Studying Hadronization by Machine Learning Techniques
This work addresses the challenge of hadronization modeling for particle physicists, but it appears incremental as it applies existing deep learning methods to a known physical problem.
The paper tackled the problem of modeling hadronization, a non-perturbative process in particle physics, by applying ResNet neural networks to learn features from jet- and event-shape variables in proton-proton collisions at 7 TeV, using the Lund string fragmentation model as a baseline to predict observables at higher LHC energies.
Hadronization is a non-perturbative process, which theoretical description can not be deduced from first principles. Modeling hadron formation requires several assumptions and various phenomenological approaches. Utilizing state-of-the-art Computer Vision and Deep Learning algorithms, it is eventually possible to train neural networks to learn non-linear and non-perturbative features of the physical processes. In this study, results of two ResNet networks are presented by investigating global and kinematical quantities, indeed jet- and event-shape variables. The widely used Lund string fragmentation model is applied as a baseline in $\sqrt{s}= 7$ TeV proton-proton collisions to predict the most relevant observables at further LHC energies.