Model independent analysis of coupled-channel scattering: a deep learning approach

Abstract

We develop a robust method to extract the pole configuration of a given partial-wave amplitude. In our approach, a deep neural network is constructed where the statistical errors of the experimental data are taken into account. The teaching dataset is constructed using a generic S-matrix parametrization, ensuring that all the poles produced are independent of each other. The inclusion of statistical error results into a noisy classification dataset which we should solve using the curriculum method. As an application, we use the elastic $\pi N$ amplitude in the $I(J^P)=1/2(1/2^{-})$ sector where $10^6$ amplitudes are produced by combining points in each error bar of the experimental data. We fed the amplitudes to the trained deep neural network and find that the enhancements in the $\pi N$ amplitude are caused by one pole in each nearby unphysical sheet and at most two poles in the distant sheet. Finally, we show that the extracted pole configurations are independent of the way points in each error bar are drawn and combined, demonstrating the statistical robustness of our method.

arXiv comment11 pages, 6 figures, 5 tables, companion paper to arXiv:2104.14182

References in corpus (21)

• Machine learning and the physical sciences
• Hadronic molecules
• Non-Standard Heavy Mesons and Baryons, an Experimental Review
• Observation of a narrow pentaquark state, $P_c(4312{)}^{+}$, and of two-peak structure of the $P_c(4450{)}^{+}$
• Extended Partial-Wave Analysis of piN Scattering Data
• Observation of structure in the $J/\psi$-pair mass spectrum
• Nucleon resonances within a dynamical coupled-channels model of pi N and gamma N reactions
• Evidence for the two pole structure of the Lambda(1405) resonance
• Flavor SU(3) breaking effects in the chiral unitary model for meson-baryon scatterings
• Electromagnetic Meson Production in the Nucleon Resonance Region
• Machine and Deep Learning Applications in Particle Physics
• Parameterization dependence of T matrix poles and eigenphases from a fit to piN elastic scattering data
• Interpretation of the LHCb Pc(4312) Signal
• Coupled-channel interpretation of the LHCb double-$J/\psi$ spectrum and hints of a new state near the $J/\psi J/\psi$ threshold
• Extraction of Resonances from Meson-Nucleon Reactions
• Pole analysis on the hadron spectroscopy of ${\Lambda }_b\to J/\Psi p{K}^{-}$
• Building up the spectrum of pentaquark states as hadronic molecules
• Classifying Pole of Amplitude Using Deep Neural Network
• Classifying near-threshold enhancement using deep neural network
• A New Method to Extract Information of Near-Threshold Resonances: Uniformized Pole-Sum Representation of Green's Function and T-matrix
• Application of the Uniformized Mittag-Leffler Expansion to $\Lambda (1405)$

Cited by in corpus (13)

• An updated review of the new hadron states
• Novel approaches in Hadron Spectroscopy
• Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
• Revealing the nature of hidden charm pentaquarks with machine learning
• Decay behaviors of the fully-bottom and fully-charm tetraquark states
• Deep Learning Exotic Hadrons
• Classifying near-threshold enhancement using deep neural network
• Identifying Hadronic Molecular States with a Neural Network
• Study of exotic hadrons with machine learning
• Interpretation of near-threshold peaks using the method of independent S-matrix poles
• Rediscovery of Numerical Lüscher's Formula from the Neural Network
• Learning Pole Structures of Hadronic States using Predictive Uncertainty Estimation
• A Novel Implementation of the Matrix Element Method at Next-to-Leading Order for the Measurement of the Higgs Self-Coupling ${\lambda }_{3H}$