Corpus ID: 227248124

Cosmic Background Removal with Deep Neural Networks in SBND

@article{Acciarri2020CosmicBR,
  title={Cosmic Background Removal with Deep Neural Networks in SBND},
  author={S. C. R. Acciarri and C. Adams and C. Backhouse and W. Badgett and L. Bagby and V. Basque and M. and C. and Q. Bazetto and A. Bhanderi and A. Bhat and D. Brailsford and {\'A}. and G. Brandt and F. Carneiro and Y. Chen and H. Chen and G. Chisnall and J. and I. Crespo-Anad'on and E. Cristaldo and C. Cuesta and I.. and L. Astiz and A. Roeck and M. Tutto and V. D. Benedetto and A. Ereditato and J. Evans and C. Ezeribe and R. and S. Fitzpatrick and B. and T. Fleming and W. Foreman and D. Franco and S. Gao and D. Garc{\'i}a-G{\'a}mez and H. Frandini and I. Gil-Botella and S. Gollapinni and O. Goodwin and P. Green and W. and C. Griffith and R. Guenette and P. Guzowski and T. Ham and A. Holin and D.Kalra and L. Kashur and J. Kim and V. and A. Kudryavtsev and J. Larkin and I. Lepetic and R. Littlejohn and C. Louis and M. Malek and D. Mardsen and F. Marinho and A. Mastbaum and K. Mavrokoridis and N. McConkey and V. Meddage and D. and P. M'endez and T. Mettler and K. Mistry and M. Mooney and L. Mora and A. Moura and A. Navrer-Agasson and A. Nowak and O. Palamara and V. Pandey and J. Pater and L. Paulucci and L. Pimentel and F. Psihas and G. Putnam and E. Raguzin and M. Reggiani-Guzzo and D. Rivera and M. Ross-Lonergan and G. Scanavini and A. Scarff and W. Schmitz and M. Soderberg and S. Soldner-Rembold and J. Spitz and {\~N}. and C. Spooner and M. Stancari and G. and V. Stenico and A. Szelc and W. Tang and J. T. Vidal and D. Torretta and M. Toups and M. Tripathi and S. Tufanli and E. Tyley and A. Valdiviesso and E. Worcester and M. Worcester and J. Yu and B. Zamorano and J. Zennamo and A. N. Laboratory and Universitat Bern and B. N. Laboratory and Universidade Estadual de Campinas and Center for Information Technology Renato Archer Campinas and Cern and Enrico Fermi Institute and Ciemat and Colorado State University and C. University and Universidade Federal do Abc and Universidade Federal de Alfenas and Universidade Federal de Sao Carlos and F. N. Laboratory and U. Florida and U. Granada and H. University and I. O. Technology and L. University and U. Liverpool and Los Alamos National Laboratory and U. Manchester and U. Michigan and Fiuna Facultad de Ingenier'ia and U. Pennsylvania and R. University and U. Sheffield and U. Sussex and S. University and University of Tennessee at Knoxville and U. T. Arlington and U. London and W. Laboratory},
  journal={arXiv: Data Analysis, Statistics and Probability},
  year={2020}
}
In this paper, we have demonstrated a novel technique for pixel level segmentation to remove cosmic backgrounds from LArTPC images. We have shown how different deep neural networks can be designed and trained for this task, and presented metrics that can be used to select the best versions. The technique developed is applicable to other LArTPC detectors running at surface level, such as MicroBooNE, ICARUS and ProtoDUNE. We anticipate future publications studying the hyperparameters of these… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 34 REFERENCES
Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber
Scalable Deep Convolutional Neural Networks for Sparse, Locally Dense Liquid Argon Time Projection Chamber Data
Focal Loss for Dense Object Detection
Three-dimensional imaging for large LArTPCs
Deep Residual Learning for Image Recognition
Underground operation of the ICARUS T600 LAr-TPC: first results
...
1
2
3
4
...