Deep Learning Jet Image as a Probe of Light Higgsino Dark Matter at the LHC

Abstract

Higgsino in supersymmetric standard models can play the role of dark matter particle. In conjunction with the naturalness criterion, the higgsino mass parameter is expected to be around the electroweak scale. In this work, we explore the potential of probing the nearly degenerate light higgsinos with machine learning at the LHC. By analyzing jet images and other jet substructure information, we use the Convolutional Neural Network(CNN) to enhance the signal significance. We find that our deep learning jet image method can improve the previous result based on the conventional cut-flow by about a factor of two at the High-Luminosity LHC.

arXiv comment24 pages, 9 figures, 1 table, discussions and references added, version accepted by PRD

References in corpus (73)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• Supersymmetric Dark Matter
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Particle-flow reconstruction and global event description with the CMS detector
• Identifying Boosted Objects with N-subjettiness
• Natural SUSY Endures
• A Natural SUSY Higgs Near 125 GeV
• Multi-TeV Scalars are Natural in Minimal Supergravity
• Focus Points and Naturalness in Supersymmetry
• The Well-Tempered Neutralino
• ParticleNet: Jet Tagging via Particle Clouds
• Deep Learning and its Application to LHC Physics
• Jet reconstruction and performance using particle flow with the ATLAS Detector
• Neutralino Dark Matter in Focus Point Supersymmetry
• Dark matter production in the early Universe: beyond the thermal WIMP paradigm
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• A Convolutional Neural Network Neutrino Event Classifier
• The Machine Learning Landscape of Top Taggers
• Neutralino Dark Matter at 14 and 100 TeV
• Quark and Gluon Tagging at the LHC
• Seeing in Color: Jet Superstructure
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Hunting Quasi-Degenerate Higgsinos
• Quark and Gluon Jet Substructure
• Compressed electroweakino spectra at the LHC
• The Lund Jet Plane
• Hidden SUSY at the LHC: the light higgsino-world scenario and the role of a lepton collider
• Probing Light Higgsinos in Natural SUSY from Monojet Signals at the LHC
• Higgsino Dark Matter in High-Scale Supersymmetry
• Search for chargino--neutralino pair production in final states with three leptons and missing transverse momentum in $\sqrt{s}=13$ TeV $pp$ collisions with the ATLAS detector
• Anomaly detection with Convolutional Graph Neural Networks
• Boosting $H\to b\bar{b}$ with Machine Learning
• Nearly Degenerate Gauginos and Dark Matter at the LHC
• Direct and indirect detection of higgsino-like WIMPs: concluding the story of electroweak naturalness
• Uncovering Natural Supersymmetry via the interplay between the LHC and Direct Dark Matter Detection
• Probing natural SUSY from stop pair production at the LHC
• Search for disappearing tracks as a signature of new long-lived particles in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Accessing the core of naturalness, nearly degenerate higgsinos, at the LHC
• Current experimental bounds on stop mass in natural SUSY
• Probing stop pair production at the LHC with graph neural networks
• Supervised deep learning in high energy phenomenology: a mini review
• Mass Degeneracy of the Higgsinos
• A light SUSY dark matter after CDMS-II, LUX and LHC Higgs data
• Status and prospects of light bino-higgsino dark matter in natural SUSY
• Search for supersymmetry in final states with two or three soft leptons and missing transverse momentum in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• Search for resonant production of strongly coupled dark matter in proton-proton collisions at 13 TeV
• Natural MSSM after the LHC 8 TeV run
• Higgsino Dark Matter in the MSSM
• Photon-jet events as a probe of axion-like particles at the LHC
• Detecting an axion-like particle with machine learning at the LHC
• Higgs boson tagging with the Lund jet plane
• Cornering Higgsino: Use of Soft Displaced Track
• Complementarity of WIMP Sensitivity with direct SUSY, Monojet and Dark Matter Searches in the MSSM
• Quark-Gluon Jet Discrimination Using Convolutional Neural Networks
• Probing triple Higgs coupling with machine learning at the LHC
• The LHC higgsino discovery plane for present and future SUSY searches
• Deep learning for the R-parity violating supersymmetry searches at the LHC
• New angular (and other) cuts to improve the higgsino signal at the LHC
• Indirect Detection of a Light Higgsino Motivated by Collider Data
• Using Machine Learning to disentangle LHC signatures of Dark Matter candidates
• Quark Gluon Jet Discrimination with Weakly Supervised Learning
• Higgs boson decays into narrow di-photon jets and their search strategies at the Large Hadron Collider
• An indirect probe of higgsino world at the CEPC
• On the coverage of neutralino dark matter in coannihilations at the upgraded LHC
• Searching for the light Higgsinos in MSSM at the future e-p colliders
• Probing Higgs exotic decay at the LHC with machine learning
• Artificial Neural Networks as Non-Linear Extensions of Statistical Methods in Astronomy
• Deeply Learned Preselection of Higgs Dijet Decays at Future Lepton Colliders

Cited by in corpus (8)

• Quantum Generative Adversarial Networks For Anomaly Detection In High Energy Physics
• MLAnalysis: An open-source program for high energy physics analyses
• New Physics Search at the CEPC: a General Perspective
• Interpretable deep learning models for the inference and classification of LHC data
• Discriminating sub-TeV gamma and hadron-induced showers through their footprints
• Fast multilabel classification of HEP constraints with deep learning
• HL-LHC sensitivity to higgsinos from natural SUSY with gravitino LSP
• Machine Learning Electroweakino Production