Deep-neural-network extraction of unpolarized transverse-momentum-dependent parton distributions in bT space from Drell-Yan data
Abstract
We present a physics-informed deep-neural-network extraction of unpolarized transverse-momentum-dependent parton distribution functions (TMDPDFs) in impact-parameter space from Drell--Yan data. The perturbative contribution is computed with a resummed W term using N3LL evolution, strict-NLO hard and operator-product-expansion matching, and smooth profile scales at small and large bT. A compact feature-wise linear modulation network learns only a shared nonperturbative factor FNP(x,bT); the collinear PDFs, hard factor, evolution kernel, matching coefficients, and Fourier--Bessel transform remain fixed. The primary result is a smooth light-flavor bT-space TMD ensemble and its cross-section-level validation. The reported kT distributions are regularized finite-bT Hankel transforms, not independent momentum-space fits. As a separate robustness test, a smooth finite-Y transition is applied to 24 additional Tevatron points extending to qT/Q≃0.30. The nominal 329-point fit is unchanged, and the results remain stable when FNP is held fixed while the transition profile is varied. An independent 122-bin Tevatron N3LL+NNLO W+Y grid provides a direct perturbative benchmark. A separate W+Y candidate using the specified non-LHCb finite-Y inputs is retained as an identifiability study.
Related
- Extraction of transverse-momentum-dependent helicity distributions of the nucleon
- Gravitational transverse momentum dependent distributions for the gluons
- Recent Advances in Transverse-Momentum--Dependent Distributions in Lattice QCD
- Transverse momentum dependent parton distributions at small x
- Energy-momentum tensor at small x from gravitational transverse-momentum distributions
BibTeX
@misc{fernando2026deepneuralnetwork,
title = {{Deep-neural-network extraction of unpolarized transverse-momentum-dependent parton distributions in $b_T$ space from Drell-Yan data}},
author = {I. P. Fernando and D. Keller},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.27907},
eprint = {2608.27907},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.27907},
}
RIS
TY - UNPB
TI - Deep-neural-network extraction of unpolarized transverse-momentum-dependent parton distributions in b_T space from Drell-Yan data
AU - I. P. Fernando
AU - D. Keller
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.27907
UR - https://arxiv.org/abs/2608.27907
AB - We present a physics-informed deep-neural-network extraction of unpolarized transverse-momentum-dependent parton distribution functions (TMDPDFs) in impact-parameter space from Drell--Yan data. The perturbative contribution is computed with a resummed W term using N^3LL evolution, strict-NLO hard and operator-product-expansion matching, and smooth profile scales at small and large b_T. A compact feature-wise linear modulation network learns only a shared nonperturbative factor F_NP(x,b_T); the collinear PDFs, hard factor, evolution kernel, matching coefficients, and Fourier--Bessel transform remain fixed. The primary result is a smooth light-flavor b_T-space TMD ensemble and its cross-section-level validation. The reported k_T distributions are regularized finite-b_T Hankel transforms, not independent momentum-space fits. As a separate robustness test, a smooth finite-Y transition is applied to 24 additional Tevatron points extending to q_T/Q≃0.30. The nominal 329-point fit is unchanged, and the results remain stable when F_NP is held fixed while the transition profile is varied. An independent 122-bin Tevatron N^3LL+NNLO W+Y grid provides a direct perturbative benchmark. A separate W+Y candidate using the specified non-LHCb finite-Y inputs is retained as an identifiability study.
ER -