Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment

[EN] Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrin...

Descripción completa

Detalles Bibliográficos
Autores: Kekic, M., Adams, C., Woodruff, K., Renner, J., Church, E., Del Tutto, M., Hernando Morata, J. A., Gomez-Cadenas, J. J., Arazi, L., Arnquist, I.J., Azevedo, C. D. R., Bailey, K., Benlloch-Rodriguez, J. M., Rodriguez-Samaniego, Javier, Álvarez-Puerta, Vicente|||0000-0001-6938-8259, Ballester Merelo, Francisco José|||0000-0002-2464-5116, Esteve Bosch, Raul|||0000-0002-1289-6938, Herrero Bosch, Vicente|||0000-0003-0860-2789, Mora Mas, Francisco José|||0000-0003-2281-9546, Toledo Alarcón, José Francisco|||0000-0002-9782-4510
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/179911
Acceso en línea:https://riunet.upv.es/handle/10251/179911
Access Level:acceso abierto
Palabra clave:Dark Matter and Double Beta Decay (experiments)
TECNOLOGIA ELECTRONICA
Descripción
Sumario:[EN] Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in Xe-136. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6 MeV gamma rays from a Th-228 calibration source. We train a network on Monte Carlo-simulated events and show that, by applying on-the-fly data augmentation, the network can be made robust against differences between simulation and data. The use of CNNs offers significant improvement in signal efficiency and background rejection when compared to previous non-CNN-based analyses

Similares en LA Referencia