Результаты исследований: Научные публикации в периодических изданиях › статья по материалам конференции › Рецензирование
Reconstruction of sub-threshold events of cosmic-ray radio detectors using an autoencoder. / the Tunka-Rex Collaboration.
в: Proceedings of Science, Том 395, 223, 18.03.2022.Результаты исследований: Научные публикации в периодических изданиях › статья по материалам конференции › Рецензирование
}
TY - JOUR
T1 - Reconstruction of sub-threshold events of cosmic-ray radio detectors using an autoencoder
AU - the Tunka-Rex Collaboration
AU - Bezyazeekov, P.
AU - Shipilov, D.
AU - Kostunin, D.
AU - Plokhikh, I.
AU - Mikhaylenko, A.
AU - Turishcheva, P.
AU - Golovachev, S.
AU - Sotnikov, V.
AU - Sotnikova, E.
AU - Bezyazeekov, P.
AU - Budnev, N.
AU - Fedorov, O.
AU - Gress, O.
AU - Grishin, O.
AU - Haungs, A.
AU - Huege, T.
AU - Kazarina, Y.
AU - Kleifges, M.
AU - Korosteleva, E.
AU - Kostunin, D.
AU - Kuzmichev, L.
AU - Lenok, V.
AU - Lubsandorzhiev, N.
AU - Malakhov, S.
AU - Marshalkina, T.
AU - Monkhoev, R.
AU - Osipova, E.
AU - Pakhorukov, A.
AU - Pankov, L.
AU - Prosin, V.
AU - Schröder, F. G.
AU - Shipilov, D.
AU - Zagorodnikov, A.
N1 - Funding Information: The authors would like to express gratitude to the colleagues from KCDC team. The development and testing of the software was supported by the state contract with Institute of Thermophysics SB RAS. Publisher Copyright: © Copyright owned by the author(s).
PY - 2022/3/18
Y1 - 2022/3/18
N2 - Radio detection of air showers produced by ultra-high energy cosmic rays is a cost-effective technique for the next generation of sparse arrays. The performance of this technique strongly depends on the environmental background, which has different constituents, namely anthropogenic radio frequency interference, synchrotron galactic radiation and others. These components have recognizable features, which can help for background suppression. A powerful method for handling this is the application of convolution neural networks with a specific architecture called autoencoder. By suppressing unwanted signatures, the autoencoder keeps the signal-like ones. We have successfully developed and trained an autoencoder, which is now applied to the data from Tunka-Rex. We show the procedures of the training and optimization of the network including benchmarks of different architectures. Using the autoencoder, we improved the standard analysis of Tunka-Rex in order to lower the threshold of the detection. This enables the reconstructing of sub-threshold events with energies lower than 0.1 EeV with satisfactory angular and energy resolutions.
AB - Radio detection of air showers produced by ultra-high energy cosmic rays is a cost-effective technique for the next generation of sparse arrays. The performance of this technique strongly depends on the environmental background, which has different constituents, namely anthropogenic radio frequency interference, synchrotron galactic radiation and others. These components have recognizable features, which can help for background suppression. A powerful method for handling this is the application of convolution neural networks with a specific architecture called autoencoder. By suppressing unwanted signatures, the autoencoder keeps the signal-like ones. We have successfully developed and trained an autoencoder, which is now applied to the data from Tunka-Rex. We show the procedures of the training and optimization of the network including benchmarks of different architectures. Using the autoencoder, we improved the standard analysis of Tunka-Rex in order to lower the threshold of the detection. This enables the reconstructing of sub-threshold events with energies lower than 0.1 EeV with satisfactory angular and energy resolutions.
UR - http://www.scopus.com/inward/record.url?scp=85144126827&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85144126827
VL - 395
JO - Proceedings of Science
JF - Proceedings of Science
SN - 1824-8039
M1 - 223
T2 - 37th International Cosmic Ray Conference, ICRC 2021
Y2 - 12 July 2021 through 23 July 2021
ER -
ID: 41163427