Publication:
Convolutional neural network approach to event position reconstruction in DarkSide-50 experiment

Дата
2020
Авторы
Journal Title
Journal ISSN
Volume Title
Издатель
Научные группы
Организационные подразделения
Организационная единица
Институт ядерной физики и технологий
Цель ИЯФиТ и стратегия развития - создание и развитие научно-образовательного центра мирового уровня в области ядерной физики и технологий, радиационного материаловедения, физики элементарных частиц, астрофизики и космофизики.
Выпуск журнала
Аннотация
© 2020 Institute of Physics Publishing. All rights reserved.Neural networks are currently used in various fields of science and technology, as well as in experiments related to particle physics. DarkSide-50 is a two-phase (liquid and gas) argon TPC which has two main signals: scintillation in LAr (S1 signal) and electroluminescence in GAr (S2 signal) [1]. In the low-mass dark matter search only the more energetic second signal is used for position reconstruction [2]. As a result only events detected by seven central photomultiplier tubes are used for the analysis. Here we attempt to improve reconstruction using the convolutional neural networks (CNN).
Описание
Ключевые слова
Цитирование
Grobov, A. Convolutional neural network approach to event position reconstruction in DarkSide-50 experiment / Grobov, A., Ilyasov, A. // Journal of Physics: Conference Series. - 2020. - 1690. - № 1. - 10.1088/1742-6596/1690/1/012013
Коллекции