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

• Published in: Journal of Instrumentation
• Main Authors: Abbasi, R., Ackermann, M., Adams, J., Aguilar, J. A., Ahlers, M., Ahrens, M., Alispach, C., Alves, A. A., Jr., Amin, N. M., An, R., Andeen, K., Anderson, T., Ansseau, I, Anton, G., Arguelles, C., Axani, S., Bai, X., Balagopal V, A., Barbano, A., Barwick, S. W., Bastian, B., Basu, V, Baum, V, Baur, S., Bay, R., Beatty, J. J., Becker, K-H, Tjus, J. Becker, Bellenghi, C., BenZvi, S., Berley, D., Bernardini, E., Besson, D. Z., Binder, G., Bindig, D., Blaufuss, E., Blot, S., Boeser, S., Botner, O., Boettcher, J., Bourbeau, E., Bourbeau, J., Bradascio, F., Braun, J., Bron, S., Brostean-Kaiser, J., Burgman, A., Busse, R. S., Campana, M. A., Chen, C., Chirkin, D., Choi, S., Clark, B. A., Clark, K., Classen, L., Coleman, A., Collin, G. H., Conrad, J. M., Coppin, P., Correa, P., Cowen, D. F., Cross, R., Dave, P., Clercq, C. D., DeLaunay, J. J., Dembinski, H., Deoskar, K., De Ridder, Sam, Desai, A., Desiati, P., de Vries, K. D., de Wasseige, G., de With, M., DeYoung, T., Dharani, S., Diaz, A., Diaz-Velez, J. C., Dujmovic, H., Dunkman, M., DuVernois, M. A., Dvorak, E., Ehrhardt, T., Eller, P., Engel, R., Evans, J., Evenson, P. A., Fahey, S., Fazely, A. R., Fiedlschuster, S., Fienberg, A. T., Filimonov, K., Finley, C., Fischer, L., Fox, D., Franckowiak, A., Friedman, E., Fritz, A., Fuerst, P., Gaisser, T. K., Gallagher, J., Ganster, E., Garrappa, S., Gerhardt, L., Ghadimi, A., Glaser, C., Glauch, T., Gluesenkamp, T., Goldschmidt, A., Gonzalez, J. G., Goswami, S., Grant, D., Gregoire, T., Griffith, Z., Griswold, S., Gunduz, M., Haack, C., Hallgren, A., Halliday, R., Halve, L., Halzen, F., Minh, M. H., Hanson, K., Hardin, J., Harnisch, A. A., Haungs, A., Hauser, S., Hebecker, D., Helbing, K., Henningsen, F., Hettinger, E. C., Hickford, S., Hignight, J., Hill, C., Hill, G. C., Hoffman, K. D., Hoffmann, R., Hoinka, T., Hokanson-Fasig, B., Hoshina, K., Huang, F., Huber, M., Huber, T., Hultqvist, K., Hunnefeld, M., Hussain, R., In, S., Iovine, N., Ishihara, A., Jansson, M., Japaridze, G. S., Jeong, M., Jones, B. J. P., Joppe, R., Kang, D., Kang, W., Kang, X., Kappes, A., Kappesser, D., Karg, T., Karl, M., Karle, A., Katz, U., Kauer, M., Kellermann, M., Kelley, J. L., Kheirandish, A., Kim, J., Kin, K., Kintscher, T., Kiryluk, J., Klein, S. R., Koirala, R., Kolanoski, H., Koepke, L., Kopper, C., Kopper, S., Koskinen, D. J., Koundal, P., Kovacevich, M., Kowalski, M., Krings, K., Kruckl, G., Kurahashi, N., Kyriacou, A., Gualda, C. Lagunas, Lanfranchi, J. L., Larson, M. J., Lauber, F., Lazar, J. P., Leonard, K., Leszczynska, A., Li, Y., Liu, Q. R., Lohfink, E., Mariscal, C. J. Lozano, Lu, L., Lucarelli, F., Ludwig, A., Luszczak, W., Lyu, Y., Ma, W. Y., Madsen, J., Mahn, K. B. M., Makino, Y., Mallik, P., Mancina, S., Maris, I. C., Maruyama, R., Mase, K., McNally, F., Meagher, K., Medina, A., Meier, M., Meighen-Berger, S., Merz, J., Micallef, J., Mockler, D., Momente, G., Montaruli, T., Moore, R. W., Morik, K., Morse, R., Moulai, M., Naab, R., Nagai, R., Naumann, U., Necker, J., Niederhausen, H., Nisa, M. U., Nowicki, S. C., Nygren, D. R., Pollmann, A. Obertacke, Oehler, M., Olivas, A., Pandya, H., Pankova, D., V, Park, N., Parker, G. K., Paudel, E. N., Peiffer, P., de los Heros, C. Perez, Philippen, S., Pieloth, D., Pieper, S., Pizzuto, A., Plum, M., Popovych, Y., Porcelli, Alessio, Rodriguez, M. Prado, Price, P. B., Pries, B., Przybylski, G. T., Raab, C., Raissi, A., Rameez, M., Rawlins, K., Rea, I. C., Rehman, A., Reimann, R., Renschler, M., Renzi, G., Resconi, E., Reusch, S., Rhode, W., Richman, M., Riedel, B., Robertson, S., Roellinghoff, G., Rongen, M., Rott, C., Ruhe, T., Ryckbosch, Dirk, Cantu, D. Rysewyk, Safa, I, Herrera, S. E. Sanchez, Sandrock, A., Sandroos, J., Santander, M., Sarkar, S., Satalecka, K., Scharf, M., Schaufel, M., Schieler, H., Schlunder, P., Schmidt, T., Schneider, A., Schneider, J., Schroeder, F. G., Schumacher, L., Sclafani, S., Seckel, D., Seunarine, S., Sharma, A., Shefali, S., Silva, M., Skrzypek, B., Smithers, B., Snihur, R., Soedingrekso, J., Soldin, D., Spiczak, G. M., Spiering, C., Stachurska, J., Stamatikos, M., Stanev, T., Stein, R., Stettner, J., Steuer, A., Stezelberger, T., Stokstad, R. G., Sturwald, T., Stuttard, T., Sullivan, G. W., Taboada, I, Tenholt, F., Ter-Antonyan, S., Tilav, S., Tischbein, F., Tollefson, K., Tomankova, L., Tonnis, C., Toscano, S., Tosi, D., Trettin, A., Tselengidou, M., Tung, C. F., Turcati, A., Turcotte, R., Turley, C. F., Twagirayezu, J. P., Ty, B., Elorrieta, M. A. Unland, Valtonen-Mattila, N., Vandenbroucke, J., van Eijk, D., van Eijndhoven, N., Vannerom, D., van Santen, J., Verpoest, Stef, Vraeghe, Matthias, Walck, C., Wallace, A., Watson, T. B., Weaver, C., Weindl, A., Weiss, M. J., Weldert, J., Wendt, C., Werthebach, J., Weyrauch, M., Whelan, B. J., Whitehorn, N., Wiebe, K., Wiebusch, C. H., Williams, D. R., Wolf, M., Woschnagg, K., Wrede, G., Wulff, J., Xu, X. W., Xu, Y., Yanez, J. P., Yoshida, S., Yuan, T., Zhang, Z.
• Format: Article in Journal/Newspaper
• Language: English
• Published: 2021
• Subjects: Physics and Astronomy; Data analysis; Neutrino detectors; Pattern recognition; cluster finding; calibration and fitting methods; South Pole; South pole
• Online Access: https://biblio.ugent.be/publication/8757284; http://hdl.handle.net/1854/LU-8757284; https://doi.org/10.1088/1748-0221/16/07/P07041; https://biblio.ugent.be/publication/8757284/file/8757286

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.