Object detection with deep learning for rare event search in the GADGET II TPC
Artikel i vetenskaplig tidskrift, 2025

In the pursuit of identifying rare two-particle events within the GADGET II Time Projection Chamber (TPC), this paper presents a comprehensive approach for leveraging Convolutional Neural Networks (CNNs) and various data processing methods. To address the inherent complexities of 3D TPC track reconstructions, the data is expressed in 2D projections and 1D quantities. This approach capitalizes on the diverse data modalities of the TPC, allowing for the efficient representation of the distinct features of the 3D events, with no loss in topology uniqueness. Additionally, it leverages the computational efficiency of 2D CNNs and benefits from the extensive availability of pre-trained models. Given the scarcity of real training data for the rare events of interest, simulated events are used to train the models to detect real events. To account for potential distribution shifts when predominantly depending on simulations, significant perturbations are embedded within the simulations. This produces a broad parameter space that works to account for potential physics parameter and detector response variations and uncertainties. These parameter-varied simulations are used to train sensitive 2D CNN object detectors. When combined with 1D histogram peak detection algorithms, this multi-modal detection framework is highly adept at identifying rare, two-particle events in data taken during experiment 21072 at the Facility for Rare Isotope Beams (FRIB), demonstrating a 100% recall for events of interest. We present the methods and outcomes of our investigation and discuss the potential future applications of these techniques.

Object detection

Convolutional neural network

Rare event detection

GADGET

Machine learning

Time projection chamber

Författare

Tyler Wheeler

Michigan State University

S. Ravishankar

Michigan State University

C. Wrede

Michigan State University

A. Andalib

Michigan State University

A. Anthony

Michigan State University

High Point University

Y. Ayyad

Michigan State University

Universidade de Santiagode Compostela

B. Jain

Michigan State University

A. Jaros

Michigan State University

R. Mahajan

Michigan State University

L. Schaedig

Michigan State University

A. Adams

Michigan State University

S. Ahn

Institute for Basic Science

J. M. Allmond

Oak Ridge National Laboratory

D. Bardayan

University of Notre Dame

D. Bazin

Michigan State University

K. Bosmpotinis

Michigan State University

T. Budner

Argonne National Laboratory

S. R. Carmichael

University of Notre Dame

S. M. Cha

Institute for Basic Science

A. Chen

McMaster University

K. A. Chipps

Oak Ridge National Laboratory

J. M. Christie

University of Tennessee

I. Cox

University of Tennessee

J. Dopfer

Michigan State University

M. Friedman

The Hebrew University Of Jerusalem

J. Garcia-Duarte

Lawrence Livermore National Laboratory

E. Good

Michigan State University

T. J. Gray

Oak Ridge National Laboratory

University of Tennessee

A. Green

The Hebrew University Of Jerusalem

R. Grzywacz

University of Tennessee

K. Hahn

Institute for Basic Science

R. Jain

Michigan State University

Erik Asbjörn Mikkelsen Jensen

Chalmers, Fysik, Subatomär, högenergi- och plasmafysik

Aarhus Universitet

T. King

Oak Ridge National Laboratory

S. N. Liddick

Michigan State University

B. Longfellow

Lawrence Livermore National Laboratory

R. Lubna

Michigan State University

C. Marshall

Ohio University

Michigan State University

Y. Mishnayot

Lawrence Livermore National Laboratory

A. J. Mitchell

Australian National University

F. Montes

Michigan State University

T. H. Ogunbeku

Michigan State University

Mississippi State University

Lawrence Livermore National Laboratory

J. Owens-Fryar

Michigan State University

S. D. Pain

Oak Ridge National Laboratory

University of Tennessee

J. Pereira

Michigan State University

E. Pollacco

Institut de Recherche sur les Lois Fondamentales de l'Univers

A. M. Rogers

University of Massachusetts Lowell

M. Z. Serikow

Michigan State University

K. Setoodehnia

Michigan State University

L. J. Sun

Michigan State University

J. Surbrook

Michigan State University

A. Tsantiri

Michigan State University

L. E. Weghorn

Michigan State University

Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment

0168-9002 (ISSN)

Vol. 1080 170659

Ämneskategorier (SSIF 2025)

Subatomär fysik

DOI

10.1016/j.nima.2025.170659

Mer information

Senast uppdaterat

2025-06-13