Ultra-Peripheral Collisions as a Nuclear-Structure Interferometer with Interpretable Multitask Deep Learning

2026-06-22

AI Summary

Precisely probing nuclear structure is challenged by the difficulty in disentangling correlated effects such as deformation and neutron skin. This work proposes the first framework integrating interpretable multi-task deep learning with physical modeling of ultra-peripheral collisions, leveraging the transverse momentum distribution of coherent photoproduced J/ψ mesons to simultaneously extract multiple nuclear structure observables and identify the key kinematic regions driving each inference. The method effectively separates diffractive and interference contributions, successfully decoupling the two dominant structural features in zirconium-96 collisions. It thereby delivers high-quality, analysis-ready observables suitable for constraining nuclear density distributions in high-luminosity experiments.

Abstract

Precise knowledge of nuclear structure is essential across fundamental physics, yet probing these structures is notoriously difficult. To address this challenge, ultra-peripheral collisions (UPCs) provide a femtoscopic tomography for imaging the atomic nucleus. UPCs offer a pristine electromagnetic pathway: coherent vector-meson photoproduction generates patterns of diffraction and two-source interference that directly encode the nuclear spatial density. Turning these patterns into quantitative constraints is, however, a challenging inverse problem, complicated by correlated sensitivities to deformation and neutron skin, phase smearing, and experimental backgrounds. Here we introduce an interpretable Multitask deep-learning framework that maps transverse momentum distributions to multiple nuclear-structure indicators simultaneously and identifies the kinematic regions driving each inference. We demonstrate the approach with coherent $J/ψ$ photoproduction in $^{96}_{40}\text{Zr} + ^{96}_{40}\text{Zr}$ collisions, showing that the learned features separate diffraction-dominated and interference-dominated information and provide analysis-ready observables for future high-luminosity data.

Problem

• nuclear structure
• ultra-peripheral collisions
• vector-meson photoproduction
• diffraction
• interference

Innovation

• ultra-peripheral collisions
• interpretable deep learning
• multitask learning
• nuclear structure tomography
• coherent photoproduction