Detecting Chiral Magnetic Effect via Deep Learning

Abstract

The search of chiral magnetic effect (CME) in heavy-ion collisions has attracted long-term attentions. Multiple observables have been proposed but all suffer from obstacles due to large background contaminations. In this Letter, we construct an observable-independent CME-meter based on a deep convolutional neural network. After trained over data set generated by a multiphase transport model, the CME-meter shows high accuracy in recognizing the CME-featured charge separation from the final-state pion spectra. It also exhibits remarkable robustness to diverse conditions including different collision energies, centralities, and elliptic flow backgrounds. In a transfer learning manner, the CME-meter is validated in isobaric collision systems, showing good transferability among different colliding systems. Based on variational approaches, we utilize the DeepDream method to derive the most responsive CME-spectra that demonstrates the physical contents the machine learns.

7 pages, 10 figures

References in corpus (17)

• Deep Learning in Neural Networks: An Overview
• The Chiral Magnetic Effect
• Learning phase transitions by confusion
• Charge conservation in RHIC and contributiuons to local parity violation observables
• Lambda hyperon polarization in relativistic heavy ion collisions from the chiral kinetic approach
• Testing the Chiral Magnetic Effect with Central U+U collisions
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Azimuthal correlations from transverse momentum conservation and possible local parity violation
• Evolution of transverse flow and effective temperatures in the parton phase from a multi-phase transport model
• Test the chiral magnetic effect with isobaric collisions
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Electric Fields and Chiral Magnetic Effect in Cu + Au Collisions
• The effect of triangular flow on di-hadron azimuthal correlations in relativistic heavy ion collisions
• Heavy quark potential in quark-gluon Plasma: Deep neural network meets lattice quantum chromodynamics
• Deep learning stochastic processes with QCD phase transition
• A fast centrality-meter for heavy-ion collisions at the CBM experiment
• Reconstructing spectral functions via automatic differentiation

Cited by in corpus (8)

• Machine Learning in Nuclear Physics
• Exploring QCD matter in extreme conditions with Machine Learning
• Machine learning study to identify collective flow in small and large colliding systems
• Estimation of collision centrality in terms of the number of participating nucleons in heavy-ion collisions using deep learning
• Neural Unfolding of the Chiral Magnetic Effect in Heavy-Ion Collisions
• Optimal Observables for the Chiral Magnetic Effect from Machine Learning
• Applying Deep Learning Technique to Chiral Magnetic Wave Search
• A deep learning approach for predicting multiple observables in Au+Au collisions at RHIC