DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A low-latency graph computer to identify metastable particles at the Large Hadron Collider for real-time analysis of potential dark matter signatures

Journal Article · · Scientific Reports

Abstract Image recognition is a pervasive task in many information-processing environments. We present a solution to a difficult pattern recognition problem that lies at the heart of experimental particle physics. Future experiments with very high-intensity beams will produce a spray of thousands of particles in each beam-target or beam-beam collision. Recognizing the trajectories of these particles as they traverse layers of electronic sensors is a massive image recognition task that has never been accomplished in real time. We present a real-time processing solution that is implemented in a commercial field-programmable gate array using high-level synthesis. It is an unsupervised learning algorithm that uses techniques of graph computing. A prime application is the low-latency analysis of dark-matter signatures involving metastable charged particles that manifest as disappearing tracks.

Sponsoring Organization:
USDOE
Grant/Contract Number:
SC0010007
OSTI ID:
2345816
Alternate ID(s):
OSTI ID: 2471870
Journal Information:
Scientific Reports, Journal Name: Scientific Reports Journal Issue: 1 Vol. 14; ISSN 2045-2322
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (15)

A detailed map of Higgs boson interactions by the ATLAS experiment ten years after the discovery journal July 2022
Unsupervised Learning book January 2004
Graph Neural Networks for Charged Particle Tracking on FPGAs journal March 2022
A fast method for particle tracking and triggering using small-radius silicon detectors journal March 2020
Tracking Triggers for the HL-LHC journal October 2020
Searching for metastable particles using graph computing journal September 2021
k-means Requires Exponentially Many Iterations Even in the Plane journal March 2011
Sorting networks and their applications conference January 1968
FPGA-Based Real-Time Charged Particle Trajectory Reconstruction at the Large Hadron Collider
  • Bartz, Edward; Chaves, Jorge; Gershtein, Yuri
  • 2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM) https://doi.org/10.1109/FCCM.2017.27
conference April 2017
Fast inference of Boosted Decision Trees in FPGAs for particle physics journal May 2020
On the Philosophy of Unsupervised Learning journal April 2023
Hardware Implementation Study of Particle Tracking Algorithm on FPGAs journal October 2021
A portrait of the Higgs boson by the CMS experiment ten years after the discovery journal July 2022
Track Trigger at the High Luminosity LHC conference December 2018
Modular Design of High-Throughput, Low-Latency Sorting Units journal July 2013