boasted over two hundred participants in a hybrid format and delved into the myriad applications of Artificial Intelligence and Machine Learning (AI/ML) for the Electron-Ion Collider (EIC). This workshop aimed to catalyze advancements in AI/ML with applications ranging from advancements in accelerator and detector technologies—highlighted by the ongoing work on the ePIC detector and potential development of a second detector for the EIC—to data analytics, reconstruction, and particle identification, as well as the synergies between theoretical and experimental research. Complementing the technical agenda was an enriched educational outreach program that featured tutorials from leading AI/ML experts representing academia, national laboratories, and industry. The hackathon, held on the final day, showcased international participation with ten teams from around the globe. Each team, comprising up to four members, focused on the dual-radiator Ring Imaging Cherenkov (dRICH) detector, an integral part of the particle identification (PID) system in ePIC. The data for the hackathon were generated using the ePIC software suite. While the hackathon presented questions of increasing complexity, its challenges were designed with deliberate simplifications to serve as a preliminary step toward the integration of machine learning and deep learning techniques in PID with the dRICH detector. This article encapsulates the key findings and insights gained from this unique experience.