Detecting Chiral Magnetic Effect via Deep Learning

TL;DR

This paper introduces a deep learning-based observable-independent CME-meter that accurately detects the chiral magnetic effect in heavy-ion collisions, demonstrating robustness and transferability across different experimental conditions.

Contribution

It develops a novel deep convolutional neural network approach for CME detection that overcomes background issues and is validated across multiple collision systems.

Findings

High accuracy in recognizing CME features from pion spectra

Robustness to different collision energies and backgrounds

Good transferability among different colliding systems

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.