Event reconstruction for KM3NeT/ORCA using convolutional neural networks

Aiello, S.; Albert, A.; Garre, S. Alves; Aly, Z.; Ameli, F.; André, M.; Androulakis, G.; Anghinolfi, M.; Anguita, M.; Anton, G.; Ardid, M.; Aublin, J.; Bagatelas, C.; Barbarino, G. C.; Baret, B.; Pree, S. Başeğmez du; Bendahman, M.; Berbee, E.; Berg, A. M. van den; Bertín, V.; Biagi, S.; Biagioni, A.; Bissinger, M.; Boettcher, Markus; Boumaaza, J.; Bouta, M.; Bouwhuis, M. C.; Bozza, C.; Brânzaş, H.; Bruijn, R.; Brünner, J.; Buis, E. J.; Buompane, R.; Busto, J.; Caiffi, B.; Calvo, David; Capone, A.; Carretero, V.; Castaldi, Paolo; Celli, S.; Chabab, M.; Chau, N.; Chen, A.; Cherubini, S.; Chiarella, V.; Chiarusi, T.; Circella, M.; Cocimano, R.; Coelho, J. A. B.; Coleiro, A.; Molla, Marta Colomer; Coniglione, R.; Coyle, P.; Creusot, A.; Cuttone, G.; D’Onofrio, Antonio; Dallier, R.; Palma, M. De; Palma, I. Di; Dı́az, A.; Diego-Tortosa, D.; Distefano, C.; Domi, Alba; Donà, R.; Donzaud, C.; Dornic, D.; Dörr, M.; Drouhin, D.; Eberl, T.; Eddyamoui, A.; Eeden, T. van; Eijk, D. van; Bojaddaini, I. El; Elsäesser, D.; Enzenhöfer, A.; Espinosa, V.; Fermani, P.; Ferrara, G.; Filipović, Miroslav; Filippini, F.; Fusco, L.; Gabella, Omar; Gal, T.; Soto, A. García; Garufi, F.; Gatelet, Y.; Geißelbrecht, N.; Gialanella, L.; Giorgio, Emidio; Gozzini, S. R.; Gracía, R.; Graf, Κ.; Grasso, Dario; Grella, G.; Guderian, D.; Guidi, C.; Hallmann, S.; Hamdaoui, H.; Haren, Hans van; Heijboer, A.; Hekalo, A.; Hernández-Rey, J. J.; Hofestädt, J.; Huang, F.; Ibnsalih, W. Idrissi; Illuminati, G.; James, C. W.; Jong, M. de; Jong, P. de; Jung, B. J.; Kadler, M.; Kalaczyński, P.; Kalekin, O.; Katz, U.; Chowdhury, Nafis Rezwan Khan; Kistauri, G.; Knaap, F. van der; Koffeman, E.; Kooijman, P.; Kouchner, A.; Kreter, M.; Kulikovskiy, V.; Lahmann, R.; Larosa, G.; Breton, R. Le; Leonardi, O.; Leone, F.; Leonora, E.; Levi, G.; Lincetto, Massimiliano; Clark, M. Lindsey; Lipreau, T.; Lonardo, A.; Longhitano, F.; Lopez-Coto, D.; Maderer, L.; Mańczak, J.; Mannheim, K.; Margiotta, A.; Marinelli, A.; Markou, C.; Martin, L.; Martínez-Mora, J. A.; Martini, A.; Marzaioli, Fabio; Mastroianni, S.; Mazzou, S.; Melis, K.; Miele, Gennaro; Migliozzi, P.; Migneco, E.; Mijakowski, P.; Miranda, Luis Salvador; Mollo, C.M.; Morganti, M.; Möser, Michael; Moussa, A.; Müller, R.; Musumeci, M.; Nauta, L.; Navas, S. Sánchez; Nicolau, C. A.; Fearraigh, B. Ó; Organokov, M.; Orlando, A.; Papalashvili, G.; Papaleo, R.; Pastore, C.; Păun, A.; Păvălaş, G. E.; Pellegrino, C.; Perrin-Terrin, M.; Piattelli, P.; Pieterse, C.; Pikounis, K.; Pisanti, O.; Poirè, C.; Popa, V.; Post, M.; Pradier, T.; Pühlhofer, G.; Pulvirenti, S.; Rabyang, O.; Raffaelli, F.; Randazzo, N.; Rapicavoli, Antonio; Razzaque, S.; Real, D.; Reck, S.; Riccobene, G.; Richer, M.; Rivoire, S.; Rovelli, A.; Greus, F. Salesa; Samtleben, D. F. E.; Losa, A. Sánchez; Sanguineti, M.; Santangelo, A.; Santonocito, D.; Sapienza, P.; Schnabel, J.; Seneca, J.; Sgura, I.; Shanidze, R.; Sharma, A.; Simeone, F.; Sinopoulou, A.; Spisso, B.; Spurio, M.; Stavropoulos, D.; Steijger, J. J. M.; Stellacci, Francesco; Taiuti, M.; Tayalati, Y.; Tenllado, E.; Thakore, T.; Tingay, S. J.; Tzamariudaki, E.; Tzanetatos, D.; Elewyck, V. Van; Vannoye, G.; Vasileiadis, G.; Versari, F.; Viola, Salvatore; Vivolo, D.; Wasseige, Gwenhaël de; Wilms, J.; Wojaczyński, R.; Wolf, E. de; Zaborov, D.; Zavatarelli, S.; Zegarelli, A.; Zito, D.; Zornoza, J. D.; Zúñiga, J.; Żywucka, N.

doi:10.1088/1748-0221/15/10/p10005

Cited by 24 publications

(18 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Deep learning algorithms have been adopted in KM3NeT since the middle of the last decade. Convolutional Neural Networks (CNNs), based on their TensorFlow 3 implementation, were explored first and successfully for event classification and neutrino property regression tasks in ORCA [6]. For training and validation of the CNNs, simulated events were transformed into multi-dimensional images binned in space and time.…”

Section: Machine Learning Techniquesmentioning

confidence: 99%

Machine learning techniques deep underwater in km3net

Eberl¹

2022

Europhysics News

View full text Add to dashboard Cite

show abstract

Section: Machine Learning Techniquesmentioning

confidence: 99%

Machine learning techniques deep underwater in km3net

Eberl¹

2022

Europhysics News

View full text Add to dashboard Cite

show abstract

“…Applications utilizing CNNs include, but are not limited to, work detailed in refs. [14][15][16][17][18][19][20].…”

Section: Jinst 16 P07041 1 Potential Of Deep Learning-based Reconstru...mentioning

confidence: 99%

A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory

Abbasi¹,

Ackermann²,

Adams³

et al. 2021

J. Inst.

Self Cite

View full text Add to dashboard Cite

A: Continued improvements on existing reconstruction methods are vital to the success of high-energy physics experiments, such as the IceCube Neutrino Observatory. In IceCube, further challenges arise as the detector is situated at the geographic South Pole where computational resources are limited. However, to perform real-time analyses and to issue alerts to telescopes around the world, powerful and fast reconstruction methods are desired. Deep neural networks can be extremely powerful, and their usage is computationally inexpensive once the networks are trained. These characteristics make a deep learning-based approach an excellent candidate for the application in IceCube. A reconstruction method based on convolutional architectures and hexagonally shaped kernels is presented. The presented method is robust towards systematic uncertainties in the simulation and has been tested on experimental data. In comparison to standard reconstruction methods in IceCube, it can improve upon the reconstruction accuracy, while reducing the time necessary to run the reconstruction by two to three orders of magnitude.

show abstract

“…[201,202]), and in particular data reconstruction (see, e.g. [203][204][205]), due to the increasing use of large, high-resolution tracking calorimeters as neutrino detectors.…”

Section: B Neutrino Experimentsmentioning

confidence: 99%

Machine Learning in the Search for New Fundamental Physics

Karagiorgi¹,

Kasieczka²,

Kravitz³

et al. 2021

Preprint

View full text Add to dashboard Cite

Machine learning plays a crucial role in enhancing and accelerating the search for new fundamental physics. We review the state of machine learning methods and applications for new physics searches in the context of terrestrial high energy physics experiments, including the Large Hadron Collider, rare event searches, and neutrino experiments. While machine learning has a long history in these fields, the deep learning revolution (early 2010s) has yielded a qualitative shift in terms of the scope and ambition of research. These modern machine learning developments are the focus of the present review.

show abstract

Event reconstruction for KM3NeT/ORCA using convolutional neural networks

Cited by 24 publications

References 22 publications

Machine learning techniques deep underwater in km3net

Machine learning techniques deep underwater in km3net

A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory

Machine Learning in the Search for New Fundamental Physics

Contact Info

Product

Resources

About