MétaCan
Menu
Back to cohort

Graph Neural Networks for low-energy event classification & reconstruction in IceCube

2022· article· en· W4308197356 on OpenAlexafffund
M. Ackermann, J. Adams, N. Aggarwal, J. A. Aguilar, M. Ahlers, M. Ahrens, Jean-Marco Alameddine, A. A. Alves, N.M. Amin, K. Andeen, T. Anderson, G. Anton, C. Argüelles, Y. Ashida, S. Athanasiadou, Spencer Axani, X. Bai, Aswathi Balagopal, M. Baricevic, S. W. Barwick, Vedant Basu, R. Bay, J. J. Beatty, K. Becker, J. Becker Tjus, J. Beise, C. Bellenghi, S. Benda, S. BenZvi, D. Berley, E. Bernardini, D. Z. Besson, G. Binder, D. Bindig, E. Blaufuss, Summer Blot, F. Bontempo, Julia Book, J. Borowka, Caterina Boscolo Meneguolo, S. Böser, O. Botner, J. Böttcher, E. Bourbeau, J. Braun, Bennett Brinson, J. Brostean-Kaiser, R.T. Burley, R.S. Busse, Michael Campana, E.G. Carnie-Bronca, C. Chen, Z. Chen, D. Chirkin, K. Choi, B.A. Clark, L. Classen, A. Coleman, G. H. Collin, A. Connolly, J. M. Conrad, Paul Coppin, Pablo Correa, S. Countryman, D. F. Cowen, R. Cross, Christian Dappen, Pranav Dave, C. De Clercq, J.J. DeLaunay, H.-P. Dembinski, Kunal Deoskar, Amruta Desai, P. Desiati, K. D. de Vries, G. de Wasseige, T. DeYoung, Alejandro Diaz, J. C. Díaz–Vélez, Markus Dittmer, H. Dujmovic, M. A. DuVernois, T. Ehrhardt, P. Eller, R. Engel, H. Erpenbeck, John Evans, P. A. Evenson, Kwok Lung Fan, A. R. Fazely, A. Fedynitch, Nora Feigl, S. Fiedlschuster, A. T. Fienberg, C. Finley, L. Fischer, D. B. Fox, A. Franckowiak, E. Friedman, A. Fritz, Philipp Fürst, T. K. Gaisser, J. Gallagher, Erik Ganster, Alfonso Garcia, S. Garrappa, L. Gerhardt, A. Ghadimi, C. Glaser, T. Glauch, T. Glüsenkamp, N. Goehlke, J.G. Gonzalez, Sreetama Goswami, D. Grant, S. J. Gray, T. Grégoire, S. Griswold, C. Günther, Pascal Gutjahr, Christian Haack, A. Hallgren, R. Halliday, L. Halve, F. Halzen, H. Hamdaoui, M. Ha Minh, K. Hanson, J. Hardin, A.A. Harnisch, P. Hatch, A. Haungs, K. Helbing, Jonas Hellrung, F. Henningsen, Lars Philipp Heuermann, S. Hickford, Colton Hill, G. C. Hill, K.D. Hoffman, K. Hoshina, Wenjie Hou, Thomas Huber, K. Hultqvist, M. Hünnefeld, R. Hussain, Karolin Hymon, S. In, N. Iovine, A. Ishihara, M. Jansson, G. S. Japaridze, Minjin Jeong, Miaochen Jin, B. J. P. Jones, Woosik Kang, X. Kang, A. Kappes, D. Kappesser, Leonora Kardum, T. Karg, M. Karl, A. Karle, U. Katz, M. Kauer, J. L. Kelley, A. Kheirandish, K. Kin, J. Kiryluk, A. Kochocki, Ramesh Koirala, H. Kolanoski, T. Kontrimas, L. Köpke, C. Kopper, D. J. Koskinen, Paras Koundal, M. Kovacevich, M. Kowalski, T. Kozynets, E. Krupczak, E. Kun, N. Kurahashi, Neha Navnitkumar Lad, Cristina Lagunas Gualda, M.J. Larson, Frederik Hermann Lauber, Jeffrey Lazar, J.W. Lee, A. Leszczyńska, M. Lincetto, Qinrui Liu, M. Liubarska, Elisa Lohfink, Christina Love, L. Lu, Francesco Lucarelli, A. Ludwig, W. Luszczak, W. Y., J. Madsen, K. B. M. Mahn, Y. Makino, Sarah Mancina, W. Marie Sainte, Ioana Codrina Mariş, Szabolcs Márka, Z. Márka, M. Marsee, I. Martinez-Soler, R. Maruyama, T. McElroy, F. McNally, J. V. Mead, K. Meagher, S. Mechbal, A. Medina, Maximilian Meier, S. Meighen-Berger, Yarno Merckx, J. Micallef, D. Mockler, T. Montaruli, R. W. Moore, R. Morse, Marjon Moulai, Tista Mukherjee, Richard Naab, R. Nagai, U. Naumann, A. Nayerhoda, J. Necker, M. Neumann, H. Niederhausen, M. U. Nisa, S.C. Nowicki, A. Obertacke Pollmann, M. Oehler, Bob Oeyen, A. Olivas, R. Orsoe, J. Osborn, Erin O’Sullivan, Hershal Pandya, D. V. Pankova, N. Park, G.K. Parker, E.N. Paudel, L. Paul, C. Pérez de los Heros, L. Peters, T. C. Petersen, J. Peterson, S. Philippen, S. Pieper, A. Pizzuto, M. Plum, Y. Popovych, A. Porcelli, M. Prado Rodriguez, B. Pries, R. Procter-Murphy, G. T. Przybylski, Christoph Raab, J. Rack-Helleis, M. Rameez, K. Rawlins, Z. Rechav, Abdul Rehman, Patrick Reichherzer, Giovanni Renzi, E. Resconi, S. Reusch, W. Rhode, M. Richman, B. Riedel, E.J. Roberts, S. Robertson, S. Rodan, Gerrit Roellinghoff, Martin Rongen, C. Rott, T. Ruhe, L. Ruohan, D. Ryckbosch, Devyn Rysewyk Cantu, I. Safa, J. Saffer, D. Salazar-Gallegos, P. Sampathkumar, S. E. Sanchez Herrera, Alexander Sandrock, M. Santander, S. Sarkar, M. Schaufel, H. Schieler, S. Schindler, B. Schlueter, T. Schmidt, J. Schneider, Frank Schröder, L. Schumacher, Georg Schwefer, S. Sclafani, D. Seckel, S. Seunarine, Ankur Sharma, S. Shefali, N. Shimizu, M. Silva, B. Skrzypek, B. Smithers, R. Snihur, J. Soedingrekso, A. Søgaard, D. Soldin, Christian Spannfellner, G. M. Spiczak, C. Spiering, M. Stamatikos, T. Stanev, Robert Stein, T. Stezelberger, T. Stürwald, Thomas Stuttard, G. W. Sullivan, I. Taboada, S. Ter–Antonyan, W. G. Thompson, Jessie Thwaites, S. Tilav, K. Tollefson, C. Tönnis, S. Toscano, D. Tosi, A. Trettin, C. F. Tung, R. Turcotte, Jean Pierre Twagirayezu, B. Ty, Martin Unland Elorrieta, K. Upshaw, N. Valtonen-Mattila, J. Vandenbroucke, N. van Eijndhoven, D. Vannerom, J. van Santen, J. Vara, J. Veitch-Michaelis, S. Verpoest, Doğa Veske, C. Walck, W. Wang, T.B. Watson, Chris Weaver, P. Weigel, A. Weindl, J. Weldert, Chris Wendt, J. Werthebach, M. Weyrauch, N. Whitehorn, C. H. Wiebusch, N. Willey, D. R. Williams, Martin Wolf, G. Wrede, Johan Wilfried Wulff, Xiaolin Xu, E. Yildizci, S. Yoshida, Shiqi Yu, Tony Yuan, Z. Zhang, P. Zhelnin

Bibliographic record

VenueJournal of Instrumentation · 2022
Typearticle
Languageen
FieldPhysics and Astronomy
TopicAstrophysics and Cosmic Phenomena
Canadian institutionsQueen's UniversityInstitute of Particle PhysicsUniversity of Alberta
FundersOffice of Experimental Program to Stimulate Competitive ResearchJapan Society for the Promotion of ScienceDeutsches Elektronen-SynchrotronOffice of Polar ProgramsCollege of Engineering, Michigan State UniversityHelmholtz Alliance for Astroparticle PhysicsInstitute for Global Prominent Research, Chiba UniversityRWTH Aachen UniversityChiba UniversityKnut och Alice Wallenbergs StiftelseVillum FondenNational Research Foundation of KoreaFonds Wetenschappelijk OnderzoekMarsden FundBundesministerium für Bildung und ForschungSchweizerischer Nationalfonds zur Förderung der Wissenschaftlichen ForschungNational Science FoundationBelgian Federal Science Policy OfficeDeutsche ForschungsgemeinschaftMichigan State UniversityNational Research FoundationVetenskapsrådetU.S. Department of EnergyEuropean CommissionWestern Canada Research GridUniversity of OxfordCompute CanadaMarquette UniversityFonds De La Recherche Scientifique - FNRSPolarforskningssekretariatet
KeywordsPhysicsNeutrinoEvent reconstructionEvent (particle physics)DetectorCOSMIC cancer databasePoint cloudAstrophysicsParticle physicsComputer scienceArtificial intelligenceOptics

Abstract

fetched live from OpenAlex

Abstract IceCube, a cubic-kilometer array of optical sensors built to detect atmospheric and astrophysical neutrinos between 1 GeV and 1 PeV, is deployed 1.45 km to 2.45 km below the surface of the ice sheet at the South Pole. The classification and reconstruction of events from the in-ice detectors play a central role in the analysis of data from IceCube. Reconstructing and classifying events is a challenge due to the irregular detector geometry, inhomogeneous scattering and absorption of light in the ice and, below 100 GeV, the relatively low number of signal photons produced per event. To address this challenge, it is possible to represent IceCube events as point cloud graphs and use a Graph Neural Network (GNN) as the classification and reconstruction method. The GNN is capable of distinguishing neutrino events from cosmic-ray backgrounds, classifying different neutrino event types, and reconstructing the deposited energy, direction and interaction vertex. Based on simulation, we provide a comparison in the 1 GeV–100 GeV energy range to the current state-of-the-art maximum likelihood techniques used in current IceCube analyses, including the effects of known systematic uncertainties. For neutrino event classification, the GNN increases the signal efficiency by 18% at a fixed background rate, compared to current IceCube methods. Alternatively, the GNN offers a reduction of the background (i.e. false positive) rate by over a factor 8 (to below half a percent) at a fixed signal efficiency. For the reconstruction of energy, direction, and interaction vertex, the resolution improves by an average of 13%–20% compared to current maximum likelihood techniques in the energy range of 1 GeV–30 GeV. The GNN, when run on a GPU, is capable of processing IceCube events at a rate nearly double of the median IceCube trigger rate of 2.7 kHz, which opens the possibility of using low energy neutrinos in online searches for transient events.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.027
Threshold uncertainty score0.054

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.244
Teacher spread0.231 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations38
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueJournal of InstrumentationSame topicAstrophysics and Cosmic PhenomenaFrench-language works237,207