Identification and denoising of radio signals from cosmic-ray air showers using convolutional neural networks

Abbasi, R.; Ackermann, M.; Adams, J.; Agarwalla, S.; Aguilar, J.; Ahlers, M.; Alameddine, J.; Ali, S.; Amin, N.; Andeen, K.; Arguelles, C.; Ashida, Y.; Athanasiadou, S.; Axani, S.; Babu, R.; Bai, X.; Baines-Holmes, J.; Balagopal, A.; Barwick, S.; Bash, S.; Basu, V.; Bay, R.; Beatty, J.; Tjus, J.; Behrens, P.; Beise, J.; Bellenghi, C.; Benkel, S.; BenZvi, S.; Berley, D.; Bernardini, E.; Besson, D.; Blaufuss, E.; Bloom, L.; Blot, S.; Bodo, I.; Bontempo, F.; Motzkin, J.; Meneguolo, C.; Boser, S.; Botner, O.; Bottcher, J.; Braun, J.; Brinson, B.; Brisson-Tsavoussis, Z.; Burley, R.; Butterfield, D.; Campana, M.; Carloni, K.; Carpio, J.; Chattopadhyay, S.; Chau, N.; Chen, Z.; Chirkin, D.; Choi, S.; Clark, B.; Coleman, P.; Collin, G.; Borja, D.; Connolly, A.; Conrad, J.; Corley, R.; Cowen, D.; De Clercq, C.; DeLaunay, J.; Delgado, D.; Delmeulle, T.; Deng, S.; Desiati, P.; de Vries, K.; de Wasseige, G.; DeYoung, T.; Diaz-Velez, J.; DiKerby, S.; Dittmer, M.; Domi, A.; Draper, L.; Dueser, L.; Durnford, D.; Dutta, K.; DuVernois, M.; Ehrhardt, T.; Eidenschink, L.; Eimer, A.; Eller, P.; Ellinger, E.; Elsaesser, D.; Engel, R.; Erpenbeck, H.; Esmail, W.; Eulig, S.; Evans, J.; Evenson, P.; Fan, K.; Fang, K.; Farrag, K.; Fazely, A.; Fedynitch, A.; Feigl, N.; Finley, C.; Fischer, L.; Fox, D.; Franckowiak, A.; Fukami, S.; Furst, P.; Gallagher, J.; Molina, P.; Ganster, E.; Garcia, A.; Garcia, M.; Garg, G.; Genton, E.; Gerhardt, L.; Ghadimi, A.; Glaser, C.; Glusenkamp, T.; Gonzalez, J.; Goswami, S.; Granados, A.; Grant, D.; Gray, S.; Griffin, S.; Griswold, S.; Groth, K.; Guevel, D.; Guenther, C.; Gutjahr, P.; Ha, C.; Haack, C.; Hallgren, A.; Halve, L.; Halzen, F.; Hamacher, L.; Minh, M.; Handt, M.; Hanson, K.; Hardin, J.; Harnisch, A.; Hatch, P.; Haungs, A.; Haeussler, J.; Helbing, K.; Hellrung, J.; Henke, B.; Hennig, L.; Henningsen, F.; Heuermann, L.; Hewett, R.; Heyer, N.; Hickford, S.; Hidvegi, A.; Hill, C.; Hill, G.; Hmaid, R.; Hoffman, K.; Hooper, D.; Hori, S.; Hoshina, K.; Hostert, M.; Hou, W.; Hrywniak, M.; Huber, T.; Hultqvist, K.; Hymon, K.; Ishihara, A.; Iwakiri, W.; Jacquart, M.; Jain, S.; Janik, O.; Jansson, M.; Jeong, M.; Jin, M.; Kamp, N.; Kang, D.; Kang, W.; Kang, X.; Kappes, A.; Kardum, L.; Karg, T.; Karl, M.; Karle, A.; Katil, A.; Kauer, M.; Kelley, J.; Khanal, M.; Zathul, A.; Kheirandish, A.; Kimku, H.; Kiryluk, J.; Klein, C.; Klein, S.; Kobayashi, Y.; Kochocki, A.; Koirala, R.; Kolanoski, H.; Kontrimas, T.; Kopke, L.; Kopper, C.; Koskinen, D.; Koundal, P.; Kowalski, M.; Kozynets, T.; Kravka, A.; Krishnamoorthi, J.; Krishnan, T.; Kruiswijk, K.; Krupczak, E.; Kullgren, D.; Kumar, A.; Kun, E.; Kurahashi, N.; Lad, N.; Gualda, C.; Arnaud, L.; Lamoureux, M.; Larson, M.; Lauber, F.; Lazar, J.; DeHolton, K.; Leszczynska, A.; Liao, J.; Lin, C.; Liu, Y.; Liubarska, M.; Love, C.; Lu, L.; Lucarelli, F.; Luszczak, W.; Lyu, Y.; Madsen, J.; Magnus, E.; Makino, Y.; Manao, E.; Mancina, S.; Mand, A.; Maris, I.; Marka, S.; Marka, Z.; Marten, L.; Martinez-Soler, I.; Maruyama, R.; Mauro, J.; Mayhew, F.; McNally, F.; Mead, J.; Meagher, K.; Mechbal, S.; Medina, A.; Meier, M.; Merckx, Y.; Merten, L.; Mitchell, J.; Molchany, L.; Montaruli, T.; Moore, R.; Morii, Y.; Mosbrugger, A.; Moulai, M.; Mousadi, D.; Moyaux, E.; Mukherjee, T.; Naab, R.; Nakos, M.; Naumann, U.; Necker, J.; Neste, L.; Neumann, M.; Niederhausen, H.; Nisa, M.; Noda, K.; Noell, A.; Novikov, A.; Obertacke, A.; O'Dell, V.; Olivas, A.; Orsoe, R.; Osborn, J.; O'Sullivan, E.; Palusova, V.; Pandya, H.; Parenti, A.; Park, N.; Parrish, V.; Paudel, E.; Paul, L.; de los Heros, C.; Pernice, T.; Peterson, J.; Plum, M.; Ponten, A.; Poojyam, V.; Popovych, Y.; Rodriguez, M.; Pries, B.; Procter-Murphy, R.; Przybylski, G.; Pyras, L.; Raab, C.; Rack-Helleis, J.; Rad, N.; Ravn, M.; Rawlins, K.; Rechav, Z.; Rehman, A.; Reistroffer, I.; Resconi, E.; Reusch, S.; Rho, C.; Rhode, W.; Ricca, L.; Riedel, B.; Rifaie, A.; Roberts, E.; Rongen, M.; Rosted, A.; Rott, C.; Ruhe, T.; Ruohan, L.; Ryckbosch, D.; Saffer, J.; Salazar-Gallegos, D.; Sampathkumar, P.; Sandrock, A.; Sanger-Johnson, G.; Santander, M.; Sarkar, S.; Savelberg, J.; Scarnera, M.; Schaile, P.; Schaufel, M.; Schieler, H.; Schindler, S.; Schlickmann, L.; Schluter, B.; Schluter, F.; Schmeisser, N.; Schmidt, T.; Schroder, F.; Schumacher, L.; Schwirn, S.; Sclafani, S.; Seckel, D.; Seen, L.; Seikh, M.; Seunarine, S.; Myhr, P.; Shah, R.; Shefali, S.; Shimizu, N.; Skrzypek, B.; Snihur, R.; Soedingrekso, J.; Sogaard, A.; Soldin, D.; Soldin, P.; Sommani, G.; Spannfellner, C.; Spiczak, G.; Spiering, C.; Stachurska, J.; Stamatikos, M.; Stanev, T.; Stezelberger, T.; Sturwald, T.; Stuttard, T.; Sullivan, G.; Taboada, I.; Ter-Antonyan, S.; Terliuk, A.; Thakuri, A.; Thiesmeyer, M.; Thompson, W.; Thwaites, J.; Tilav, S.; Tollefson, K.; Toscano, S.; Tosi, D.; Trettin, A.; Upadhyay, A.; Upshaw, K.; Vaidyanathan, A.; Valtonen-Mattila, N.; Valverde, J.; Vandenbrouck, J.; Van Eeden, T.; van Eijndhoven, N.; Van Rootselaar, L.; van Santen, J.; Vara, J.; Varsi, F.; Venugopal, M.; Vereecken, M.; Carrasco, S.; Verpoest, S.; Veske, DOĞA; Vijai, A.; Villarreal, J.; Walck, C.; Wang, A.; Warrick, E.; Weaver, C.; Weigel, P.; Weindl, A.; Weldert, J.; Wen, A.; Wendt, C.; Werthebach, J.; Weyrauch, M.; Whitehorn, N.; Wiebusch, C.; Williams, D.; Witthaus, L.; Wolf, M.; Wrede, G.; Xu, X.; Yanez, J.; Yao, Y.; Yildizci, E.; Yoshida, S.; Young, R.; Yu, F.; Yu, S.; Yuan, T.; Zegarelli, A.; Zhang, S.; Zhang, Z.; Zhelnin, P.; Zilberman, P.

doi:10.1103/xw99-zq7j

Identification and denoising of radio signals from cosmic-ray air showers using convolutional neural networks

Abbasi R., Ackermann M., Adams J., Agarwalla S. K., Aguilar J. A., Ahlers M., ...Daha Fazla

PHYSICAL REVIEW D, cilt.113, sa.12, 2026 (SCI-Expanded, Scopus)

Yayın Türü: Makale / Tam Makale
Cilt numarası: 113 Sayı: 12
Basım Tarihi: 2026
Doi Numarası: 10.1103/xw99-zq7j
Dergi Adı: PHYSICAL REVIEW D
Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Chemical Abstracts Core, INSPEC, MathSciNet, zbMATH
Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

Radio pulses generated by cosmic-ray air showers can be used to reconstruct key properties like the energy and depth of the electromagnetic component of cosmic-ray air showers. Radio detection threshold, influenced by natural and anthropogenic radio background, can be reduced through various techniques. In this work, we demonstrate that convolutional neural networks (CNNs) are an effective way to lower the threshold. We developed two CNNs: a classifier to distinguish radio signal waveforms frombackground noise and a denoiser to clean contaminated radio signals. Following the training and testing phases, we applied the networks to airshower data triggered by scintillation detectors of the prototype station for the enhancement of IceTop, IceCube's surface array at the South Pole. Over a four-month period, we identified 554 cosmic-ray events in coincidencewith IceTop, approximately five times more compared to a reference method based on a cut on the signal-to-noise ratio. Comparisons with IceTop measurements of the same air showers confirmed that the CNNs reliably identified cosmic-ray radio pulses and outperformed the referencemethod. Additionally, wefind that CNNs reduce the false-positive rate of air-shower candidates and effectively denoise radio waveforms, thereby improving the accuracy of the power and arrival time reconstruction of radio pulses.