26-31 July 2021
Mexico City
Mexico/General timezone
HADRON 2021 is over. Thanks for making it a success!
Home > Timetable > Session details > Contribution details

Contribution Leading parallel

Mexico City -
Analysis Tools

Probing the pole configuration of scattering amplitude using deep learning

Speakers

  • Dr. Denny Lane SOMBILLO

Primary authors

  • Dr. Denny Lane SOMBILLO (Research Center for Nuclear Physics, Osaka University/ National Institute of Physics, University of the Philippines Diliman)

Co-authors

Abstract

We propose a deep learning method that identifies the pole configuration of a coupled-channel scattering, i.e., the number of nearby poles in each Riemann sheet associated with the structures in the amplitude. A generic parametrized S-matrix is used to generate the dataset and curriculum learning is used for the training. We apply our method to the elastic $\pi N$ scattering and found that the observed structures are caused by one pole in each nearby sheet and two poles in the distance sheet.