论文标题

使用卷积神经网络的KM3NET/ORCA的事件重建

Event reconstruction for KM3NeT/ORCA using convolutional neural networks

论文作者

Aiello, Sebastiano, Albert, Arnauld, Garre, Sergio Alves, Aly, Zineb, Ameli, Fabrizio, Andre, Michel, Androulakis, Giorgos, Anghinolfi, Marco, Anguita, Mancia, Anton, Gisela, Ardid, Miquel, Aublin, Julien, Bagatelas, Christos, Barbarino, Giancarlo, Baret, Bruny, Pree, Suzan Basegmez du, Bendahman, Meriem, Berbee, Edward, Bertin, Vincent, Biagi, Simone, Biagioni, Andrea, Bissinger, Matthias, Boettcher, Markus, Boumaaza, Jihad, Bouta, Mohammed, Bouwhuis, Mieke, Bozza, Cristiano, Branzas, Horea, Bruijn, Ronald, Brunner, Jürgen, Buis, Ernst-Jan, Buompane, Raffaele, Busto, Jose, Caiffi, Barbara, Calvo, David, Capone, Antonio, Carretero, Víctor, Castaldi, Paolo, Celli, Silvia, Chabab, Mohamed, Chau, Nhan, Chen, Andrew, Cherubini, Silvio, Chiarella, Vitaliano, Chiarusi, Tommaso, Circella, Marco, Cocimano, Rosanna, Coelho, Joao, Coleiro, Alexis, Molla, Marta Colomer, Coniglione, Rosa, Coyle, Paschal, Creusot, Alexandre, Cuttone, Giacomo, D'Onofrio, Antonio, Dallier, Richard, de Jong, Maarten, de Jong, Paul, De Palma, Mauro, de Wasseige, Gwenhaël, de Wolf, Els, Di Palma, Irene, Diaz, Antonio, Diego-Tortosa, Dídac, Distefano, Carla, Domi, Alba, Donà, Roberto, Donzaud, Corinne, Dornic, Damien, Dörr, Manuel, Drouhin, Doriane, Eberl, Thomas, Bojaddaini, Imad El, Elsaesser, Dominik, Enzenhöfer, Alexander, Fermani, Paolo, Ferrara, Giovanna, Filipovic, Miroslav, Filippini, Francesco, Fusco, Luigi Antonio, Gabella, Omar, Gal, Tamas, Soto, Alfonso Andres Garcia, Garufi, Fabio, Gatelet, Yoann, Geißelbrecht, Nicole, Gialanella, Lucio, Giorgio, Emidio, Gozzini, Sara Rebecca, Gracia, Rodrigo, Graf, Kay, Grasso, Dario, Grella, Giuseppe, Guidi, Carlo, Hallmann, Steffen, Hamdaoui, Hassane, Heijboer, Aart, Hekalo, Amar, Hernandez-Rey, Juan-Jose, Hofestädt, Jannik, Huang, Feifei, Ibnsalih, Walid Idrissi, Illuminati, Giulia, James, Clancy, Jung, Bouke Jisse, Kadler, Matthias, Kalaczyński, Piotr, Kalekin, Oleg, Katz, Uli, Chowdhury, Nafis Rezwan Khan, Kistauri, Giorgi, Koffeman, Els, Kooijman, Paul, Kouchner, Antoine, Kreter, Michael, Kulikovskiy, Vladimir, Lahmann, Robert, Larosa, Giuseppina, Breton, Remy Le, Leonardi, Ornella, Leone, Francesco, Leonora, Emanuele, Levi, Giuseppe, Lincetto, Massimiliano, Clark, Miles Lindsey, Lipreau, Thomas, Lonardo, Alessandro, Longhitano, Fabio, Coto, Daniel Lopez, Maderer, Lukas, Mańczak, Jerzy, Mannheim, Karl, Margiotta, Annarita, Marinelli, Antonio, Markou, Christos, Martin, Lilian, Martínez-Mora, Juan Antonio, Martini, Agnese, Marzaioli, Fabio, Mastroianni, Stefano, Mazzou, Safaa, Melis, Karel, Miele, Gennaro, Migliozzi, Pasquale, Migneco, Emilio, Mijakowski, Piotr, Palacios, Luis Salvador Miranda, Mollo, Carlos Maximiliano, Morganti, Mauro, Moser, Michael, Moussa, Abdelilah, Muller, Rasa, Musumeci, Mario, Nauta, Lodewijk, Navas, Sergio, Nicolau, Carlo Alessandro, Fearraigh, Brían Ó, Organokov, Mukharbek, Orlando, Angelo, Papalashvili, Gogita, Papaleo, Riccardo, Pastore, Cosimo, Paun, Alice, Pavalas, Gabriela Emilia, Pellegrino, Carmelo, Perrin-Terrin, Mathieu, Piattelli, Paolo, Pieterse, Camiel, Pikounis, Konstantinos, Pisanti, Ofelia, Poirè, Chiara, Popa, Vlad, Post, Maarten, Pradier, Thierry, Pühlhofer, Gerd, Pulvirenti, Sara, Rabyang, Omphile, Raffaelli, Fabrizio, Randazzo, Nunzio, Rapicavoli, Antonio, Razzaque, Soebur, Real, Diego, Reck, Stefan, Riccobene, Giorgio, Richer, Marc, Rivoire, Stephane, Rovelli, Alberto, Greus, Francisco Salesa, Samtleben, Dorothea Franziska Elisabeth, Losa, Agustín Sánchez, Sanguineti, Matteo, Santangelo, Andrea, Santonocito, Domenico, Sapienza, Piera, Schnabel, Jutta, Seneca, Jordan, Sgura, Irene, Shanidze, Rezo, Sharma, Ankur, Simeone, Francesco, Sinopoulou, Anna, Spisso, Bernardino, Spurio, Maurizio, Stavropoulos, Dimitris, Steijger, Jos, Stellacci, Simona Maria, Taiuti, Mauro, Tayalati, Yahya, Tenllado, Enrique, Thakore, Tarak, Tingay, Steven, Tzamariudaki, Ekaterini, Tzanetatos, Dimitrios, Berg, Ad van den, van der Knaap, Frits, van Eijk, Daan, Van Elewyck, Véronique, van Haren, Hans, Vannoye, Godefroy, Vasileiadis, George, Versari, Federico, Viola, Salvatore, Vivolo, Daniele, Wilms, Joern, Wojaczyński, Rafał, Zaborov, Dmitry, Zavatarelli, Sandra, Zegarelli, Angela, Zito, Daniele, Zornoza, Juan-de-Dios, Zúñiga, Juan, Zywucka, Natalia

论文摘要

KM3NET研究基础设施目前正在地中海的两个地点正在建设中。法国海岸附近的KM3NET/ORCA Water-Cherenkov Neutmino探测器将用光传感器来启动几兆雄的海水。它的主要目的是确定中微子质量排序。这项工作旨在使用km3net/orca检测器的模拟数据集证明深卷积神经网络对中微子望远镜的一般适用性。为此,使用网络来实现重建和分类任务,这些任务构成了KM3NET意向书中为KM3NET/ORCA提供的分析管道的替代方案。它们用于推断事件的重建估计值,对入射中微子的方向和相互作用点。由中微子相互作用引起的带电颗粒产生的Cherenkov光的空间分布分类为淋浴或轨道样,并且识别与检测到大气中微子相关的主要背景过程。提供了与机器学习分类和先前针对KM3NET/ORCA开发的最大样本重建算法的性能比较。结果表明,这种深层卷积神经网络在模拟大型中微子望远镜的模拟数据集中的应用可产生竞争性重建结果和相对于经典方法的绩效改进。

The KM3NeT research infrastructure is currently under construction at two locations in the Mediterranean Sea. The KM3NeT/ORCA water-Cherenkov neutrino detector off the French coast will instrument several megatons of seawater with photosensors. Its main objective is the determination of the neutrino mass ordering. This work aims at demonstrating the general applicability of deep convolutional neural networks to neutrino telescopes, using simulated datasets for the KM3NeT/ORCA detector as an example. To this end, the networks are employed to achieve reconstruction and classification tasks that constitute an alternative to the analysis pipeline presented for KM3NeT/ORCA in the KM3NeT Letter of Intent. They are used to infer event reconstruction estimates for the energy, the direction, and the interaction point of incident neutrinos. The spatial distribution of Cherenkov light generated by charged particles induced in neutrino interactions is classified as shower- or track-like, and the main background processes associated with the detection of atmospheric neutrinos are recognized. Performance comparisons to machine-learning classification and maximum-likelihood reconstruction algorithms previously developed for KM3NeT/ORCA are provided. It is shown that this application of deep convolutional neural networks to simulated datasets for a large-volume neutrino telescope yields competitive reconstruction results and performance improvements with respect to classical approaches.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源