Applying Deep Learning Techniques for Multiparticle Track Reconstruction of Drift Chamber Data
https://doi.org/10.56304/S2079562920060603
Abstract
The new coordinate-tracking detector TREK, based of drift chambers, is being developed at NRNU MEPhI for studies of ultrahigh energy cosmic rays. To reconstruct events with a high multiplicity from the data of drift chambers, the histogram method is currently used, which is designed to search for parallel tracks. However, we observe afterpulses in the experimental data obtained using a coordinate-tracking unit based on drift chambers (CTUDC). The afterpulses lead to fake track reconstructions. To solve this problem, a new method is being developed using deep learning. The paper presents the results of the development of this method and its application to simulated data.
About the Authors
V. S. Vorob’ev
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)
Russian Federation
Russian Federation
V. S. Vorob’ev,
Moscow, 115409.
Е. А. Zadeba
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)
Russian Federation
Russian Federation
Е. А. Zadeba,
Moscow, 115409.
R. V. Nikolaenko
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)
Russian Federation
Russian Federation
R. V. Nikolaenko,
Moscow, 115409.
А. А. Petrukhin
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)
Russian Federation
Russian Federation
А. А. Petrukhin,
Moscow, 115409.
I. Yu. Troshin
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)
Russian Federation
Russian Federation
I. Yu. Troshin,
Moscow, 115409.
References
1. Zadeba E.A. et al. // J. Instrum. 2014. V. 9. P. C08018.
2. Petrukhin A.A. // Phys. Usp. 2015. V. 58. P. 486–494.
3. Petrukhin A.A. // Nucl. Instrum. Methods Phys. Res., Sect. A. 2012. V. 692. P. 228–232.
4. Barabash L.S. et al. // Proc. Int. Conf. Neutrino-82. 1982. V. 2. P. 249
5. Vorobyev V.S. et al. // J. Phys.: Conf. Ser. 2018. V. 945. P. 012027.
6. Воробьев В.С., Борисов А.А., Волков Н.С., Задеба Е.А., Кожин А.С., Петрухин А.А., Фахрутдинов Р.М., Яшин И.И. // Ядерная физика и инжиниринг. 2017. Т. 8. № 4. С. 344-352 [Vorobyev V.S., Borisov A.A., Volkov N.S., Zadeba E.A., Kozhin A.S., Petrukhin A.A., Fakhrutdinov R.M., Yashin I.I. // Phys. At. Nucl. 2018. V. 81. P. 1325].
7. Nebauer C. // IEEE Trans. Neural Networks. 1998. V. 9. P. 685–696. https://doi.org/10.1109/72.701181
8. Garfield++. https://garfieldpp.web.cern.ch/.
9. Hochreiter S. et al. // Neural Comput. 1997. V. 9. P. 1735–1780.
10. Farrell S. et al. // EPJ Web Conf. 2017. V. 150. P. 00003.
Review
For citations:
Vorob’ev V.S., Zadeba Е.А., Nikolaenko R.V., Petrukhin А.А., Troshin I.Yu. Applying Deep Learning Techniques for Multiparticle Track Reconstruction of Drift Chamber Data. Nuclear Physics and Engineering. 2021;12(1):26-31. (In Russ.) https://doi.org/10.56304/S2079562920060603
Views:
29
Email this article 