Reconstructing parton collisions with machine learning techniques

TL;DR

This paper demonstrates that machine learning, specifically neural networks, can effectively reconstruct parton-level kinematics from collider event data, enhancing understanding of particle collision dynamics.

Contribution

The study introduces a novel machine learning approach using neural networks to reconstruct parton collisions with high efficiency, incorporating NLO QCD-QED corrections in simulated collider events.

Findings

Neural networks achieved high reconstruction efficiency.

Photon-hadron production provided a clean signal for analysis.

Inclusion of NLO QCD-QED corrections improved accuracy.

Abstract

Having access to the parton-level kinematics is important for understanding the internal dynamics of particle collisions. Here, we present new results aiming to an efficient reconstruction of parton collisions using machine-learning techniques. By simulating the collider events, we related experimentally-accessible quantities with the momentum fractions of the involved partons. We used photon-hadron production to exploit the cleanliness of the photon signal, including up to NLO QCD-QED corrections. Neural networks led to an outstanding reconstruction efficiency, suggesting a powerful strategy for unveiling the behaviour of the fundamental bricks of matter in high-energy collisions.