Search for new phenomena in two-body invariant mass distributions using unsupervised machine learning for anomaly detection at √s = 13 TeV with the ATLAS detector

ATLAS Collaboration

doi:10.1103/PhysRevLett.132.081801

Search for new phenomena in two-body invariant mass distributions using unsupervised machine learning for anomaly detection at √s = 13 TeV with the ATLAS detector

ATLAS Collaboration

Physics and Astronomy

Research output: Contribution to journal › Letter › peer-review

13 Downloads (Pure)

Abstract

Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb⁻¹ of pp collisions at √s = 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b-jet and either one lepton (e, μ), photon, or second light jet or b-jet in the anomalous regions. No significant deviations from the background hypotheses are observed.

Original language	English
Article number	081801
Number of pages	23
Journal	Physical Review Letters
Volume	132
Issue number	8
Early online date	20 Feb 2024
DOIs	https://doi.org/10.1103/PhysRevLett.132.081801
Publication status	Published - 23 Feb 2024

Bibliographical note

Acknowledgments:
We thank CERN for the very successful operation of the LHC, as well as the support staff from our institutions without whom ATLAS could not be operated efficiently. We acknowledge the support of ANPCyT, Argentina; YerPhI, Armenia; ARC, Australia; BMWFW and FWF, Austria; ANAS, Azerbaijan; CNPq and FAPESP, Brazil; NSERC, NRC and CFI, Canada; CERN; ANID, Chile; CAS, MOST and NSFC, China; Minciencias, Colombia; MEYS CR, Czech Republic; DNRF and DNSRC, Denmark; IN2P3-CNRS and CEA-DRF/IRFU, France; SRNSFG, Georgia; BMBF, HGF and MPG, Germany; GSRI, Greece; RGC and Hong Kong SAR, China; ISF and Benoziyo Center, Israel; INFN, Italy; MEXT and JSPS, Japan; CNRST, Morocco; NWO, Netherlands; RCN, Norway; MEiN, Poland; FCT, Portugal; MNE/IFA, Romania; MESTD, Serbia; MSSR, Slovakia; ARRS and MIZŠ, Slovenia; DSI/NRF, South Africa; MICINN, Spain; SRC and Wallenberg Foundation, Sweden; SERI, SNSF and Cantons of Bern and Geneva, Switzerland; MOST, Taiwan; TENMAK, Türkiye; STFC, United Kingdom; DOE and NSF, USA. In addition, individual groups and members have received support from BCKDF, CANARIE, Compute Canada and CRC, Canada; PRIMUS 21/SCI/017 and UNCE SCI/013, Czech Republic; COST, ERC, ERDF, Horizon 2020, ICSC-NextGenerationEU and Marie Skłodowska-Curie Actions, European Union; Investissements d’Avenir Labex, Investissements d’Avenir Idex and ANR, France; DFG and AvH Foundation, Germany; Herakleitos, Thales and Aristeia programmes co-financed by EU-ESF and the Greek NSRF, Greece; BSF-NSF and MINERVA, Israel; Norwegian Financial Mechanism 2014-2021, Norway; NCN and NAWA, Poland; La Caixa Banking Foundation, CERCA Programme Generalitat de Catalunya and PROMETEO and GenT Programmes Generalitat Valenciana, Spain; Göran Gustafssons Stiftelse, Sweden; The Royal Society and Leverhulme Trust, United Kingdom. The crucial computing support from all WLCG partners is acknowledged gratefully, in particular from CERN, the ATLAS Tier-1 facilities at TRIUMF (Canada), NDGF (Denmark, Norway, Sweden), CC-IN2P3 (France), KIT/GridKA (Germany), INFN-CNAF (Italy), NL-T1 (Netherlands), PIC (Spain), ASGC (Taiwan), RAL (UK) and BNL (USA), the Tier-2 facilities worldwide and large non-WLCG resource providers. Major contributors of computing resources are listed in Ref. [61].

Access to Document

10.1103/PhysRevLett.132.081801Licence: Creative Commons: Attribution (CC BY)

AadG2024SearchFinal published version, 48.3 MBLicence: Creative Commons: Attribution (CC BY)

Cite this

@article{f85a1b6d75d642f4a37ea44ebc692f89,

title = "Search for new phenomena in two-body invariant mass distributions using unsupervised machine learning for anomaly detection at √s = 13 TeV with the ATLAS detector",

abstract = "Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb−1 of pp collisions at √s = 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b-jet and either one lepton (e, μ), photon, or second light jet or b-jet in the anomalous regions. No significant deviations from the background hypotheses are observed.",

author = "{ATLAS Collaboration} and P. P. Allport and A. D. Auriol and P. Bellos and G. A. Bird and J. Bracinik and D. G. Charlton and A. S. Chisholm and H. G. Cooke and L. Gonella and K. Krizka and J. D. Lomas and M. Marinescu and T. J. Neep and P. R. Newman and K. Nikolopoulos and {Cardoso Silva}, J. M. and E. Skorda and A. Stampekis and J. P. Thomas and P. D. Thompson and R. J. Ward and A. T. Watson and M. F. Watson and C. Wu",

note = "Acknowledgments: We thank CERN for the very successful operation of the LHC, as well as the support staff from our institutions without whom ATLAS could not be operated efficiently. We acknowledge the support of ANPCyT, Argentina; YerPhI, Armenia; ARC, Australia; BMWFW and FWF, Austria; ANAS, Azerbaijan; CNPq and FAPESP, Brazil; NSERC, NRC and CFI, Canada; CERN; ANID, Chile; CAS, MOST and NSFC, China; Minciencias, Colombia; MEYS CR, Czech Republic; DNRF and DNSRC, Denmark; IN2P3-CNRS and CEA-DRF/IRFU, France; SRNSFG, Georgia; BMBF, HGF and MPG, Germany; GSRI, Greece; RGC and Hong Kong SAR, China; ISF and Benoziyo Center, Israel; INFN, Italy; MEXT and JSPS, Japan; CNRST, Morocco; NWO, Netherlands; RCN, Norway; MEiN, Poland; FCT, Portugal; MNE/IFA, Romania; MESTD, Serbia; MSSR, Slovakia; ARRS and MIZ{\v S}, Slovenia; DSI/NRF, South Africa; MICINN, Spain; SRC and Wallenberg Foundation, Sweden; SERI, SNSF and Cantons of Bern and Geneva, Switzerland; MOST, Taiwan; TENMAK, T{\"u}rkiye; STFC, United Kingdom; DOE and NSF, USA. In addition, individual groups and members have received support from BCKDF, CANARIE, Compute Canada and CRC, Canada; PRIMUS 21/SCI/017 and UNCE SCI/013, Czech Republic; COST, ERC, ERDF, Horizon 2020, ICSC-NextGenerationEU and Marie Sk{\l}odowska-Curie Actions, European Union; Investissements d{\textquoteright}Avenir Labex, Investissements d{\textquoteright}Avenir Idex and ANR, France; DFG and AvH Foundation, Germany; Herakleitos, Thales and Aristeia programmes co-financed by EU-ESF and the Greek NSRF, Greece; BSF-NSF and MINERVA, Israel; Norwegian Financial Mechanism 2014-2021, Norway; NCN and NAWA, Poland; La Caixa Banking Foundation, CERCA Programme Generalitat de Catalunya and PROMETEO and GenT Programmes Generalitat Valenciana, Spain; G{\"o}ran Gustafssons Stiftelse, Sweden; The Royal Society and Leverhulme Trust, United Kingdom. The crucial computing support from all WLCG partners is acknowledged gratefully, in particular from CERN, the ATLAS Tier-1 facilities at TRIUMF (Canada), NDGF (Denmark, Norway, Sweden), CC-IN2P3 (France), KIT/GridKA (Germany), INFN-CNAF (Italy), NL-T1 (Netherlands), PIC (Spain), ASGC (Taiwan), RAL (UK) and BNL (USA), the Tier-2 facilities worldwide and large non-WLCG resource providers. Major contributors of computing resources are listed in Ref. [61].",

year = "2024",

month = feb,

day = "23",

doi = "10.1103/PhysRevLett.132.081801",

language = "English",

volume = "132",

journal = "Physical Review Letters",

issn = "0031-9007",

publisher = "American Physical Society (APS)",

number = "8",

}

TY - JOUR

T1 - Search for new phenomena in two-body invariant mass distributions using unsupervised machine learning for anomaly detection at √s = 13 TeV with the ATLAS detector

AU - ATLAS Collaboration

AU - Allport, P. P.

AU - Auriol, A. D.

AU - Bellos, P.

AU - Bird, G. A.

AU - Bracinik, J.

AU - Charlton, D. G.

AU - Chisholm, A. S.

AU - Cooke, H. G.

AU - Gonella, L.

AU - Krizka, K.

AU - Lomas, J. D.

AU - Marinescu, M.

AU - Neep, T. J.

AU - Newman, P. R.

AU - Nikolopoulos, K.

AU - Cardoso Silva, J. M.

AU - Skorda, E.

AU - Stampekis, A.

AU - Thomas, J. P.

AU - Thompson, P. D.

AU - Ward, R. J.

AU - Watson, A. T.

AU - Watson, M. F.

AU - Wu, C.

N1 - Acknowledgments: We thank CERN for the very successful operation of the LHC, as well as the support staff from our institutions without whom ATLAS could not be operated efficiently. We acknowledge the support of ANPCyT, Argentina; YerPhI, Armenia; ARC, Australia; BMWFW and FWF, Austria; ANAS, Azerbaijan; CNPq and FAPESP, Brazil; NSERC, NRC and CFI, Canada; CERN; ANID, Chile; CAS, MOST and NSFC, China; Minciencias, Colombia; MEYS CR, Czech Republic; DNRF and DNSRC, Denmark; IN2P3-CNRS and CEA-DRF/IRFU, France; SRNSFG, Georgia; BMBF, HGF and MPG, Germany; GSRI, Greece; RGC and Hong Kong SAR, China; ISF and Benoziyo Center, Israel; INFN, Italy; MEXT and JSPS, Japan; CNRST, Morocco; NWO, Netherlands; RCN, Norway; MEiN, Poland; FCT, Portugal; MNE/IFA, Romania; MESTD, Serbia; MSSR, Slovakia; ARRS and MIZŠ, Slovenia; DSI/NRF, South Africa; MICINN, Spain; SRC and Wallenberg Foundation, Sweden; SERI, SNSF and Cantons of Bern and Geneva, Switzerland; MOST, Taiwan; TENMAK, Türkiye; STFC, United Kingdom; DOE and NSF, USA. In addition, individual groups and members have received support from BCKDF, CANARIE, Compute Canada and CRC, Canada; PRIMUS 21/SCI/017 and UNCE SCI/013, Czech Republic; COST, ERC, ERDF, Horizon 2020, ICSC-NextGenerationEU and Marie Skłodowska-Curie Actions, European Union; Investissements d’Avenir Labex, Investissements d’Avenir Idex and ANR, France; DFG and AvH Foundation, Germany; Herakleitos, Thales and Aristeia programmes co-financed by EU-ESF and the Greek NSRF, Greece; BSF-NSF and MINERVA, Israel; Norwegian Financial Mechanism 2014-2021, Norway; NCN and NAWA, Poland; La Caixa Banking Foundation, CERCA Programme Generalitat de Catalunya and PROMETEO and GenT Programmes Generalitat Valenciana, Spain; Göran Gustafssons Stiftelse, Sweden; The Royal Society and Leverhulme Trust, United Kingdom. The crucial computing support from all WLCG partners is acknowledged gratefully, in particular from CERN, the ATLAS Tier-1 facilities at TRIUMF (Canada), NDGF (Denmark, Norway, Sweden), CC-IN2P3 (France), KIT/GridKA (Germany), INFN-CNAF (Italy), NL-T1 (Netherlands), PIC (Spain), ASGC (Taiwan), RAL (UK) and BNL (USA), the Tier-2 facilities worldwide and large non-WLCG resource providers. Major contributors of computing resources are listed in Ref. [61].

PY - 2024/2/23

Y1 - 2024/2/23

N2 - Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb−1 of pp collisions at √s = 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b-jet and either one lepton (e, μ), photon, or second light jet or b-jet in the anomalous regions. No significant deviations from the background hypotheses are observed.

AB - Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb−1 of pp collisions at √s = 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b-jet and either one lepton (e, μ), photon, or second light jet or b-jet in the anomalous regions. No significant deviations from the background hypotheses are observed.

U2 - 10.1103/PhysRevLett.132.081801

DO - 10.1103/PhysRevLett.132.081801

M3 - Letter

SN - 0031-9007

VL - 132

JO - Physical Review Letters

JF - Physical Review Letters

IS - 8

M1 - 081801

ER -

Search for new phenomena in two-body invariant mass distributions using unsupervised machine learning for anomaly detection at √s = 13 TeV with the ATLAS detector

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this