Köln 2025 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
HK: Fachverband Physik der Hadronen und Kerne
HK 9: Heavy-Ion Collisions and QCD Phases II
HK 9.2: Talk
Monday, March 10, 2025, 17:00–17:15, HS 3 Chemie
Modeling charged-particle spectra in high-energy pp collisions with deep neural networks — •Maria Alejandra Calmon Behling, Jerome Jung, Mario Krüger, and Henner Büsching — Institut für Kernphysik, Goethe Universität Frankfurt
During the data-taking campaigns Run 1 and Run 2 of the Large Hadron Collider (LHC), the ALICE collaboration recorded a large amount of proton-proton (pp) collisions across a variety of center-of-mass energies (√s ). This extensive dataset is well suited to study the energy dependence of particle production. Deep neural networks (DNNs) provide a powerful regression tool to capture underlying multidimensional correlations inherent in the data. DNNs are used to parametrize recent ALICE measurements of multiplicity (Nch)- and transverse momentum (pT)-dependent charged-particle spectra. This new approach allows extrapolating the measurements towards higher Nch and pT values as well as to unmeasured √s , providing data-driven references for future heavy-ion measurements.
In this talk, we present the current status of the analysis. We discuss the potential and limitations of using DNNs to model complex multidimensional data and compare the results to those from event generators.
Supported by BMBF and the Helmholtz Association.
Keywords: ALICE; LHC; pp collisions; charged particles; deep neural networks