Machine Learning for electromagnetic showers reconstruction in emulsion cloud chambers

Shirobokov, S.; Filatov, Anton Vladimirovich; Belavin, V.; Ustyuzhanin, A.

doi:10.1088/1742-6596/1085/4/042025

Cited by 4 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The low computation cost and differentiability (if available) of surrogate models enable tasks that might be infeasible using the original expensive model, including sensitivity analysis (e.g., using differentiability), optimization of parameters (e.g., using gradient descent), and uncertainty quantification (e.g., via efficient sampling). Surrogate models have been used in settings as diverse as particle physics (Shirobokov et al., 2020), exoplanet studies (Himes et al., 2022), probabilistic programming (Munk et al., 2022), and computer vision (Behl et al., 2020).…”

Section: Methods and Datamentioning

confidence: 99%

A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population

Baydin,

Poduval,

Schwadron

2023

Space Weather

View full text Add to dashboard Cite

The high energy particles originating from the Sun, known as solar energetic particles (SEPs), contribute significantly to the space radiation environment, posing serious threats to astronauts and scientific instruments on board spacecraft. The mechanism that accelerates the SEPs to the observed energy ranges, their transport in the inner heliosphere, and the influence of suprathermal seed particle spectrum are open questions in heliophysics. Accurate predictions of the occurrences of SEP events well in advance are necessary to mitigate their adverse effects but prediction based on first principle models still remains a challenge. In this scenario, adopting a machine learning approach to SEP modeling and prediction is desirable. However, the lack of a balanced database of SEP events restrains this approach. We addressed this limitation by generating large data sets of synthetic SEP events sampled from the physics‐based model, Energetic Particle Radiation Environment Module (EPREM). Using this data, we developed neural networks‐based surrogate models to study the seed population parameter space. Our models, EPREM‐S, run thousands to millions of times faster (depending on computer hardware), making simulation‐based inference workflows practicable in SEP studies while providing predictive uncertainty estimates using a deep ensemble approach.

show abstract

Section: Methods and Datamentioning

confidence: 99%

A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population

Baydin,

Poduval,

Schwadron

2023

Space Weather

View full text Add to dashboard Cite

show abstract

“…The emulsion stacks are very good for reconstructing the vertex of a neutrino interaction, but they cannot easily provide a measurement of the neutrino energy. On an event by event basis the neutrino energy can be estimated using the methods developed in OPERA and other emulsion based detectors, which for instance exploit the correlation between track multiplicity and neutrino energy [16][17][18]. The achievable resolution depends on the brick structure; a resolution of 50% in the 0.1-1 TeV energy range seems realistic.…”

Section: Experiments Generalitiesmentioning

confidence: 99%

Further studies on the physics potential of an experiment using LHC neutrinos

Béni

Brucoli

Cafaro

et al. 2020

J. Phys. G: Nucl. Part. Phys.

View full text Add to dashboard Cite

We discuss an experiment to investigate neutrino physics at the LHC, with emphasis on tau flavour. As described in our previous paper Beni et al (2019 J. Phys. G: Nucl. Part. Phys. 46 115008), the detector can be installed in the decommissioned TI18 tunnel, ≈480 m downstream the ATLAS cavern, after the first bending dipoles of the LHC arc. The detector intercepts the intense neutrino flux, generated by the LHC beams colliding in IP1, at large pseudorapidity η, where neutrino energies can exceed a TeV. This paper focuses on exploring the neutrino pseudorapity versus energy phase space available in TI18 in order to optimize the detector location and acceptance for neutrinos originating at the pp interaction point, in contrast to neutrinos from pion and kaon decays. The studies are based on the comparison of simulated pp collisions at s = 13 TeV: PYTHIA events of heavy quark (c and b) production, compared to DPMJET minimum bias events (including charm) with produced particles traced through realistic LHC optics with FLUKA. Our studies favour a configuration where the detector is positioned off the beam axis, slightly above the ideal prolongation of the LHC beam from the straight section, covering 7.4 < η < 9.2. In this configuration, the flux at high energies (0.5–1.5 TeV and beyond) is found to be dominated by neutrinos originating directly from IP1, mostly from charm decays, of which ≈50% are electron neutrinos and ≈5% are tau neutrinos. The contribution of pion and kaon decays to the muon neutrino flux is found small at those high energies. With 150 fb−1 of delivered LHC luminosity in Run 3 the experiment can record a few thousand very high energy neutrino charged current (CC) interactions and over 50 tau neutrino CC events. These events provide useful information in view of a high statistics experiment at HL–LHC. The electron and muon neutrino samples can extend the knowledge of the charm PDF to a new region of x, which is dominated by theory uncertainties. The tau neutrino sample can provide first experience on reconstruction of tau neutrino events in a very boosted regime.

show abstract

“…The emulsion packages are very good for reconstructing the vertex of a neutrino interaction, but they cannot easily provide a measurement of the neutrino energy. On an event by event basis the neutrino energy can be estimated using the methods developed in OPERA and other emulsion based detectors, which for instance exploit the correlation between track multiplicity and neutrino energy [17][18][19]. The achievable resolution depends on the brick structure which is begin optimized; we target a resolution of 50% in the 0.1-1 TeV energy range.…”

Section: Detector Design Considerationsmentioning

confidence: 99%

XSEN: a $ν$N Cross Section Measurement using High Energy Neutrinos from pp collisions at the LHC

Beni,

Buontempo,

Camporesi

et al. 2019

Preprint

View full text Add to dashboard Cite

XSEN (Cross Section of Energetic Neutrinos) is a small experiment designed to study, for the first time, neutrino-nucleon interactions (including the tau flavour) in the 0.5-1 TeV neutrino energy range. The detector will be installed in the decommissioned TI18 tunnel and uses nuclear emulsions. Its simplicity allows construction and installation before the LHC Run 3, 2021-2023; with 150/fb in Run3, the experiment can record up to two thousand neutrino interactions, and up to a hundred tau neutrino events. The XSEN detector intercepts the intense neutrino flux, generated by the LHC beams colliding in IP1, at large pseudo-rapidities, where neutrino energies can exceed the TeV. Since the neutrino-N interaction cross section grows almost linearly with energy, the detector can be light and still collect a considerable sample of neutrino interactions. In our proposal, the detector weighs less than 3 tons. It is lying slightly above the ideal prolongation of the LHC beam from the straight section; this configuration, off the beam axis, although very close to it, enhances the contribution of neutrinos from c and b decays, and consequently of tau neutrinos. The detector fits in the TI18 tunnel without modifications. We plan for a demonstrator experiment in 2021 with a small detector of about 0.5 tons; with 25/fb, nearly a hundred interactions of neutrinos of about 1 TeV can be recorded. The aim of this pilot run is a good in-situ characterisation of the machine-generated backgrounds, an experimental verification of the systematic uncertainties and efficiencies, and a tuning of the emulsion analysis infrastructure and efficiency. This Letter provides an overview of the experiment motivations, location, design constraints, technology choice, and operation.

show abstract

Machine Learning for electromagnetic showers reconstruction in emulsion cloud chambers

Cited by 4 publications

References 4 publications

A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population

A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population

Further studies on the physics potential of an experiment using LHC neutrinos

XSEN: a $ν$N Cross Section Measurement using High Energy Neutrinos from pp collisions at the LHC

Contact Info

Product

Resources

About