A Neural-Network Extraction of Unpolarised Transverse-Momentum-Dependent Distributions

TL;DR

This paper demonstrates that neural networks can effectively extract unpolarised transverse-momentum-dependent distributions from experimental data, surpassing traditional methods in accuracy and paving the way for advanced hadronic structure analysis.

Contribution

It introduces a neural-network-based approach for extracting TMDs from Drell-Yan data, showing improved data description over traditional parametrisations.

Findings

Neural networks outperform traditional parametrisations in data fitting.

First extraction of unpolarised TMDs using neural networks.

Establishes feasibility of machine learning for multi-dimensional hadronic structure analysis.

Abstract

We present the first extraction of transverse-momentum-dependent distributions of unpolarised quarks from experimental Drell-Yan data using neural networks to parametrise their nonperturbative part. We show that neural networks outperform traditional parametrisations providing a more accurate description of data. This work establishes the feasibility of using neural networks to explore the multi-dimensional partonic structure of hadrons and paves the way for more accurate determinations based on machine-learning techniques.