Optimising simulations for diphoton production at hadron colliders using amplitude neural networks

TL;DR

This paper develops neural network-based methods to efficiently approximate matrix elements for diphoton production in high-energy collider simulations, improving computational speed and flexibility.

Contribution

It introduces a realistic neural network approach trained on one-loop amplitudes to simulate diphoton production at hadron colliders, applicable to high-multiplicity scattering processes.

Findings

Neural networks accurately approximate matrix elements for diphoton production.

The method maintains reliability under various kinematic cuts.

Significant speed-up in event simulation processes.

Abstract

Machine learning technology has the potential to dramatically optimise event generation and simulations. We continue to investigate the use of neural networks to approximate matrix elements for high-multiplicity scattering processes. We focus on the case of loop-induced diphoton production through gluon fusion and develop a realistic simulation method that can be applied to hadron collider observables. Neural networks are trained using the one-loop amplitudes implemented in the NJet C++ library and interfaced to the Sherpa Monte Carlo event generator where we perform a detailed study for $2\to3$ and $2\to4$ scattering problems. We also consider how the trained networks perform when varying the kinematic cuts effecting the phase space and the reliability of the neural network simulations.