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.
@article{arxiv.2502.04166,
title = {A Neural-Network Extraction of Unpolarised Transverse-Momentum-Dependent Distributions},
author = {Alessandro Bacchetta and Valerio Bertone and Chiara Bissolotti and Matteo Cerutti and Marco Radici and Simone Rodini and Lorenzo Rossi},
journal= {arXiv preprint arXiv:2502.04166},
year = {2025}
}