Neural Unfolding of the Chiral Magnetic Effect in Heavy-Ion Collisions
arXiv:2507.05808 · doi:10.1088/0256-307X/42/11/110101
Abstract
The search for the chiral magnetic effect (CME) in relativistic heavy-ion collisions (HICs) is challenged by significant background contamination. We present a novel deep learning approach based on a U-Net architecture to time-reversely unfold the dynamics of CME-related charge separation, enabling the reconstruction of the physics signal across the entire evolution of HICs. Trained on the events simulated by a multi-phase transport model with different cases of CME settings, our model learns to recover the charge separation based on final-state transverse momentum distributions at either the quark-gloun plasma freeze-out or hadronic freeze-out. This devises a methodological tool for the study of CME and underscores the promise of deep learning approaches in retrieving physics signals in HICs.
9+1 pages, 6+1 figures, final published version
References in corpus (30)
- Deep Learning in Neural Networks: An Overview
- The Chiral Magnetic Effect
- Learning phase transitions by confusion
- Berry Curvature, Triangle Anomalies, and the Chiral Magnetic Effect in Fermi Liquids
- Charge separation induced by P-odd bubbles in QCD matter
- Measurements of Strange Particle Production in Collisions at = 200 GeV
- Chiral anomaly and local polarization effect from quantum kinetic approach
- Beam-energy dependence of charge separation along the magnetic field in Au+Au collisions at RHIC
- Novel quantum phenomena induced by strong magnetic fields in heavy-ion collisions
- Properties of the QCD Matter -- An Experimental Review of Selected Results from RHIC BES Program
- Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
- Further developments of a multi-phase transport model for relativistic nuclear collisions
- Evolution of transverse flow and effective temperatures in the parton phase from a multi-phase transport model
- Enhanced Higgs to Searches with Deep Learning
- Exploring QCD matter in extreme conditions with Machine Learning
- Determine the neutron skin type by relativistic isobaric 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
- Impact of magnetic-field fluctuations on measurements of the chiral magnetic effect in collisions of isobaric nuclei
- Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
- Properties of the QCD Matter: A Review of Selected Results from the ALICE Experiment
- Dynamical exploring the QCD matter at finite temperatures and densities-a short review
- Electromagnetic fields from the extended Kharzeev-McLerran-Warringa model in relativistic heavy-ion collisions
- Two- and three-particle nonflow contributions to the chiral magnetic effect measurement by spectator and participant planes in relativistic heavy ion collisions
- Electromagnetic fields in ultra-peripheral relativistic heavy-ion collisions
- Search for the chiral magnetic effect in collisions between two isobars with deformed and neutron-rich nuclear structures
- Detecting Chiral Magnetic Effect via Deep Learning
- Machine learning study to identify collective flow in small and large colliding systems
- Difference between signal and background of the chiral magnetic effect relative to spectator and participant planes in isobar collisions at GeV