Anomaly detection with flow-based fast calorimeter simulators

Krause, Claudius; Nachman, Benjamin; Pang, Ian; Shih, David; Zhu, Yunhao

doi:10.1103/physrevd.110.035036

Title: Anomaly detection with flow-based fast calorimeter simulators

Journal Article · 29 August 2024 · Physical Review. D.

DOI: https://doi.org/10.1103/physrevd.110.035036 · OSTI ID:2438516

^[1];

^[2];

^[3];

^[4]

Heidelberg Univ. (Germany); Austrian Academy of Sciences, Vienna (Austria). Institute of High Energy Physics (HEPHY)
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); University of California, Berkeley, CA (United States)
Rutgers Univ., Piscataway, NJ (United States)
Rutgers Univ., Piscataway, NJ (United States); Northeastern Univ., Boston, MA (United States)

Recently, several normalizing flow-based deep generative models have been proposed to accelerate the simulation of calorimeter showers. Using caloflow as an example, we show that these models can simultaneously perform unsupervised anomaly detection with no additional training cost. As a demonstration, we consider electromagnetic showers initiated by one (background) or multiple (signal) photons. The caloflow model is designed to generate single-photon showers, but it also provides access to the shower likelihood. We use this likelihood as an anomaly score and study the showers tagged as being unlikely. As expected, the tagger struggles when the signal photons are nearly collinear but is otherwise effective. This approach is complementary to a supervised classifier trained on only specific signal models using the same low-level calorimeter inputs. While the supervised classifier is also highly effective at unseen signal models, the unsupervised method is more sensitive in certain regions, and, thus, we expect that the ultimate performance will require a combination of these approaches.

View Journal Article

Cite

Export

Save

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC), High Energy Physics (HEP)

Grant/Contract Number:: AC02-05CH11231; SC0010008

OSTI ID:: 2438516

Journal Information:: Physical Review. D., Journal Name: Physical Review. D. Journal Issue: 3 Vol. 110; ISSN 2470-0010

Publisher:: American Physical Society (APS)Copyright Statement

Country of Publication:: United States

Language:: English

References (72)

A Family of Nonparametric Density Estimation Algorithms Tabak, E. G.; Turner, Cristina V. Communications on Pure and Applied Mathematics, Vol. 66, Issue 2 https://doi.org/10.1002/cpa.21423	journal	September 2012
Final state interactions in the (nuclear) FRITIOF string interaction scenario Andersson, B.; Tai, A.; Sa, Ben-Hao Zeitschrift f�r Physik C Particles and Fields, Vol. 70, Issue 3 https://doi.org/10.1007/s002880050127	journal	April 1996
Generating and Refining Particle Detector Simulations Using the Wasserstein Distance in Adversarial Networks Erdmann, Martin; Geiger, Lukas; Glombitza, Jonas Computing and Software for Big Science, Vol. 2, Issue 1 https://doi.org/10.1007/s41781-018-0008-x	journal	July 2018
Fast and Accurate Simulation of Particle Detectors Using Generative Adversarial Networks Musella, Pasquale; Pandolfi, Francesco Computing and Software for Big Science, Vol. 2, Issue 1 https://doi.org/10.1007/s41781-018-0015-y	journal	November 2018
Precise Simulation of Electromagnetic Calorimeter Showers Using a Wasserstein Generative Adversarial Network Erdmann, Martin; Glombitza, Jonas; Quast, Thorben Computing and Software for Big Science, Vol. 3, Issue 1 https://doi.org/10.1007/s41781-018-0019-7	journal	January 2019
AtlFast3: The Next Generation of Fast Simulation in ATLAS Aad, G.; Abbott, B.; Abbott, D. C. Computing and Software for Big Science, Vol. 6, Issue 1 https://doi.org/10.1007/s41781-021-00079-7	journal	March 2022
Deep Generative Models for Fast Photon Shower Simulation in ATLAS Computing and Software for Big Science, Vol. 8, Issue 1 https://doi.org/10.1007/s41781-023-00106-9	journal	March 2024
Interactions between hadrons and nuclei: The Lund Monte Carlo - FRITIOF version 1.6 - Nilsson-Almqvist, Bo; Stenlund, Evert Computer Physics Communications, Vol. 43, Issue 3 https://doi.org/10.1016/0010-4655(87)90056-7	journal	February 1987
Calculation of the capture of negative pions in light elements and comparison with experiments pertaining to cancer radiotherapy Guthrie, M. P.; Alsmiller, R. G.; Bertini, H. W. Nuclear Instruments and Methods, Vol. 66, Issue 1 https://doi.org/10.1016/0029-554X(68)90054-2	journal	December 1968
News item results from medium-energy intranuclear-cascade calculation Bertini, Hugo W.; Guthrie, Miriam P. Nuclear Physics A, Vol. 169, Issue 3 https://doi.org/10.1016/0375-9474(71)90710-X	journal	July 1971
Light-front wave function of a relativistic composite system in an explicitly solvable model Karmanov, V. A. Nuclear Physics B, Vol. 166, Issue 3 https://doi.org/10.1016/0550-3213(80)90204-7	journal	April 1980
A model for low-pT hadronic reactions with generalizations to hadron-nucleus and nucleus-nucleus collisions Andersson, B.; Gustafson, G.; Nilsson-Almqvist, B. Nuclear Physics B, Vol. 281, Issue 1-2 https://doi.org/10.1016/0550-3213(87)90257-4	journal	January 1987
Geant4—a simulation toolkit Agostinelli, S.; Allison, J.; Amako, K. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 506, Issue 3 https://doi.org/10.1016/S0168-9002(03)01368-8	journal	July 2003
Recent developments in Geant4 Allison, J.; Amako, K.; Apostolakis, J. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 835 https://doi.org/10.1016/j.nima.2016.06.125	journal	November 2016
Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC Aad, G.; Abajyan, T.; Abbott, B. Physics Letters B, Vol. 716, Issue 1 https://doi.org/10.1016/j.physletb.2012.08.020	journal	September 2012
Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC Chatrchyan, S.; Khachatryan, V.; Sirunyan, A. M. Physics Letters B, Vol. 716, Issue 1 https://doi.org/10.1016/j.physletb.2012.08.021	journal	September 2012
Author Correction: Ultra-high-granularity detector simulation with intra-event aware generative adversarial network and self-supervised relational reasoning Hashemi, Baran; Hartmann, Nikolai; Sharifzadeh, Sahand Nature Communications, Vol. 15, Issue 1 https://doi.org/10.1038/s41467-024-49971-x	journal	July 2024
3D convolutional GAN for fast simulation Vallecorsa, Sofia; Carminati, Federico; Khattak, Gulrukh EPJ Web of Conferences, Vol. 214 https://doi.org/10.1051/epjconf/201921402010	journal	January 2019
Generative Models for Fast Calorimeter Simulation: the LHCb case> Chekalina, Viktoria; Orlova, Elena; Ratnikov, Fedor EPJ Web of Conferences, Vol. 214 https://doi.org/10.1051/epjconf/201921402034	journal	January 2019
Generative models for fast cluster simulations in the TPC for the ALICE experiment Deja, Kamil; Trzcin´ski, Tomasz; Graczykowski, Łukasz EPJ Web of Conferences, Vol. 214 https://doi.org/10.1051/epjconf/201921406003	journal	January 2019
Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network Buhmann, Erik; Diefenbacher, Sascha; Eren, Engin EPJ Web of Conferences, Vol. 251 https://doi.org/10.1051/epjconf/202125103003	journal	January 2021
The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics Kasieczka, Gregor; Nachman, Benjamin; Shih, David Reports on Progress in Physics, Vol. 84, Issue 12 https://doi.org/10.1088/1361-6633/ac36b9	journal	December 2021
Generative models for fast simulation Vallecorsa, S. Journal of Physics: Conference Series, Vol. 1085 https://doi.org/10.1088/1742-6596/1085/2/022005	journal	September 2018
Three dimensional Generative Adversarial Networks for fast simulation Carminati, F.; Gheata, A.; Khattak, G. Journal of Physics: Conference Series, Vol. 1085 https://doi.org/10.1088/1742-6596/1085/3/032016	journal	September 2018
Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters de Oliveira, Luke; Paganini, Michela; Nachman, Benjamin Journal of Physics: Conference Series, Vol. 1085 https://doi.org/10.1088/1742-6596/1085/4/042017	journal	September 2018
Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks Ahdida, C.; Albanese, R.; Alexandrov, A. Journal of Instrumentation, Vol. 14, Issue 11 https://doi.org/10.1088/1748-0221/14/11/P11028	journal	November 2019
L2LFlows: generating high-fidelity 3D calorimeter images Diefenbacher, Sascha; Eren, Engin; Gaede, Frank Journal of Instrumentation, Vol. 18, Issue 10 https://doi.org/10.1088/1748-0221/18/10/P10017	journal	October 2023
Generalizing to new geometries with Geometry-Aware Autoregressive Models (GAAMs) for fast calorimeter simulation Liu, Junze; Ghosh, Aishik; Smith, Dylan Journal of Instrumentation, Vol. 18, Issue 11 https://doi.org/10.1088/1748-0221/18/11/P11003	journal	November 2023
CaloClouds: fast geometry-independent highly-granular calorimeter simulation Buhmann, Erik; Diefenbacher, Sascha; Eren, Engin Journal of Instrumentation, Vol. 18, Issue 11 https://doi.org/10.1088/1748-0221/18/11/P11025	journal	November 2023
CaloScore v2: single-shot calorimeter shower simulation with diffusion models Mikuni, Vinicius; Nachman, Benjamin Journal of Instrumentation, Vol. 19, Issue 02 https://doi.org/10.1088/1748-0221/19/02/P02001	journal	February 2024
Comparison of point cloud and image-based models for calorimeter fast simulation Torales Acosta, Fernando; Mikuni, Vinicius; Nachman, Benjamin Journal of Instrumentation, Vol. 19, Issue 05 https://doi.org/10.1088/1748-0221/19/05/P05003	journal	May 2024
`i- flow` : High-dimensional integration and sampling with normalizing flows Gao, Christina; Isaacson, Joshua; Krause, Claudius Machine Learning: Science and Technology, Vol. 1, Issue 4 https://doi.org/10.1088/2632-2153/abab62	journal	November 2020
Hadrons, better, faster, stronger Buhmann, Erik; Diefenbacher, Sascha; Hundhausen, Daniel Machine Learning: Science and Technology, Vol. 3, Issue 2 https://doi.org/10.1088/2632-2153/ac7848	journal	June 2022
New angles on fast calorimeter shower simulation Diefenbacher, Sascha; Eren, Engin; Gaede, Frank Machine Learning: Science and Technology, Vol. 4, Issue 3 https://doi.org/10.1088/2632-2153/acefa9	journal	September 2023
Searching for new physics with deep autoencoders Farina, Marco; Nakai, Yuichiro; Shih, David Physical Review D, Vol. 101, Issue 7 https://doi.org/10.1103/PhysRevD.101.075021	journal	April 2020
Anomaly detection with density estimation Nachman, Benjamin; Shih, David Physical Review D, Vol. 101, Issue 7 https://doi.org/10.1103/PhysRevD.101.075042	journal	April 2020
Event generation with normalizing flows Gao, Christina; Höche, Stefan; Isaacson, Joshua Physical Review D, Vol. 101, Issue 7 https://doi.org/10.1103/PhysRevD.101.076002	journal	April 2020
Novelty detection meets collider physics Hajer, Jan; Li, Ying-Ying; Liu, Tao Physical Review D, Vol. 101, Issue 7 https://doi.org/10.1103/PhysRevD.101.076015	journal	April 2020
Classifying anomalies through outer density estimation Hallin, Anna; Isaacson, Joshua; Kasieczka, Gregor Physical Review D, Vol. 106, Issue 5 https://doi.org/10.1103/PhysRevD.106.055006	journal	September 2022
Score-based generative models for calorimeter shower simulation Mikuni, Vinicius; Nachman, Benjamin Physical Review D, Vol. 106, Issue 9 https://doi.org/10.1103/PhysRevD.106.092009	journal	November 2022
Anomaly detection under coordinate transformations Kasieczka, Gregor; Mastandrea, Radha; Mikuni, Vinicius Physical Review D, Vol. 107, Issue 1 https://doi.org/10.1103/PhysRevD.107.015009	journal	January 2023
Fast and accurate simulations of calorimeter showers with normalizing flows Krause, Claudius; Shih, David Physical Review D, Vol. 107, Issue 11 https://doi.org/10.1103/PhysRevD.107.113003	journal	June 2023
Accelerating accurate simulations of calorimeter showers with normalizing flows and probability density distillation Krause, Claudius; Shih, David Physical Review D, Vol. 107, Issue 11 https://doi.org/10.1103/PhysRevD.107.113004	journal	June 2023
Resonant anomaly detection without background sculpting Hallin, Anna; Kasieczka, Gregor; Quadfasel, Tobias Physical Review D, Vol. 107, Issue 11 https://doi.org/10.1103/PhysRevD.107.114012	journal	June 2023
Fast and improved neutrino reconstruction in multineutrino final states with conditional normalizing flows Raine, John Andrew; Leigh, Matthew; Zoch, Knut Physical Review D, Vol. 109, Issue 1 https://doi.org/10.1103/PhysRevD.109.012005	journal	January 2024
Inductive simulation of calorimeter showers with normalizing flows Buckley, Matthew R.; Pang, Ian; Shih, David Physical Review D, Vol. 109, Issue 3 https://doi.org/10.1103/PhysRevD.109.033006	journal	February 2024
Calorimeter shower superresolution Pang, Ian; Shih, David; Raine, John Andrew Physical Review D, Vol. 109, Issue 9 https://doi.org/10.1103/PhysRevD.109.092009	journal	May 2024
CaloGAN: Simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks Paganini, Michela; de Oliveira, Luke; Nachman, Benjamin Physical Review D, Vol. 97, Issue 1 https://doi.org/10.1103/PhysRevD.97.014021	journal	January 2018
Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters Paganini, Michela; de Oliveira, Luke; Nachman, Benjamin Physical Review Letters, Vol. 120, Issue 4 https://doi.org/10.1103/PhysRevLett.120.042003	journal	January 2018
Geant4 standard electromagnetic package for HEP applications Burkhardt, H.; Grichine, V. M.; Gumplinger, P. IEEE Symposium Conference Record Nuclear Science 2004. https://doi.org/10.1109/NSSMIC.2004.1462617	conference	January 2004
Geant4 developments and applications Allison, J.; Amako, K.; Apostolakis, J. IEEE Transactions on Nuclear Science, Vol. 53, Issue 1 https://doi.org/10.1109/TNS.2006.869826	journal	February 2006
Calorimetry with deep learning: particle simulation and reconstruction for collider physics Belayneh, Dawit; Carminati, Federico; Farbin, Amir The European Physical Journal C, Vol. 80, Issue 7 https://doi.org/10.1140/epjc/s10052-020-8251-9	journal	July 2020
Inference of cosmic-ray source properties by conditional invertible neural networks Bister, Teresa; Erdmann, Martin; Köthe, Ullrich The European Physical Journal C, Vol. 82, Issue 2 https://doi.org/10.1140/epjc/s10052-022-10138-x	journal	February 2022
Phase space sampling and inference from weighted events with autoregressive flows Stienen, Bob; Verheyen, Rob SciPost Physics, Vol. 10, Issue 2 https://doi.org/10.21468/SciPostPhys.10.2.038	journal	January 2021
Measuring QCD Splittings with Invertible Networks Bieringer, Sebastian; Butter, Anja; Heimel, Theo SciPost Physics, Vol. 10, Issue 6 https://doi.org/10.21468/SciPostPhys.10.6.126	journal	June 2021
The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider Aarrestad, Thea; van Beekveld, Melissa; Bona, Marcella SciPost Physics, Vol. 12, Issue 1 https://doi.org/10.21468/SciPostPhys.12.1.043	journal	January 2022
Targeting multi-loop integrals with neural networks Winterhalder, Ramon; Magerya, Vitaly; Villa, Emilio SciPost Physics, Vol. 12, Issue 4 https://doi.org/10.21468/SciPostPhys.12.4.129	journal	April 2022
Understanding Event-Generation Networks via Uncertainties Bellagente, Marco; Haussmann, Manuel; Luchmann, Michel SciPost Physics, Vol. 13, Issue 1 https://doi.org/10.21468/SciPostPhys.13.1.003	journal	July 2022
Event Generation and Density Estimation with Surjective Normalizing Flows Verheyen, Rob SciPost Physics, Vol. 13, Issue 3 https://doi.org/10.21468/SciPostPhys.13.3.047	journal	September 2022
Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows Butter, Anja; Diefenbacher, Sascha; Kasieczka, Gregor SciPost Physics, Vol. 13, Issue 4 https://doi.org/10.21468/SciPostPhys.13.4.087	journal	October 2022
Generative networks for precision enthusiasts Butter, Anja; Heimel, Theo; Hummerich, Sander SciPost Physics, Vol. 14, Issue 4 https://doi.org/10.21468/SciPostPhys.14.4.078	journal	April 2023
$\nu$-flows: Conditional neutrino regression Leigh, Matthew; Raine, John Andrew; Zoch, Knut SciPost Physics, Vol. 14, Issue 6 https://doi.org/10.21468/SciPostPhys.14.6.159	journal	June 2023
Two invertible networks for the matrix element method Butter, Anja; Heimel, Theo; Martini, Till SciPost Physics, Vol. 15, Issue 3 https://doi.org/10.21468/SciPostPhys.15.3.094	journal	September 2023
MadNIS - Neural multi-channel importance sampling Heimel, Theo; Winterhalder, Ramon; Butter, Anja SciPost Physics, Vol. 15, Issue 4 https://doi.org/10.21468/SciPostPhys.15.4.141	journal	October 2023
High-dimensional and permutation invariant anomaly detection Mikuni, Vinicius; Nachman, Benjamin SciPost Physics, Vol. 16, Issue 3 https://doi.org/10.21468/SciPostPhys.16.3.062	journal	February 2024
CaloFlow for CaloChallenge dataset 1 Krause, Claudius; Pang, Ian; Shih, David SciPost Physics, Vol. 16, Issue 5 https://doi.org/10.21468/SciPostPhys.16.5.126	journal	May 2024
Returning CP-observables to the frames they belong Ackerschott, Jona; Barman, Rahool Kumar; Gonçalves, Dorival SciPost Physics, Vol. 17, Issue 1 https://doi.org/10.21468/SciPostPhys.17.1.001	journal	July 2024
QCD or what? Heimel, Theo; Kasieczka, Gregor; Plehn, Tilman SciPost Physics, Vol. 6, Issue 3 https://doi.org/10.21468/SciPostPhys.6.3.030	journal	January 2019
Exploring phase space with Neural Importance Sampling Bothmann, Enrico; Janßen, Timo; Knobbe, Max SciPost Physics, Vol. 8, Issue 4 https://doi.org/10.21468/SciPostPhys.8.4.069	journal	January 2020
Invertible networks or partons to detector and back again Bellagente, Marco; Butter, Anja; Kasieczka, Gregor SciPost Physics, Vol. 9, Issue 5 https://doi.org/10.21468/SciPostPhys.9.5.074	journal	January 2020
An unfolding method based on conditional invertible neural networks (cINN) using iterative training Backes, Mathias; Butter, Anja; Dunford, Monica SciPost Physics Core, Vol. 7, Issue 1 https://doi.org/10.21468/SciPostPhysCore.7.1.007	journal	February 2024
Perfect Density Models Cannot Guarantee Anomaly Detection Le Lan, Charline; Dinh, Laurent Entropy, Vol. 23, Issue 12 https://doi.org/10.3390/e23121690	journal	December 2021

Similar Records

Fast and accurate simulations of calorimeter showers with normalizing flows

Journal Article · 2023 · Physical Review. D. · OSTI ID:2419968

Krause, Claudius; Shih, David

CaloFlow for CaloChallenge dataset 1

Journal Article · 2024 · SciPost Physics · OSTI ID:2350862

Krause, Claudius; Pang, Ian; Shih, David

Accelerating accurate simulations of calorimeter showers with normalizing flows and probability density distillation

Journal Article · 2023 · Physical Review. D. · OSTI ID:2419969

Krause, Claudius; Shih, David

Related Subjects

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
artificial neural networks
electromagnetic calorimeters
hadronic decays
hypothetical particle physics models
hypothetical particles
machine learning
particle phenomena

Title: Anomaly detection with flow-based fast calorimeter simulators

Citation Formats

References (72)

Similar Records

Related Subjects