SuperCDMS Event Reconstruction Using Convolutional Neural Networks [Thesis]
Abstract
The SuperCDMS experiment uses cryogenic silicon and germanium detectors to search for dark matter candidates such as WIMPs (Weakly Interacting Massive Particles) streaming through the Earth. Collisions in the silicon and germanium crystals are expected to produce phonons whose thermal signatures can be measured. This thesis first describes the integration of a new Signal Distribution Unit (SDU) to the SuperCDMS data acquisition system, which allows for synchronization of multiple detectors and electronic/mechanical noise characterization via accelerometer, antenna, and AC phase measurements. From SuperCDMS detector data it is necessary to reconstruct the energies of the particle events. This thesis explores the use of Convolutional Neural Networks (CNNs) to perform this reconstruction and finds that, although they perform well, changing the noise model breaks the model and requires the neural network to be retrained. In order to mitigate this issue, a new CNN model is proposed which includes the noise Power Spectral Density (PSD) of the data as an additional input to the CNN. While it proves to be effective as a denoising algorithm, it still fails for data with a different noise model. However, including data from multiple PSDs in the neural network training sample allows it to handle data withmore »
- Authors:
-
- Univ. of British Columbia, Vancouver, BC (Canada)
- Publication Date:
- Research Org.:
- Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Univ. of British Columbia, Vancouver, BC (Canada)
- Sponsoring Org.:
- USDOE Office of Science (SC), High Energy Physics (HEP)
- OSTI Identifier:
- 1864219
- Report Number(s):
- FERMILAB-MASTERS-2020-11
oai:inspirehep.net:2057310
- DOE Contract Number:
- AC02-07CH11359
- Resource Type:
- Thesis/Dissertation
- Resource Relation:
- Related Information: Thesis
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 79 ASTRONOMY AND ASTROPHYSICS; 46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
Citation Formats
Soares Bezerra, Lucas Valenca. SuperCDMS Event Reconstruction Using Convolutional Neural Networks [Thesis]. United States: N. p., 2020.
Web.
Soares Bezerra, Lucas Valenca. SuperCDMS Event Reconstruction Using Convolutional Neural Networks [Thesis]. United States.
Soares Bezerra, Lucas Valenca. 2020.
"SuperCDMS Event Reconstruction Using Convolutional Neural Networks [Thesis]". United States. https://www.osti.gov/servlets/purl/1864219.
@article{osti_1864219,
title = {SuperCDMS Event Reconstruction Using Convolutional Neural Networks [Thesis]},
author = {Soares Bezerra, Lucas Valenca},
abstractNote = {The SuperCDMS experiment uses cryogenic silicon and germanium detectors to search for dark matter candidates such as WIMPs (Weakly Interacting Massive Particles) streaming through the Earth. Collisions in the silicon and germanium crystals are expected to produce phonons whose thermal signatures can be measured. This thesis first describes the integration of a new Signal Distribution Unit (SDU) to the SuperCDMS data acquisition system, which allows for synchronization of multiple detectors and electronic/mechanical noise characterization via accelerometer, antenna, and AC phase measurements. From SuperCDMS detector data it is necessary to reconstruct the energies of the particle events. This thesis explores the use of Convolutional Neural Networks (CNNs) to perform this reconstruction and finds that, although they perform well, changing the noise model breaks the model and requires the neural network to be retrained. In order to mitigate this issue, a new CNN model is proposed which includes the noise Power Spectral Density (PSD) of the data as an additional input to the CNN. While it proves to be effective as a denoising algorithm, it still fails for data with a different noise model. However, including data from multiple PSDs in the neural network training sample allows it to handle data with different types of noise while still maintaining the quality of the reconstruction. Nevertheless, neural networks trained even on multiple PSDs do not robustly handle data taken with PSDs dissimilar to those in the training sample, suggesting that CNNs may need to be retrained whenever the noise environment changes in a significant way.},
doi = {},
url = {https://www.osti.gov/biblio/1864219},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sat Aug 01 00:00:00 EDT 2020},
month = {Sat Aug 01 00:00:00 EDT 2020}
}