Reconstructing axion-like particles from beam dumps with simulation-based inference

TL;DR

This paper demonstrates that simulation-based inference using neural networks can effectively reconstruct axion-like particle properties from beam-dump experiment data, outperforming traditional methods and aiding experimental design.

Contribution

It introduces a machine learning framework employing invertible neural networks for ALP parameter reconstruction, enhancing accuracy and flexibility over conventional techniques.

Findings

Neural networks outperform traditional parameter reconstruction methods.

The approach provides reliable uncertainty estimates.

The method can be quickly adapted to different detector configurations.

Abstract

Axion-like particles (ALPs) that decay into photon pairs pose a challenge for experiments that rely on the construction of a decay vertex in order to search for long-lived particles. This is particularly true for beam-dump experiments, where the distance between the unknown decay position and the calorimeter can be very large. In this work we use machine learning to explore the possibility to reconstruct the ALP properties, in particular its mass and lifetime, from such inaccurate observations. We use a simulation-based inference approach based on conditional invertible neural networks to reconstruct the posterior probability of the ALP parameters for a given set of events. We find that for realistic angular and energy resolution, such a neural network significantly outperforms parameter reconstruction from conventional high-level variables while at the same time providing reliable uncertainty estimates. Moreover, the neural network can quickly be re-trained for different detector properties, making it an ideal framework for optimizing experimental design.