Cargando…
A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme
Particle identification in large high-energy physics experiments typically relies on classifiers obtained by combining many experimental observables. Predicting the probability density function (pdf) of such classifiers in the multivariate space covering the relevant experimental features is usually...
Autores principales: | , , , , , |
---|---|
Lenguaje: | eng |
Publicado: |
2021
|
Materias: | |
Acceso en línea: | https://dx.doi.org/10.1088/1748-0221/17/02/P02018 http://cds.cern.ch/record/2788509 |
_version_ | 1780972133591023616 |
---|---|
author | Graziani, Giacomo Anderlini, Lucio Mariani, Saverio Franzoso, Edoardo Pappalardo, Luciano Libero di Nezza, Pasquale |
author_facet | Graziani, Giacomo Anderlini, Lucio Mariani, Saverio Franzoso, Edoardo Pappalardo, Luciano Libero di Nezza, Pasquale |
author_sort | Graziani, Giacomo |
collection | CERN |
description | Particle identification in large high-energy physics experiments typically relies on
classifiers obtained by combining many experimental observables. Predicting the probability density function (pdf) of such classifiers in the multivariate space covering the relevant experimental features is usually challenging.
The detailed simulation of the detector response from first principles
cannot provide the reliability needed for the most precise physics measurements.
Data-driven modelling is usually preferred, though sometimes limited by the available data size and different coverage of the feature space by the control channels.
In this paper, we discuss a novel approach to the modelling of particle
identification classifiers using machine-learning techniques. The marginal pdf of the classifiers is described with a Gaussian Mixture Model, whose parameters are predicted by Multi Layer Perceptrons trained on calibration data. As a proof of principle, the method is applied to the data acquired by the LHCb experiment in its fixed-target configuration. The model is trained on a data sample of proton-neon collisions and applied to smaller data samples of proton-helium and proton-argon collisions collected at different centre-of-mass energies. The method is shown to perform better than a detailed simulation-based approach, to be fast and suitable to be applied to a large variety of use cases. |
id | cern-2788509 |
institution | Organización Europea para la Investigación Nuclear |
language | eng |
publishDate | 2021 |
record_format | invenio |
spelling | cern-27885092023-03-31T11:58:00Zdoi:10.1088/1748-0221/17/02/P02018http://cds.cern.ch/record/2788509engGraziani, GiacomoAnderlini, LucioMariani, SaverioFranzoso, EdoardoPappalardo, Luciano Liberodi Nezza, PasqualeA Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programmeParticle Physics - ExperimentParticle identification in large high-energy physics experiments typically relies on classifiers obtained by combining many experimental observables. Predicting the probability density function (pdf) of such classifiers in the multivariate space covering the relevant experimental features is usually challenging. The detailed simulation of the detector response from first principles cannot provide the reliability needed for the most precise physics measurements. Data-driven modelling is usually preferred, though sometimes limited by the available data size and different coverage of the feature space by the control channels. In this paper, we discuss a novel approach to the modelling of particle identification classifiers using machine-learning techniques. The marginal pdf of the classifiers is described with a Gaussian Mixture Model, whose parameters are predicted by Multi Layer Perceptrons trained on calibration data. As a proof of principle, the method is applied to the data acquired by the LHCb experiment in its fixed-target configuration. The model is trained on a data sample of proton-neon collisions and applied to smaller data samples of proton-helium and proton-argon collisions collected at different centre-of-mass energies. The method is shown to perform better than a detailed simulation-based approach, to be fast and suitable to be applied to a large variety of use cases.Particle identification in large high-energy physics experiments typically relies on classifiers obtained by combining many experimental observables. Predicting the probability density function (pdf) of such classifiers in the multivariate space covering the relevant experimental features is usually challenging. The detailed simulation of the detector response from first principles cannot provide the reliability needed for the most precise physics measurements. Data-driven modelling is usually preferred, though sometimes limited by the available data size and different coverage of the feature space by the control channels. In this paper, we discuss a novel approach to the modelling of particle identification classifiers using machine-learning techniques. The marginal pdf of the classifiers is described with a Gaussian Mixture Model, whose parameters are predicted by Multi Layer Perceptrons trained on calibration data. As a proof of principle, the method is applied to the data acquired by the LHCb experiment in its fixed-target configuration. The model is trained on a data sample of proton-neon collisions and applied to smaller data samples of proton-helium and proton-argon collisions collected at different centre-of-mass energies. The method is shown to perform better than a detailed simulation-based approach, to be fast and suitable to be applied to a large variety of use cases.arXiv:2110.10259LHCb-DP-2021-007oai:cds.cern.ch:27885092021-10-19 |
spellingShingle | Particle Physics - Experiment Graziani, Giacomo Anderlini, Lucio Mariani, Saverio Franzoso, Edoardo Pappalardo, Luciano Libero di Nezza, Pasquale A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme |
title | A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme |
title_full | A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme |
title_fullStr | A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme |
title_full_unstemmed | A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme |
title_short | A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme |
title_sort | neural-network-defined gaussian mixture model for particle identification applied to the lhcb fixed-target programme |
topic | Particle Physics - Experiment |
url | https://dx.doi.org/10.1088/1748-0221/17/02/P02018 http://cds.cern.ch/record/2788509 |
work_keys_str_mv | AT grazianigiacomo aneuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT anderlinilucio aneuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT marianisaverio aneuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT franzosoedoardo aneuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT pappalardolucianolibero aneuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT dinezzapasquale aneuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT grazianigiacomo neuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT anderlinilucio neuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT marianisaverio neuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT franzosoedoardo neuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT pappalardolucianolibero neuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme AT dinezzapasquale neuralnetworkdefinedgaussianmixturemodelforparticleidentificationappliedtothelhcbfixedtargetprogramme |