Reconstructing boosted Higgs jets from event image segmentation

Abstract

Based on the jet image approach, which treats the energy deposition in each calorimeter cell as the pixel intensity, the Convolutional neural network (CNN) method has been found to achieve a sizable improvement in jet tagging compared to the traditional jet substructure analysis. In this work, the Mask R-CNN framework is adopted to reconstruct Higgs jets in collider-like events, with the effects of pileup contamination taken into account. This automatic jet reconstruction method achieves higher efficiency of Higgs jet detection and higher accuracy of Higgs boson four-momentum reconstruction than traditional jet clustering and jet substructure tagging methods. Moreover, the Mask R-CNN trained on events containing a single Higgs jet is capable of detecting one or more Higgs jets in events of several different processes, without apparent degradation in reconstruction efficiency and accuracy. The outputs of the network also serve as new handles for the $t\bar{t}$ background suppression, complementing to traditional jet substructure variables.

23 pages, 11 figures, version to appear in JHEP

References in corpus (10)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• Jet substructure as a new Higgs search channel at the LHC
• Pileup subtraction using jet areas
• Boosted Decision Trees as an Alternative to Artificial Neural Networks for Particle Identification
• Top-tagging: A Method for Identifying Boosted Hadronic Tops
• Boosted objects: a probe of beyond the Standard Model physics
• Techniques for improved heavy particle searches with jet substructure
• Jets in Hadron-Hadron Collisions
• Multivariate discrimination and the Higgs + W/Z search
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons

Cited by in corpus (8)

• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• Detecting an axion-like particle with machine learning at the LHC
• Higgs boson tagging with the Lund jet plane
• Disentangling Boosted Higgs Boson Production Modes with Machine Learning
• Machine Learning for Particle Flow Reconstruction at CMS
• Automatic detection of boosted Higgs boson and top quark jets in an event image
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• Jet Reconstruction with Mamba Networks in Collider Events