Submitted manuscript, 4.49 MB, PDF document
Available under license: CC BY: Creative Commons Attribution 4.0 International License
Final published version
Licence: CC BY: Creative Commons Attribution 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Cosmic Background Removal with Deep Neural Networks in SBND
AU - SBND Collaboration
AU - Acciarri, R.
AU - Backhouse, C.
AU - Badgett, W.
AU - Bagby, L.
AU - Basque, V.
AU - M.,
AU - C.,
AU - Bazetto, Q.
AU - Bhanderi, A.
AU - Bhat, A.
AU - Brailsford, D.
AU - A.,
AU - Brandt, G.
AU - M.,
AU - Carneiro, F.
AU - Chisnall, G.
AU - J.,
AU - Crespo-Anadón, I.
AU - Cristaldo, E.
AU - Cuesta, C.
AU - I.,
AU - Astiz, L. de Icaza
AU - Roeck, A. De
AU - Tutto, M. Del
AU - Benedetto, V. Di
AU - Ereditato, A.
AU - J.,
AU - A.,
AU - Ezeribe, C.
AU - R.,
AU - B.,
AU - Fleming, T.
AU - Foreman, W.
AU - Franco, D.
AU - Gao, S.
AU - Garcia-Gamez, D.
AU - Frandini, H.
AU - Gil-Botella, I.
AU - Gollapinni, S.
AU - Goodwin, O.
AU - W.,
AU - Griffith, C.
AU - Guenette, R.
AU - Guzowski, P.
AU - Ham, T.
AU - Holin, A.
AU - Kalra, D.
AU - Kashur, L.
AU - M.,
AU - Nowak, Jaroslaw
AU - Lay, Henry
PY - 2021/8/24
Y1 - 2021/8/24
N2 - 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 networks, and an updated dataset with a more realistic detector simulation prior to the application of this technique to real neutrino data.
AB - 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 networks, and an updated dataset with a more realistic detector simulation prior to the application of this technique to real neutrino data.
KW - physics.data-an
U2 - 10.3389/frai.2021.649917
DO - 10.3389/frai.2021.649917
M3 - Journal article
VL - 4
JO - Frontiers in Artificial Intelligence
JF - Frontiers in Artificial Intelligence
SN - 2624-8212
M1 - 649917
ER -