Cargando…

GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions

The LHCb experiment at the Large Hadron Collider (LHC) is designed to perform high-precision measurements of heavy-hadron decays, which requires the collection of large data samples and a good understanding and suppression of multiple background sources. Both factors are challenged by a five-fold in...

Descripción completa

Detalles Bibliográficos
Autores principales: García Pardinas, Julián, Calvi, Marta, Eschle, Jonas, Mauri, Andrea, Meloni, Simone, Mozzanica, Martina, Serra, Nicola
Lenguaje:eng
Publicado: 2023
Materias:
Acceso en línea:http://cds.cern.ch/record/2859637
_version_ 1780977701195087872
author García Pardinas, Julián
Calvi, Marta
Eschle, Jonas
Mauri, Andrea
Meloni, Simone
Mozzanica, Martina
Serra, Nicola
author_facet García Pardinas, Julián
Calvi, Marta
Eschle, Jonas
Mauri, Andrea
Meloni, Simone
Mozzanica, Martina
Serra, Nicola
author_sort García Pardinas, Julián
collection CERN
description The LHCb experiment at the Large Hadron Collider (LHC) is designed to perform high-precision measurements of heavy-hadron decays, which requires the collection of large data samples and a good understanding and suppression of multiple background sources. Both factors are challenged by a five-fold increase in the average number of proton-proton collisions per bunch crossing, corresponding to a change in the detector operation conditions for the LHCb Upgrade I phase, recently started. A further ten-fold increase is expected in the Upgrade II phase, planed for the next decade. The limits in the storage capacity of the trigger will bring an inverse relation between the amount of particles selected to be stored per event and the number of events that can be recorded, and the background levels will raise due to the enlarged combinatorics. To tackle both challenges, we propose a novel approach, never attempted before in a hadronic collider: a Deep-learning based Full Event Interpretation (DFEI), to perform the simultaneous identification, isolation and hierarchical reconstruction of all the heavy-hadron decay chains per event. This approach radically contrasts with the standard selection procedure used in LHCb to identify heavy-hadron decays, that looks individually at sub-sets of particles compatible with being products of specific decay types, disregarding the contextual information from the rest of the event. We present the first prototype for the DFEI algorithm, that leverages the power of Graph Neural Networks (GNN). This paper describes the design and development of the algorithm, and its performance in Upgrade I simulated conditions.
id cern-2859637
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2023
record_format invenio
spelling cern-28596372023-07-19T05:03:29Zhttp://cds.cern.ch/record/2859637engGarcía Pardinas, JuliánCalvi, MartaEschle, JonasMauri, AndreaMeloni, SimoneMozzanica, MartinaSerra, NicolaGNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisionsphysics.ins-detDetectors and Experimental Techniqueshep-exParticle Physics - ExperimentThe LHCb experiment at the Large Hadron Collider (LHC) is designed to perform high-precision measurements of heavy-hadron decays, which requires the collection of large data samples and a good understanding and suppression of multiple background sources. Both factors are challenged by a five-fold increase in the average number of proton-proton collisions per bunch crossing, corresponding to a change in the detector operation conditions for the LHCb Upgrade I phase, recently started. A further ten-fold increase is expected in the Upgrade II phase, planed for the next decade. The limits in the storage capacity of the trigger will bring an inverse relation between the amount of particles selected to be stored per event and the number of events that can be recorded, and the background levels will raise due to the enlarged combinatorics. To tackle both challenges, we propose a novel approach, never attempted before in a hadronic collider: a Deep-learning based Full Event Interpretation (DFEI), to perform the simultaneous identification, isolation and hierarchical reconstruction of all the heavy-hadron decay chains per event. This approach radically contrasts with the standard selection procedure used in LHCb to identify heavy-hadron decays, that looks individually at sub-sets of particles compatible with being products of specific decay types, disregarding the contextual information from the rest of the event. We present the first prototype for the DFEI algorithm, that leverages the power of Graph Neural Networks (GNN). This paper describes the design and development of the algorithm, and its performance in Upgrade I simulated conditions.arXiv:2304.08610oai:cds.cern.ch:28596372023-04-17
spellingShingle physics.ins-det
Detectors and Experimental Techniques
hep-ex
Particle Physics - Experiment
García Pardinas, Julián
Calvi, Marta
Eschle, Jonas
Mauri, Andrea
Meloni, Simone
Mozzanica, Martina
Serra, Nicola
GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions
title GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions
title_full GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions
title_fullStr GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions
title_full_unstemmed GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions
title_short GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions
title_sort gnn for deep full event interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions
topic physics.ins-det
Detectors and Experimental Techniques
hep-ex
Particle Physics - Experiment
url http://cds.cern.ch/record/2859637
work_keys_str_mv AT garciapardinasjulian gnnfordeepfulleventinterpretationandhierarchicalreconstructionofheavyhadrondecaysinprotonprotoncollisions
AT calvimarta gnnfordeepfulleventinterpretationandhierarchicalreconstructionofheavyhadrondecaysinprotonprotoncollisions
AT eschlejonas gnnfordeepfulleventinterpretationandhierarchicalreconstructionofheavyhadrondecaysinprotonprotoncollisions
AT mauriandrea gnnfordeepfulleventinterpretationandhierarchicalreconstructionofheavyhadrondecaysinprotonprotoncollisions
AT melonisimone gnnfordeepfulleventinterpretationandhierarchicalreconstructionofheavyhadrondecaysinprotonprotoncollisions
AT mozzanicamartina gnnfordeepfulleventinterpretationandhierarchicalreconstructionofheavyhadrondecaysinprotonprotoncollisions
AT serranicola gnnfordeepfulleventinterpretationandhierarchicalreconstructionofheavyhadrondecaysinprotonprotoncollisions