Jet Substructure Classification in High-Energy Physics with Deep Neural Networks

By Pierre Baldi, K. Bauer, C. Eng, Peter Sadowski, Daniel Whiteson. 2016

204 citations recorded by the source corpus.

At the extreme energies of the Large Hadron Collider, massive particles can be produced at such high velocities that their hadronic decays are collimated and the resulting jets overlap. Deducing whether the substructure of an observed jet is due to a low-mass single particle or due to multiple decay objects of a massive particle is an important problem in the analysis of collider data. Traditional approaches have relied on expert features designed to detect energy deposition patterns in the calorimeter, but the complexity of the data make this task an excellent candidate for the application of machine learning tools. The data collected by the detector can be treated as a two-dimensional image, lending itself to the natural application of image classification techniques. In this work, we apply deep neural networks with a mixture of locally connected and fully connected nodes. Our experiments demonstrate that without the aid of expert features, such networks match or modestly outperform the current state-of-the-art approach for discriminating between jets from single hadronic particles and overlapping jets from pairs of collimated hadronic particles, and that such performance gains persist in the presence of pileup interactions.

Subfields: Computer Vision and Pattern Recognition, Nuclear and High Energy Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Nuclear and High Energy Physics

Citations in the corpus

Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis (2017, background): “There exists an entire literature [19, 20, 24] on the effort of classifying W boson from QCD jet images using machine learning, and the topic itself is an active field of research in high energy physics.”
Integrating Physics-Based Modeling with Machine Learning: A Survey (2020, background): “ML models have been shown to outperform physics-based models in many disciplines (e.g., materials science [130, 220, 263], applied physics [15, 116], aquatic sciences [120], atmospheric science [185], biomedical science [245], computational biology [3]).”
Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks (2016, result): “[30], which showed that despite the loss of resolution when these are taken into account the neural network is still somewhat superior to traditional techniques.”
Deep learning in color: towards automated quark/gluon jet discrimination (2016, methodology): “This and related neural network approaches were used for boosted W boson tagging in [10] and [12], top tagging in [11], heavy-flavor tagging in [13, 14], and comparing parton shower uncertainties in [15].”
Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning (2017, unknown): “The first applications of DNNs using all of the available information [533, 534, 535] represented jets as images(3) [537].”
Machine learning and the physical sciences (2019, methodology): “Shortly after the first applications of deep learning for event selection, deep convolutional networks were used for the purpose of jet tagging, where the low-level detector data lends itself to an image-like representation (Baldi et al., 2016a; de Oliveira et al., 2016).”
Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems (2020, background): “ML models have been shown to outperform physics-based models in many disciplines (e.g., materials science [148, 238, 285], applied physics [22, 127], aquatic sciences [132, 286], atmospheric science [206], biomedical science [264], computational biology [9]).”
Learning to Pivot with Adversarial Networks (2016, methodology): “We reuse the datasets used in (Baldi et al., 2016a).”
Energy flow polynomials: a complete linear basis for jet substructure (2017, methodology): “Jet images have been applied successfully to the same tagging problems considered here: quark/gluon discrimination [65], W tagging [63], and top tagging [66, 68].”
Energy flow networks: deep sets for particle jets (2018, background): “One common event representation is to view events as images by treating the energy deposits in a calorimeter as pixel intensities [4–9].”