Low Frequency Noise Identification for the SuperCDMS Experiment using Convolutional Neural Networks

@misc{collaboration2026frequency,
  title = {{Low Frequency Noise Identification for the SuperCDMS Experiment using Convolutional Neural Networks}},
  author = {SuperCDMS collaboration and M. F. Albakry and I. Alkhatib and D. Alonso-González and J. Anczarski and T. Aralis and T. Aramaki and A. Ashtari Esfahani and I. Ataee Langroudy and R. Bhattacharyya and P. L. Brink and M. Buchanan and R. Bunker and B. Cabrera and R. Calkins and R. A. Cameron and C. Cartaro and D. G. Cerdeño and Y. -Y. Chang and J. -H. Chen and R. Chen and X. Chen and J. Cooley and P. Cushman and R. Cyna and S. Das and S. Dharani and M. L. di Vacri and M. D. Diamond and M. Elwan and S. Fallows and E. Figueroa-Feliciano and M. Ghaith and G. Godden and S. R. Golwala and G. Gonzalez and J. Hall and C. A. S. Harms and C. Hays and B. A. Hines and Z. Hong and L. Hsu and M. E. Huber and V. Iyer and M. Jha and V. K. S. Kashyap and M. H. Kelsey and K. T. Kennard and Z. Kromer and A. Kubik and N. A. Kurinsky and J. Leyva and J. Liu and Y. Liu and E. Lopez Asamar and R. López Nóe and R. Mahapatra and J. S. Mammo and P. C. McNamara and É. Michaud},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.00248},
  eprint = {2611.00248},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.00248},
  note = {CC BY 4.0},
}

TY  - UNPB
TI  - Low Frequency Noise Identification for the SuperCDMS Experiment using Convolutional Neural Networks
AU  - SuperCDMS collaboration
AU  - M. F. Albakry
AU  - I. Alkhatib
AU  - D. Alonso-González
AU  - J. Anczarski
AU  - T. Aralis
AU  - T. Aramaki
AU  - A. Ashtari Esfahani
AU  - I. Ataee Langroudy
AU  - R. Bhattacharyya
AU  - P. L. Brink
AU  - M. Buchanan
AU  - R. Bunker
AU  - B. Cabrera
AU  - R. Calkins
AU  - R. A. Cameron
AU  - C. Cartaro
AU  - D. G. Cerdeño
AU  - Y. -Y. Chang
AU  - J. -H. Chen
AU  - R. Chen
AU  - X. Chen
AU  - J. Cooley
AU  - P. Cushman
AU  - R. Cyna
AU  - S. Das
AU  - S. Dharani
AU  - M. L. di Vacri
AU  - M. D. Diamond
AU  - M. Elwan
AU  - S. Fallows
AU  - E. Figueroa-Feliciano
AU  - M. Ghaith
AU  - G. Godden
AU  - S. R. Golwala
AU  - G. Gonzalez
AU  - J. Hall
AU  - C. A. S. Harms
AU  - C. Hays
AU  - B. A. Hines
AU  - Z. Hong
AU  - L. Hsu
AU  - M. E. Huber
AU  - V. Iyer
AU  - M. Jha
AU  - V. K. S. Kashyap
AU  - M. H. Kelsey
AU  - K. T. Kennard
AU  - Z. Kromer
AU  - A. Kubik
AU  - N. A. Kurinsky
AU  - J. Leyva
AU  - J. Liu
AU  - Y. Liu
AU  - E. Lopez Asamar
AU  - R. López Nóe
AU  - R. Mahapatra
AU  - J. S. Mammo
AU  - P. C. McNamara
AU  - É. Michaud
PY  - 2026
DA  - 2026/11/01
PB  - arXiv
DO  - 10.48550/arxiv.2611.00248
UR  - https://arxiv.org/abs/2611.00248
AB  - The SuperCDMS experiment uses semiconductor crystal detectors operated at cryogenic temperatures to search for low-mass dark matter. Vibrations observed during the SuperCDMS Soudan experiment generated broadband low-frequency noise (LFN), which due to its similarity in the pulse shape to the low-energy signal events is difficult to remove. In the final low ionization threshold analysis, CDMSlite Run 3, the strong event selection criterion applied to remove LFN events also significantly reduced the ability to identify signal events in the low energy region, thus reducing the sensitivity of the experiment to low-mass dark matter. Therefore, an LFN rejection criterion using machine learning (ML) aimed to improve the signal efficiency while maintaining the signal purity has now been developed. This paper presents a new method using Convolutional Neural Networks (CNNs), its application to the CDMSlite Run 3 dataset, and its impact on dark matter sensitivities, with further investigation through case studies.
ER  -