Developing a Bubble Chamber Particle Discriminator Using Semi-Supervised Learning

physics.comp-ph

/ Authors

B. Matusch, C. Amole, M. Ardid, I. J. Arnquist, D. M. Asner, D. Baxter, E. Behnke, M. Bressler, B. Broerman, G. Cao

and 63 more authors

C. J. Chen, U. Chowdhury, K. Clark, J. I. Collar, P. S. Cooper, C. B. Coutu, C. Cowles, M. Crisler, G. Crowder, N. A. Cruz-Venegas, C. E. Dahl, M. Das, S. Fallows, J. Farine, I. Felis, R. Filgas, F. Girard, G. Giroux, J. Hall, C. Hardy, O. Harris, T. Hillier, E. W. Hoppe, C. M. Jackson

/ Abstract

The identification of non-signal events is a major hurdle to overcome for bubble chamber dark matter experiments such as PICO-60. The current practice of manually developing a discriminator function to eliminate background events is difficult when available calibration data is frequently impure and present only in small quantities. In this study, several different discriminator input/preprocessing formats and neural network architectures are applied to the task. First, they are optimized in a supervised learning context. Next, two novel semi-supervised learning algorithms are trained, and found to replicate the Acoustic Parameter (AP) discriminator previously used in PICO-60 with a mean of 97% accuracy.

Developing a Bubble Chamber Particle Discriminator Using Semi-Supervised Learning

physics.comp-ph

/ Authors

B. Matusch, C. Amole, M. Ardid, I. J. Arnquist, D. M. Asner, D. Baxter, E. Behnke, M. Bressler, B. Broerman, G. Cao

and 63 more authors

C. J. Chen, U. Chowdhury, K. Clark, J. I. Collar, P. S. Cooper, C. B. Coutu, C. Cowles, M. Crisler, G. Crowder, N. A. Cruz-Venegas, C. E. Dahl, M. Das, S. Fallows, J. Farine, I. Felis, R. Filgas, F. Girard, G. Giroux, J. Hall, C. Hardy, O. Harris, T. Hillier, E. W. Hoppe, C. M. Jackson

/ Abstract

The identification of non-signal events is a major hurdle to overcome for bubble chamber dark matter experiments such as PICO-60. The current practice of manually developing a discriminator function to eliminate background events is difficult when available calibration data is frequently impure and present only in small quantities. In this study, several different discriminator input/preprocessing formats and neural network architectures are applied to the task. First, they are optimized in a supervised learning context. Next, two novel semi-supervised learning algorithms are trained, and found to replicate the Acoustic Parameter (AP) discriminator previously used in PICO-60 with a mean of 97% accuracy.

, M. Jin

, B. Loer