Engineering Papers⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3158053

Improving missing transverse momentum estimation with a deep neural network

Hayrapetyan, A. [Yerevan Physics Institute]·Makarenko, V. [Yerevan Physics Institute] (ORCID:0000000284068605)·Tumasyan, A. [Yerevan Physics Institute] (ORCID:0009000006846742)·Adam, W. [Institut für Hochenergiephysik] (ORCID:0000000190994341)·Andrejkovic, J. W. [Institut für Hochenergiephysik]·Benato, L. [Institut für Hochenergiephysik] (ORCID:0000000151357489)·Bergauer, T. [Institut für Hochenergiephysik] (ORCID:0000000257860293)·Dragicevic, M. [Institut für Hochenergiephysik] (ORCID:0000000319676783)·Giordano, C. [Institut für Hochenergiephysik]·Hussain, P. S. [Institut für Hochenergiephysik] (ORCID:0000000248255278)·Jeitler, M. [Institut für Hochenergiephysik] (ORCID:0000000251419560)·Krammer, N. [Institut für Hochenergiephysik] (ORCID:0000000205480985)·Li, A. [Institut für Hochenergiephysik] (ORCID:000000024547116X)·Liko, D. [Institut für Hochenergiephysik] (ORCID:000000023380473X)·Matthewman, M. [Institut für Hochenergiephysik]·Mikulec, I. [Institut für Hochenergiephysik] (ORCID:0000000303852746)·Schieck, J. [Institut für Hochenergiephysik] (ORCID:0000000210588093)·Schöfbeck, R. [Institut für Hochenergiephysik] (ORCID:0000000223328784)·Schwarz, D. [Institut für Hochenergiephysik] (ORCID:0000000238217331)·Shooshtari, M. [Institut für Hochenergiephysik]·Sonawane, M. [Institut für Hochenergiephysik] (ORCID:0000000305107010)·Waltenberger, W. [Institut für Hochenergiephysik] (ORCID:0000000262157228)·Wulz, C.-E. [Institut für Hochenergiephysik] (ORCID:0000000192265812)·Janssen, T. [Universiteit Antwerpen] (ORCID:0000000239984081)·Kwon, H. [Universiteit Antwerpen] (ORCID:0009000251655018)·Ocampo Henao, D. [Universiteit Antwerpen] (ORCID:0000000197593452)·Van Laer, T. [Universiteit Antwerpen] (ORCID:0000000177762108)·Van Mechelen, P. [Universiteit Antwerpen] (ORCID:0000000287319051)·Bierkens, J. [Vrije Universiteit Brussel] (ORCID:0000000208753977)·Breugelmans, N. [Vrije Universiteit Brussel]·D’Hondt, J. [Vrije Universiteit Brussel] (ORCID:0000000295986241)·Dansana, S. [Vrije Universiteit Brussel] (ORCID:0000000277527471)·De Moor, A. [Vrije Universiteit Brussel] (ORCID:0000000159641935)·Delcourt, M. [Vrije Universiteit Brussel] (ORCID:0000000182061787)·Heyen, F. [Vrije Universiteit Brussel]·Hong, Y. [Vrije Universiteit Brussel] (ORCID:0000000347522458)·Kashko, P. [Vrije Universiteit Brussel] (ORCID:0000000270507152)·Lowette, S. [Vrije Universiteit Brussel] (ORCID:0000000339849987)·Makarenko, I. [Vrije Universiteit Brussel] (ORCID:0000000285534508)·Müller, D. [Vrije Universiteit Brussel] (ORCID:0000000217524527)·Song, J. [Vrije Universiteit Brussel] (ORCID:0000000327315881)·Tavernier, S. [Vrije Universiteit Brussel] (ORCID:0000000267929522)·Tytgat, M. [Vrije Universiteit Brussel] (ORCID:0000000239902074)·Van Onsem, G. P. [Vrije Universiteit Brussel] (ORCID:0000000216642337)·Van Putte, S. [Vrije Universiteit Brussel] (ORCID:0000000315593606)·Vannerom, D. [Vrije Universiteit Brussel] (ORCID:0000000227475095)·Bilin, B. [Université Libre de Bruxelles] (ORCID:0000000314397128)·Clerbaux, B. [Université Libre de Bruxelles] (ORCID:0000000185478211)·Das, A. K. [Université Libre de Bruxelles]·De Bruyn, I. [Université Libre de Bruxelles] (ORCID:0000000317044360)·De Lentdecker, G. [Université Libre de Bruxelles] (ORCID:0000000151247693)·Evard, H. [Université Libre de Bruxelles] (ORCID:0009000550391462)·Favart, L. [Université Libre de Bruxelles] (ORCID:0000000316457454)·Gianneios, P. [Université Libre de Bruxelles] (ORCID:0009000372330738)·Khalilzadeh, A. [Université Libre de Bruxelles]·Khan, F. A. [Université Libre de Bruxelles] (ORCID:000900022039277X)·Malara, A. [Université Libre de Bruxelles] (ORCID:0000000186459282)·Shahzad, M. A. [Université Libre de Bruxelles]·Thomas, L. [Université Libre de Bruxelles] (ORCID:0000000227563853)·Vanden Bemden, M. [Université Libre de Bruxelles] (ORCID:0009000077257945)·Vander Velde, C. [Université Libre de Bruxelles] (ORCID:0000000333927294)·Vanlaer, P. [Université Libre de Bruxelles] (ORCID:0000000279314496)·Zhang, F. [Université Libre de Bruxelles] (ORCID:0000000261582468)·De Coen, M. [Ghent University] (ORCID:0000000258547442)·Dobur, D. [Ghent University] (ORCID:0000000300124866)·Gokbulut, G. [Ghent University] (ORCID:0000000201756454)·Knolle, J. [Ghent University] (ORCID:0000000247815704)·Marckx, D. [Ghent University] (ORCID:0000000167522290)·Skovpen, K. [Ghent University] (ORCID:0000000211600621)·Tomaru, A. M. [Ghent University]·Van Den Bossche, N. [Ghent University] (ORCID:0000000329734991)·van der Linden, J. [Ghent University] (ORCID:000000027174781X)·Vandenbroeck, J. [Ghent University] (ORCID:0009000461413404)·Wezenbeek, L. [Ghent University] (ORCID:000000016952891X)·Bein, S. [Université Catholique de Louvain] (ORCID:0000000193877407)·Benecke, A. [Université Catholique de Louvain] (ORCID:0000000302523609)·Bethani, A. [Université Catholique de Louvain] (ORCID:0000000281507043)·Bruno, G. [Université Catholique de Louvain] (ORCID:0000000188578197)·Cappati, A. [Université Catholique de Louvain] (ORCID:0000000343860564)·De Favereau De Jeneret, J. [Université Catholique de Louvain] (ORCID:0000000317758574)·Delaere, C. [Université Catholique de Louvain] (ORCID:0000000187076021)·Giammanco, A. [Université Catholique de Louvain] (ORCID:0000000196408294)·Guzel, A. O. [Université Catholique de Louvain] (ORCID:0000000294045933)·Lemaitre, V. [Université Catholique de Louvain]·Lidrych, J. [Université Catholique de Louvain] (ORCID:0000000314390196)·Malek, P. [Université Catholique de Louvain] (ORCID:0000000331839741)·Mastrapasqua, P. [Université Catholique de Louvain] (ORCID:0000000220432367)·Turkcapar, S. [Université Catholique de Louvain] (ORCID:0000000326080494)·Alves, G. A. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000283691446)·Barroso Ferreira Filho, M. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000339040571)·Coelho, E. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000161149907)·Hensel, C. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000188747624)·Menezes De Oliveira, T. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0009000947298354)·Mora Herrera, C. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000339153170)·Rebello Teles, P. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000190298506)·Soeiro, M. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000247676468)·Tonelli Manganote, E. J. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000324598521)·Vilela Pereira, A. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000331774626)·Aldá Júnior, W. L. [Universidade do Estado do Rio de Janeiro] (ORCID:0000000158559817)·Brandao Malbouisson, H. [Universidade do Estado do Rio de Janeiro] (ORCID:000000021326318X)
View original source ↗Read source document ↗Export metadata ↓

Abstract

At hadron colliders, the net transverse momentum of particles that do not interact with the detector (missing transverse momentum, $^→_𝑝$$^{miss}_{T}$) is a crucial observable in many analyses. In the standard model, $^→_𝑝$$^{miss}_{T}$ originates from neutrinos. Many beyond-the-standard-model particles, such as dark matter candidates, are also expected to leave the experimental apparatus undetected. This paper presents a novel deep neural network based $^→_𝑝$$^{miss}_{T}$ estimator, DeepMET, developed by the CMS Collaboration at the LHC. The DeepMET algorithm produces a weight for each reconstructed particle based on its properties. The estimator is based on the negative vector sum of the weighted transverse momenta of all reconstructed particles in an event. Compared with other estimators currently employed by CMS, DeepMET improves the $^→_𝑝$$^{miss}_{T}$ resolution by 10%–30%, shows improvement for a wide range of final states, is easier to train, and is more resilient against the effects of additional proton-proton interactions accompanying the collision of interest.

Explore related subjects

artificial neural networkshadron colliderssignatures with missing energy

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Hayrapetyan, A. [Yerevan Physics Institute], Makarenko, V. [Yerevan Physics Institute] (ORCID:0000000284068605), Tumasyan, A. [Yerevan Physics Institute] (ORCID:0009000006846742), Adam, W. [Institut für Hochenergiephysik] (ORCID:0000000190994341), Andrejkovic, J. W. [Institut für Hochenergiephysik], Benato, L. [Institut für Hochenergiephysik] (ORCID:0000000151357489), Bergauer, T. [Institut für Hochenergiephysik] (ORCID:0000000257860293), Dragicevic, M. [Institut für Hochenergiephysik] (ORCID:0000000319676783), Giordano, C. [Institut für Hochenergiephysik], Hussain, P. S. [Institut für Hochenergiephysik] (ORCID:0000000248255278), Jeitler, M. [Institut für Hochenergiephysik] (ORCID:0000000251419560), Krammer, N. [Institut für Hochenergiephysik] (ORCID:0000000205480985), Li, A. [Institut für Hochenergiephysik] (ORCID:000000024547116X), Liko, D. [Institut für Hochenergiephysik] (ORCID:000000023380473X), Matthewman, M. [Institut für Hochenergiephysik], Mikulec, I. [Institut für Hochenergiephysik] (ORCID:0000000303852746), Schieck, J. [Institut für Hochenergiephysik] (ORCID:0000000210588093), Schöfbeck, R. [Institut für Hochenergiephysik] (ORCID:0000000223328784), Schwarz, D. [Institut für Hochenergiephysik] (ORCID:0000000238217331), Shooshtari, M. [Institut für Hochenergiephysik], Sonawane, M. [Institut für Hochenergiephysik] (ORCID:0000000305107010), Waltenberger, W. [Institut für Hochenergiephysik] (ORCID:0000000262157228), Wulz, C.-E. [Institut für Hochenergiephysik] (ORCID:0000000192265812), Janssen, T. [Universiteit Antwerpen] (ORCID:0000000239984081), Kwon, H. [Universiteit Antwerpen] (ORCID:0009000251655018), Ocampo Henao, D. [Universiteit Antwerpen] (ORCID:0000000197593452), Van Laer, T. [Universiteit Antwerpen] (ORCID:0000000177762108), Van Mechelen, P. [Universiteit Antwerpen] (ORCID:0000000287319051), Bierkens, J. [Vrije Universiteit Brussel] (ORCID:0000000208753977), Breugelmans, N. [Vrije Universiteit Brussel], D’Hondt, J. [Vrije Universiteit Brussel] (ORCID:0000000295986241), Dansana, S. [Vrije Universiteit Brussel] (ORCID:0000000277527471), De Moor, A. [Vrije Universiteit Brussel] (ORCID:0000000159641935), Delcourt, M. [Vrije Universiteit Brussel] (ORCID:0000000182061787), Heyen, F. [Vrije Universiteit Brussel], Hong, Y. [Vrije Universiteit Brussel] (ORCID:0000000347522458), Kashko, P. [Vrije Universiteit Brussel] (ORCID:0000000270507152), Lowette, S. [Vrije Universiteit Brussel] (ORCID:0000000339849987), Makarenko, I. [Vrije Universiteit Brussel] (ORCID:0000000285534508), Müller, D. [Vrije Universiteit Brussel] (ORCID:0000000217524527), Song, J. [Vrije Universiteit Brussel] (ORCID:0000000327315881), Tavernier, S. [Vrije Universiteit Brussel] (ORCID:0000000267929522), Tytgat, M. [Vrije Universiteit Brussel] (ORCID:0000000239902074), Van Onsem, G. P. [Vrije Universiteit Brussel] (ORCID:0000000216642337), Van Putte, S. [Vrije Universiteit Brussel] (ORCID:0000000315593606), Vannerom, D. [Vrije Universiteit Brussel] (ORCID:0000000227475095), Bilin, B. [Université Libre de Bruxelles] (ORCID:0000000314397128), Clerbaux, B. [Université Libre de Bruxelles] (ORCID:0000000185478211), Das, A. K. [Université Libre de Bruxelles], De Bruyn, I. [Université Libre de Bruxelles] (ORCID:0000000317044360), De Lentdecker, G. [Université Libre de Bruxelles] (ORCID:0000000151247693), Evard, H. [Université Libre de Bruxelles] (ORCID:0009000550391462), Favart, L. [Université Libre de Bruxelles] (ORCID:0000000316457454), Gianneios, P. [Université Libre de Bruxelles] (ORCID:0009000372330738), Khalilzadeh, A. [Université Libre de Bruxelles], Khan, F. A. [Université Libre de Bruxelles] (ORCID:000900022039277X), Malara, A. [Université Libre de Bruxelles] (ORCID:0000000186459282), Shahzad, M. A. [Université Libre de Bruxelles], Thomas, L. [Université Libre de Bruxelles] (ORCID:0000000227563853), Vanden Bemden, M. [Université Libre de Bruxelles] (ORCID:0009000077257945), Vander Velde, C. [Université Libre de Bruxelles] (ORCID:0000000333927294), Vanlaer, P. [Université Libre de Bruxelles] (ORCID:0000000279314496), Zhang, F. [Université Libre de Bruxelles] (ORCID:0000000261582468), De Coen, M. [Ghent University] (ORCID:0000000258547442), Dobur, D. [Ghent University] (ORCID:0000000300124866), Gokbulut, G. [Ghent University] (ORCID:0000000201756454), Knolle, J. [Ghent University] (ORCID:0000000247815704), Marckx, D. [Ghent University] (ORCID:0000000167522290), Skovpen, K. [Ghent University] (ORCID:0000000211600621), Tomaru, A. M. [Ghent University], Van Den Bossche, N. [Ghent University] (ORCID:0000000329734991), van der Linden, J. [Ghent University] (ORCID:000000027174781X), Vandenbroeck, J. [Ghent University] (ORCID:0009000461413404), Wezenbeek, L. [Ghent University] (ORCID:000000016952891X), Bein, S. [Université Catholique de Louvain] (ORCID:0000000193877407), Benecke, A. [Université Catholique de Louvain] (ORCID:0000000302523609), Bethani, A. [Université Catholique de Louvain] (ORCID:0000000281507043), Bruno, G. [Université Catholique de Louvain] (ORCID:0000000188578197), Cappati, A. [Université Catholique de Louvain] (ORCID:0000000343860564), De Favereau De Jeneret, J. [Université Catholique de Louvain] (ORCID:0000000317758574), Delaere, C. [Université Catholique de Louvain] (ORCID:0000000187076021), Giammanco, A. [Université Catholique de Louvain] (ORCID:0000000196408294), Guzel, A. O. [Université Catholique de Louvain] (ORCID:0000000294045933), Lemaitre, V. [Université Catholique de Louvain], Lidrych, J. [Université Catholique de Louvain] (ORCID:0000000314390196), Malek, P. [Université Catholique de Louvain] (ORCID:0000000331839741), Mastrapasqua, P. [Université Catholique de Louvain] (ORCID:0000000220432367), Turkcapar, S. [Université Catholique de Louvain] (ORCID:0000000326080494), Alves, G. A. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000283691446), Barroso Ferreira Filho, M. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000339040571), Coelho, E. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000161149907), Hensel, C. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000188747624), Menezes De Oliveira, T. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0009000947298354), Mora Herrera, C. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000339153170), Rebello Teles, P. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000190298506), Soeiro, M. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000247676468), Tonelli Manganote, E. J. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000324598521), Vilela Pereira, A. [Centro Brasileiro de Pesquisas Fisicas] (ORCID:0000000331774626), Aldá Júnior, W. L. [Universidade do Estado do Rio de Janeiro] (ORCID:0000000158559817), Brandao Malbouisson, H. [Universidade do Estado do Rio de Janeiro] (ORCID:000000021326318X). 2026-04-21. Improving missing transverse momentum estimation with a deep neural network. https://doi.org/10.1103/c4z7-tqvc

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

Physics potential of the IceCube Upgrade for atmospheric neutrino oscillations

The IceCube Upgrade is an extension of the existing IceCube Neutrino Observatory and will be deployed in the 2025–2026 austral summer. It will significantly improve the sensitivity of the detector to atmospheric neutrino oscillations. The existing 86-string IceCube array contains a dense in-fill known as DeepCore which is optimized to measure neutrinos with energies down to a few GeV. The IceCube Upgrade will consist of seven new densely instrumented strings placed within the DeepCore volume to further enhance the performance in the GeV energy range. The additional strings will feature new optical modules, each containing multiple photomultiplier tubes (PMTs), in contrast to the existing modules that each contain a single PMT. This will more than triple the number of PMT channels with respect to the current IceCube configuration, allowing for improved detection efficiency and reconstruction performance at GeV energies. We describe necessary updates to simulation, event selection, and reconstruction to accommodate the higher data rates observed by the upgraded detector and the addition of multi-PMT modules. We determine the expected sensitivity of the IceCube Upgrade to the atmospheric neutrino oscillation parameters sin 2 ⁡𝜃 23 and Δ⁢𝑚$^{2}_{32}$, the appearance of tau neutrinos and the neutrino mass ordering. The IceCube Upgrade will provide neutrino oscillation measurements that are of similar precision to those from accelerator experiments, while providing complementarity by probing higher energies and longer baselines, and with different sources of systematic uncertainties.

artificial neural networks↗
DOE OSTI2025

Incorporating Physical Priors into Weakly Supervised Anomaly Detection

We propose a new machine-learning-based anomaly detection strategy for comparing data with a background-only reference (a form of weak supervision). The sensitivity of previous strategies degrades significantly when the signal is too rare or there are many unhelpful features. Our prior-assisted weak supervision (PAWS) method incorporates information from a class of signal models to significantly enhance the search sensitivity of weakly supervised approaches. As long as the true signal is in the prespecified class, PAWS matches the sensitivity of a dedicated, fully supervised method without specifying the exact parameters ahead of time. On the benchmark LHC Olympics anomaly detection dataset, our mix of semisupervised and weakly supervised learning is able to extend the sensitivity over previous methods by a factor of 10 in cross section. Furthermore, if we add irrelevant (noise) dimensions to the inputs, classical methods degrade by another factor of 10 in cross section while PAWS remains insensitive to noise. This new approach could be applied in a number of scenarios and pushes the frontier of sensitivity between completely model-agnostic approaches and fully model-specific searches.

artificial neural networks↗
DOE OSTI2025

Data-driven analysis of dipole strength functions using artificial neural networks

Here, we present a data-driven analysis of dipole strength functions across the nuclear chart, employing an artificial neural network to model nuclear dipole responses. We train the network on a dataset of experimentally measured dipole strength functions for 216 different nuclei. To assess its predictive capability, we test the trained model on an additional set of 10 new nuclei, where experimental data exist. We demonstrate that the artificial neural network not only accurately reproduces known data but also identifies potential inconsistencies in experimental datasets, indicating which results may warrant further review or possible rejection. For nuclei where experimental data are sparse or unavailable, the network confirms theoretical calculations, reinforcing its utility as a predictive tool in nuclear physics. Finally, utilizing the predicted electric dipole polarizability, we extract the value of the symmetry energy at saturation density and find it consistent with results from the literature.

artificial neural networks↗