Unsupervised learning for identifying events in active target experiments

Solli, R.; Bazin, D.; Hjorth-Jensen, M.; Kuchera, M. P.; Strauss, R. R.

doi:10.1016/j.nima.2021.165461

Unsupervised learning for identifying events in active target experiments

Journal Article · Wed May 26 00:00:00 EDT 2021 · Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment

DOI:https://doi.org/10.1016/j.nima.2021.165461· OSTI ID:1786294

^[1]; ^[2]; ^[3]; ^[4]; ^[5]

Expert Analytics AS, Oslo (Norway); Univ. of Oslo (Norway); Michigan State University
Michigan State Univ., East Lansing, MI (United States)
Michigan State Univ., East Lansing, MI (United States); Univ. of Oslo (Norway)
Davidson College, NC (United States)
Davidson College, NC (United States); Univ. of North Carolina, Chapel Hill, NC (United States)

This article presents novel applications of unsupervised machine learning methods to the problem of event separation in an active target detector, the Active-Target Time Projection Chamber (AT-TPC). The overarching goal is to group similar events in the early stages of the data analysis, thereby improving efficiency by limiting the computationally expensive processing of unnecessary events. The application of unsupervised clustering algorithms to the analysis of two-dimensional projections of particle tracks from a resonant proton scattering experiment on ⁴⁶Ar is introduced. We explore the performance of autoencoder neural networks and a pre-trained VGG16 Simonyan and Zisserman (2015) convolutional neural network. We study clustering performance on both data from a simulated ⁴⁶Ar experiment, and real events from the AT-TPC detector. We find that a -means algorithm applied to simulated data in the VGG16 latent space forms almost perfect clusters. Additionally, the VGG16+-means approach finds high purity clusters of proton events for real experimental data. Here, we also explore the application of clustering the latent space of autoencoder neural networks for event separation. While these networks show strong performance, they suffer from high variability in their results.

Research Organization:: Michigan State Univ., East Lansing, MI (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Nuclear Physics (NP); U.S. National Science Foundation; Research Council of Norway

Grant/Contract Number:: SC0020451; SC0021152

OSTI ID:: 1786294

Alternate ID(s):: OSTI ID: 1786832

Journal Information:: Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment, Journal Name: Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment Vol. 1010; ISSN 0168-9002

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (11)

On the Surprising Behavior of Distance Metrics in High Dimensional Space Aggarwal, Charu C.; Hinneburg, Alexander; Keim, Daniel A. Database Theory — ICDT 2001 https://doi.org/10.1007/3-540-44503-x_27	book	January 2001
Comparing partitions Hubert, Lawrence; Arabie, Phipps Journal of Classification, Vol. 2, Issue 1 https://doi.org/10.1007/BF01908075	journal	December 1985
Taylor expansion of the accumulated rounding error Linnainmaa, Seppo BIT, Vol. 16, Issue 2 https://doi.org/10.1007/BF01931367	journal	June 1976
Prototype AT-TPC: Toward a new generation active target time projection chamber for radioactive beam experiments Suzuki, D.; Ford, M.; Bazin, D. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 691 https://doi.org/10.1016/j.nima.2012.06.050	journal	November 2012
Active Target detectors for studies with exotic beams: Present and next future Mittig, W.; Beceiro-Novo, S.; Fritsch, A. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 784 https://doi.org/10.1016/j.nima.2014.10.048	journal	June 2015
Commissioning of the Active-Target Time Projection Chamber Bradt, J.; Bazin, D.; Abu-Nimeh, F. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 875 https://doi.org/10.1016/j.nima.2017.09.013	journal	December 2017
Machine learning methods for track classification in the AT-TPC Kuchera, M. P.; Ramanujan, R.; Taylor, J. Z. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 940 https://doi.org/10.1016/j.nima.2019.05.097	journal	October 2019
Study of spectroscopic factors at N= 29 using isobaric analogue resonances in inverse kinematics Bradt, J.; Ayyad, Y.; Bazin, D. Physics Letters B, Vol. 778 https://doi.org/10.1016/j.physletb.2018.01.015	journal	March 2018
A high-bias, low-variance introduction to Machine Learning for physicists Mehta, Pankaj; Bukov, Marin; Wang, Ching-Hao Physics Reports, Vol. 810 https://doi.org/10.1016/j.physrep.2019.03.001	journal	May 2019
Active targets for the study of nuclei far from stability Beceiro-Novo, S.; Ahn, T.; Bazin, D. Progress in Particle and Nuclear Physics, Vol. 84 https://doi.org/10.1016/j.ppnp.2015.06.003	journal	September 2015
Use of the Hough transformation to detect lines and curves in pictures Duda, Richard O.; Hart, Peter E. Communications of the ACM, Vol. 15, Issue 1 https://doi.org/10.1145/361237.361242	journal	January 1972

Similar Records

Convolutional Variational Autoencoder-based Unsupervised Learning for Power Systems Faults

Conference · Fri Nov 01 00:00:00 EDT 2024 · OSTI ID:2573606

Challenges for unsupervised anomaly detection in particle physics

Journal Article · Tue Mar 08 23:00:00 EST 2022 · Journal of High Energy Physics (Online) · OSTI ID:1976605

Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider

Journal Article · Mon Aug 09 00:00:00 EDT 2021 · TBD · OSTI ID:1832833

Related Subjects

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
Active target experiments
Autoencoder neural networks
Machine learning
Unsupervised learning

Unsupervised learning for identifying events in active target experiments

Citation Formats

References (11)

Similar Records

Related Subjects