A new Machine Learning-based method for identification of time-correlated events at tagged photon facilities

TL;DR

This paper introduces a machine learning-based multivariate analysis method to identify time-correlated events at tagged photon facilities, improving precision and preserving kinematic correlations for better experimental analysis.

Contribution

The paper presents a novel machine learning approach that replaces traditional background subtraction, enhancing event selection accuracy and maintaining kinematic correlation information.

Findings

Effective identification of time-correlated events

Reduces uncertainties in high-precision experiments

Preserves correlations for phenomenological analysis

Abstract

We present a new Machine Learning-based multivariate analysis method for the selection of time-correlated hits in the tagging system and devices used to detect particles in the final state at the bremsstrahlung-based tagged photon facilities. This method can be applied instead of the widely used sampling and subtraction of the time-uncorrelated background, in particular at experiments aiming for high precision, where the subtraction of the time-uncorrelated background leads to increased uncertainties. Moreover, the identification of events with Machine Learning algorithms allows to preserve the information about correlations of kinematic variables in the final state, which can be advantageous for further phenomenological analyses of the experimental results.