Currently, newly developed artificial intelligence techniques, in particular convolutional neural networks, are being investigated for use in data-processing and classification of particle physics collider data. One such challenging task is to distinguish quark-initiated jets from gluon-initiated jets. Following previous work, we treat the jet as an image by pixelizing track information and calorimeter deposits as reconstructed by the detector. We test the deep learning paradigm by training several recently developed, state-of-the-art convolutional neural networks on the quark-gluon discrimination task. We compare the results obtained using various network architectures trained for quark-gluon discrimination and also a boosted decision tree (BDT) trained on summary variables.
We study the impact of including quark- and gluon-initiated jet discrimination in the search for strongly interacting supersymmetric particles at the LHC. Taking the example of gluino pair production, considerable improvement is observed in the LHC search reach on including the jet substructure observables to the standard kinematic variables within a multivariate analysis. In particular, quark and gluon jet separation has higher impact in the region of intermediate mass-gap between the gluino and the lightest neutralino, as the difference between the signal and the standard model background ki…
Understanding jets initiated by quarks and gluons is of fundamental importance in collider physics. Efficient and robust techniques for quark versus gluon jet discrimination have consequences for new physics searches, precision $α_s$ studies, parton distribution function extractions, and many other applications. Numerous machine learning analyses have attacked the problem, demonstrating that good performance can be obtained but generally not providing an understanding for what properties of the jets are responsible for that separation power. In this paper, we provide an extensive and detailed …
Deep learning techniques are currently being investigated for high energy physics experiments, to tackle a wide range of problems, with quark and gluon discrimination becoming a benchmark for new algorithms. One weakness is the traditional reliance on Monte Carlo simulations, which may not be well modelled at the detail required by deep learning algorithms. The weakly supervised learning paradigm gives an alternate route to classification, by using samples with different quark--gluon proportions instead of fully labeled samples. The paradigm has, therefore, huge potential for particle physics …
We estimate the number of quark jets in QCD multi-jet final states at hadron colliders. In the estimation, we develop the calculation of jet rates into that of quark jet rates. From the calculation, we estimate the improvement on the signal-to-background ratio for a signal semi-analytically by applying quark/gluon discrimination, where the signal predicts many quark jets. We introduce a variable related to jet flavors in multi-jet final states and propose a data-driven method using the variable to reduce systematic uncertainties of analysis results. As the same with the semi-analytical result,…
Predictions for our ability to distinguish quark and gluon jets vary by more than a factor of two between different parton showers. We study this problem using analytic resummed predictions for the thrust event shape up to NNLL' using $e^+e^- \to Z \to q \bar q$ and $e^+e^- \to H \to gg$ as proxies for quark and gluon jets. We account for hadronization effects through a nonperturbative shape function, and include an estimate of both perturbative and hadronization uncertainties. In contrast to previous studies, we find reasonable agreement between our results and predictions from both Pythia an…
Charged track multiplicity is among the most powerful observables for discriminating quark- from gluon-initiated jets. Despite its utility, it is not infrared and collinear (IRC) safe, so perturbative calculations are limited to studying the energy evolution of multiplicity moments. While IRC-safe observables, like jet mass, are perturbatively calculable, their distributions often exhibit Casimir scaling, such that their quark/gluon discrimination power is limited by the ratio of quark to gluon color factors. In this paper, we introduce new IRC-safe counting observables whose discrimination pe…
We show that in studies of light quark- and gluon-initiated jet discrimination, it is important to include the information on softer reconstructed jets (associated jets) around a primary hard jet. This is particularly relevant while adopting a small radius parameter for reconstructing hadronic jets. The probability of having an associated jet as a function of the primary jet transverse momentum ($p_T$) and radius, the minimum associated jet $p_T$ and the association radius is computed upto next-to-double logarithmic accuracy (NDLA), and the predictions are compared with results from Herwig++, …
Many physics analyses at the LHC are looking into processes where the signal jets are originating from quarks, while jets in the background are more gluon enriched. Based on observables sensitive to fundamental differences in the fragmentation properties of gluons and quarks, a likelihood discriminant is constructed to distinguish between jets originating from quarks and gluons. The performance of the tagger is evaluated using Z+jets and dijet events produced in proton-proton collisions at a centre-of-mass energy of 8 TeV, recorded by the CMS experiment at the LHC.
Discriminating quark jets from gluon jets is an important but challenging problem in jet substructure. In this paper, we use the concept of mutual information to illuminate the physics of quark/gluon tagging. Ideal quark/gluon separation requires only one bit of truth information, so even if two discriminant variables are largely uncorrelated, they can still share the same "truth overlap". Mutual information can be used to diagnose such situations, and thus determine which discriminant variables are redundant and which can be combined to improve performance. Using both parton showers and analy…
A likelihood-based discriminant for the identification of quark- and gluon-initiated jets is built and validated using 4.7 fb$^{-1}$ of proton-proton collision data at $\sqrt{s}$ = 7 TeV collected with the ATLAS detector at the LHC. Data samples with enriched quark or gluon content are used in the construction and validation of templates of jet properties that are the input to the likelihood-based discriminant. The discriminating power of the jet tagger is established in both data and Monte Carlo samples within a systematic uncertainty of 10-20%. In data, light-quark jets can be tagged with an…
Since the machine learning techniques are improving rapidly, it has been shown that the image recognition techniques in deep neural networks can be used to detect jet substructure. And it turns out that deep neural networks can match or outperform traditional approach of expert features. However, there are disadvantages such as sparseness of jet images. Based on the natural tree-like structure of jet sequential clustering, the recursive neural networks (RecNNs), which embed jet clustering history recursively as in natural language processing, have a better behavior when confronted with these p…
Pulse shape discrimination plays a key role in improving the signal-to-background ratio in NEOS analysis by removing fast neutrons. Identifying particles by looking at the tail of the waveform has been an effective and plausible approach for pulse shape discrimination, but has the limitation in sorting low energy particles. As a good alternative, the convolutional neural network can scan the entire waveform as they are to recognize the characteristics of the pulse and perform shape classification of NEOS data. This network provides a powerful identification tool for all energy ranges and helps…
We present a comparison of data of lepton angular distributions of Drell-Yan/$Z$ production with the fixed-order pQCD calculations by which the baseline of pQCD effects is illustrated. As for the $Z$ production, we predict that $A_0$ and $A_2$ for $Z$ plus single gluon-jet events are very different from that of $Z$ plus single quark-jet events, allowing a new experimental tool for checking various algorithms which attempt to discriminate quark jets from gluon jets. Using an intuitive geometric approach, we show that the violation of the Lam-Tung relation, appearing at large transverse-momentum…
In the search for neutrinoless double-beta decay, the high-pressure gaseous Time Projection Chamber has a distinct advantage, because the ionization charge tracks produced by particle interactions are extended and the detector captures the full three-dimensional charge distribution with appropriate charge readout systems. Such information of tracks provides a crucial extra-handle for discriminating signal events against backgrounds. In this paper, we constructed a toy model to demonstrate where the discrimination power comes from and how much of it the neural network models have already harnes…
The PandaX-III experiment will search for neutrinoless double beta decay of $^{136}$Xe with high pressure gaseous time projection chambers at the China Jin-Ping underground Laboratory. The tracking feature of gaseous detectors helps suppress the background level, resulting in the improvement of the detection sensitivity. We study a method based on the convolutional neural networks to discriminate double beta decay signals against the background from high energy gammas generated by $^{214}$Bi and $^{208}$Tl decays based on detailed Monte Carlo simulation. Using the 2-dimensional projections of …
New jet observables are defined which characterize both fractal and scale-dependent contributions to the distribution of hadrons in a jet. These infrared safe observables, named Extended Fractal Observables (EFOs), have been applied to quark-gluon discrimination to demonstrate their potential utility. The EFOs are found to be individually discriminating and only weakly correlated to variables used in existing discriminators. Consequently, their inclusion improves discriminator performance, as here demonstrated with particle level simulation from the parton shower.
Jet substructure observables, designed to identify specific features within jets, play an essential role at the Large Hadron Collider (LHC), both for searching for signals beyond the Standard Model and for testing QCD in extreme phase space regions. In this paper, we systematically study the structure of infrared and collinear safe substructure observables, defining a generalization of the energy correlation functions to probe $n$-particle correlations within a jet. These generalized correlators provide a flexible basis for constructing new substructure observables optimized for specific purpo…
By measuring the substructure of a jet, one can assign it a "quark" or "gluon" tag. In the eikonal (double-logarithmic) limit, quark/gluon discrimination is determined solely by the color factor of the initiating parton (C_F versus C_A). In this paper, we confront the challenges faced when going beyond this leading-order understanding, using both parton-shower generators and first-principles calculations to assess the impact of higher-order perturbative and nonperturbative physics. Working in the idealized context of electron-positron collisions, where one can define a proxy for quark and gluo…
Previous studies have demonstrated the utility and applicability of machine learning techniques to jet physics. In this paper, we construct new observables for the discrimination of jets from different originating particles exclusively from information identified by the machine. The approach we propose is to first organize information in the jet by resolved phase space and determine the effective $N$-body phase space at which discrimination power saturates. This then allows for the construction of a discrimination observable from the $N$-body phase space coordinates. A general form of this obs…
At proposed future hadron colliders and in the coming years at the LHC, top quarks will be produced at genuinely multi-TeV energies. Top-tagging at such high energies forces us to confront several new issues in terms of detector capabilities and jet physics. Here, we explore these issues in the context of some simple JHU/CMS-type declustering algorithms and the N-subjettiness jet-shape variable tau_32. We first highlight the complementarity between the two tagging approaches at particle-level with respect to discriminating top-jets against gluons and quarks, using multivariate optimization sca…
These are lecture notes presented at the 2017 CTEQ Summer School at the University of Pittsburgh and the 2018 CTEQ Summer School at the University of Puerto Rico, Mayaguez. The title is a reference to hep-th/0309149 and introduces perturbative QCD and its application to jet substructure from a bottom-up perspective based on the approximation of QCD as a weakly-coupled, conformal field theory. Using this approach, a simple derivation of the Sudakov form factor with soft gluon emission modeled as a Poisson process is presented. Topics of the identification and discrimination of quark- versus glu…
Jet identification is one of the fields in high energy physics that machine learning has begun to make an impact. More often than not, convolutional neural networks are used to classify jet images with the benefit that essentially no physics input is required. Inspired by a recent work by Datta and Larkoski, we study the classification of quark/gluon-initiated jets based on fully-connected neural networks (FNNs), where expert-designed physical variables are taken as input. FNNs are applied in two ways: trained separately on various narrow jet transverse momentum $p_{TJ}$ bins; trained on a wid…
We propose a modified definition of the jet charge, the "dynamic jet charge", where the constant jet momentum fraction weighting parameter, $κ$, in the standard jet charge definition is generalized to be a function of a dynamical property of the jet or the individual jet constituents. The dynamic jet charge can complement analyses based on the standard definition and give improved discrimination between quark and gluon initiated jets and between jets initiated by different quark flavors. We focus on the specific scenario where each hadron in the jet contributes to the dynamic jet charge with a…
We demonstrate that the classification of boosted, hadronically-decaying weak gauge bosons can be significantly improved over traditional cut-based and BDT-based methods using deep learning and the jet charge variable. We construct binary taggers for $W^+$ vs. $W^-$ and $Z$ vs. $W$ discrimination, as well as an overall ternary classifier for $W^+$/$W^-$/$Z$ discrimination. Besides a simple convolutional neural network (CNN), we also explore a composite of two CNNs, with different numbers of layers in the jet $p_{T}$ and jet charge channels. We find that this novel structure boosts the performa…
Searches for production of supersymmetric partners of gluons and quarks with the CMS experiment at CERN's LHC have excluded these particles for masses up to about 2 TeV. The paper will present results and show the analysis techniques in these searches, with an emphasis on the use of razor variables for the discrimination between standard model backgrounds and signal.
The success of Convolutional Neural Networks (CNNs) in image classification has prompted efforts to study their use for classifying image data obtained in Particle Physics experiments. Here, we discuss our efforts to apply CNNs to 2D and 3D image data from particle physics experiments to classify signal from background. In this work we present an extensive convolutional neural architecture search, achieving high accuracy for signal/background discrimination for a HEP classification use-case based on simulated data from the Ice Cube neutrino observatory and an ATLAS-like detector. We demonstrat…
Distinguishing between prompt muons produced in heavy boson decay and muons produced in association with heavy-flavor jet production is an important task in analysis of collider physics data. We explore whether there is information available in calorimeter deposits that is not captured by the standard approach of isolation cones. We find that convolutional networks and particle-flow networks accessing the calorimeter cells surpass the performance of isolation cones, suggesting that the radial energy distribution and the angular structure of the calorimeter deposits surrounding the muon contain…
Quantum Graph Neural Networks for Jet Tagging on Quantum Hardware
University of California, Los Angeles（加州大学洛杉矶分校）；University of Maryland, College Park（马里兰大学帕克分校）；National Quantum Lab, University of Maryland（马里兰大学国家量子实验室）；Mani L. Bhaumik Institute for Theoretical Physics, University of California, Los Angeles（加州大学洛杉矶分校马尼·L·巴乌米克理论物理研究所）；Center for Quantum Science and Engineering, University of California, Los Angeles（加州大学洛杉矶分校量子科学与工程中心）
Jet-flavour identification algorithms are of paramount importance to maximise the physics potential of the Future Circular Collider (FCC). Out of the extensive FCC-ee physics program, flavour tagging is crucial for the Higgs physics program, given the dominance of hadronic decays of the Higgs boson. Highly efficient discrimination of $b$-, $c$-, $s$-, and gluon jets allows access to novel decay modes that cannot be identified at the LHC, adding quantitatively new dimensions to the Higgs physics programme. This contribution presents new jet flavour identification algorithms based on advanced ma…
The Advanced Energetic Pair Telescope gamma-ray polarimeter uses a time projection chamber for measuring pair production events and is expected to generate a raw instrument data rate four orders of magnitude greater than is transmittable with typical satellite data communications. GammaNet, a convolutional neural network, proposes to solve this problem by performing event classification on-board for pair production and background events, reducing the data rate to a level that can be accommodated by typical satellite communication systems. In order to train GammaNet, a set of 1.1x10^6 pair prod…
