On-detector machine learning for beam-induced background rejection at a 10 TeV muon collider
Abstract A 10 TeV Muon Collider is a compelling candidate for a future energy-frontier facility, offering unprecedented opportunities to explore the fundamental laws of particle physics. Muon decays in the collider ring produce intense beam-induced background (BIB) that can overwhelm detector occupancy and exceed readout bandwidth constraints. We investigate the potential of on-detector Machine Learning for BIB rejection in the vertex detector, exploiting pixel cluster shapes to distinguish background from collision products. We study three classes of lightweight neural-network architectures, and evaluate their implementation feasibility using high-level synthesis. Selected architectures achieve 88-90% data reduction at 99% signal efficiency, while requiring hardware resources compatible with potential ASIC implementation. These results demonstrate the potential of performing substantial BIB rejection directly in the pixel readout, providing a strategy for meeting the tracker readout requirements at a future Muon Collider.
Authors
- Ryan Michaud
- Doug Berry (ORCID: https://orcid.org/0000-0002-5383-8320)
- J. Pearkes (ORCID: https://orcid.org/0000-0002-5205-4065)
- M. Littmann (ORCID: https://orcid.org/0009-0009-6407-3130)
- Nhan Tran (ORCID: https://orcid.org/0000-0002-8440-6854)
- Farah Fahim (ORCID: https://orcid.org/0000-0003-1252-1447)
- Benjamin Parpillon (ORCID: https://orcid.org/0009-0002-6713-1497)
- James Hirschauer (ORCID: https://orcid.org/0000-0002-8244-0805)
- Giuseppe Di Guglielmo (ORCID: https://orcid.org/0000-0002-5749-1432)
- N. Manganelli (ORCID: https://orcid.org/0000-0002-3398-4531)
- Daniel Abadjiev (ORCID: https://orcid.org/0000-0002-2702-2141)
- Petar Maksimovic (ORCID: https://orcid.org/0000-0002-2358-2168)
- B. R. Roberts (ORCID: https://orcid.org/0000-0001-5235-8256)
- Chinar Syal (ORCID: https://orcid.org/0009-0001-9451-8980)
- Harshul Gupta (ORCID: https://orcid.org/0000-0001-8551-7866)
- Danush Shekar (ORCID: https://orcid.org/0000-0001-6679-6708)
- Aidan Nicholas (ORCID: https://orcid.org/0009-0001-0837-4395)
- Ron Lipton (ORCID: https://orcid.org/0000-0002-6665-7289)
- Eliza Howard
- David Jiang
- Ricardo Silvestre (ORCID: https://orcid.org/0009-0001-4333-8058)
- Amit Trivedi (ORCID: https://orcid.org/0000-0001-5436-7922)
- Shiqi Kuang (ORCID: https://orcid.org/0009-0003-2765-1671)
- Mark S. Neubauer (ORCID: https://orcid.org/0000-0001-8434-9274)
- A Gandrakota (ORCID: https://orcid.org/0000-0003-4860-3233)
- Benjamin Weiss
- Benjamin Rosser (ORCID: https://orcid.org/0000-0001-7492-831X)
- Tsz Ngong You
- Jennet Dickinson (ORCID: https://orcid.org/0000-0001-5450-5328)
- Morris Swartz
- Adam Quinn (ORCID: https://orcid.org/0009-0006-0505-6371)
- Arghya Ranjan Das (ORCID: https://orcid.org/0000-0001-8451-0806)
- Corrinne Mills
- Karri Folan Di Petrillo (ORCID: https://orcid.org/0000-0001-8001-4602)
- Keith Ulmer (ORCID: https://orcid.org/0000-0001-6875-9177)
- Mohammad Abrar Wadud (ORCID: https://orcid.org/0000-0002-0653-0761)
- Miaoyuan Liu (ORCID: https://orcid.org/0000-0001-9012-395X)
- Lindsey Gray (ORCID: https://orcid.org/0000-0002-6408-4288)
Institutions
- Northeastern University (US)
- Fermi National Accelerator Laboratory (US)
- Johns Hopkins University (US)
- University of Illinois Urbana-Champaign (US)
- University of Colorado Boulder (US)
- Cornell University (US)
- Purdue University West Lafayette (US)
- University of Illinois Chicago (US)
- University of Chicago (US)
Publication Details
- Journal
- Machine Learning Science and Technology
- Published
- 2026-11-02
- DOI
- https://doi.org/10.1088/2632-2153/aebcc0
- Primary Topic
- Particle Detector Development and Performance
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- U.S. Department of Energy
- Simons Foundation
- Science Foundation Ireland
- Office of Science
- Division of Physics
- Office of Advanced Cyberinfrastructure
- Advanced Scientific Computing Research
- High Energy Physics