https://doi.org/10.1140/epjp/s13360-026-07556-1
Regular Article
Leptoquark searches at TeV scale using neural networks at the hadron collider
1
Federal Urdu University of Arts, Science and Technology, Islamabad, Pakistan
2
Riphah International University, Islamabad, Pakistan
3
Department of Physics, Sang-Ho College, Konkuk University, 05029, Seoul, South Korea
4
International Islamic University, Islamabad, Pakistan
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
b
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
25
November
2025
Accepted:
7
March
2026
Published online:
16
April
2026
Abstract
Several discrepancies in the decay of B-meson decay have drawn a lot of interest in leptoquarks (LQ), making them an exciting discovery. The current investigation aims to discover the pair-production of leptoquarks that links strongly to the third generation of quarks and leptons at the center of mass energy 
= 14 TeV via proton-proton collisions at the Large Hadron Collider (LHC). Based on the lepton-quark coupling parameters and branching fractions, we separated our search into various benchmark points. The leading order (LO) signals and background processes are generated, while parton showering and hadronization are also performed to simulate the detector effects. This article examines the hadronic and neutrino decay modes of Leptoquark at 1500 LQ mass. We analyze the signal significance at integrated luminosities 300, 1000, and 3000 fb−1 for cut-based analysis. The comprehensive analysis of cut based analysis of hadronic (BP1) decay as well as 2b+MET channel provides a significance of 
and 
at a typical point of 1500 GeV and 3000 fb−1. We apply four distinct classifiers available in multivariate analysis (MVA) algorithms at the same mass and luminosity to increase sensitivity. The hadronic (BP1) channel significance is increased to 
using the MVA method( BDT), indicating a significant improvement. The 2b+MET decay is consistently more significant, 
(BDT) than the hadronic mode across all benchmarks. Our results demonstrate how well machine learning methods might enhance the possibility of discovering scalar leptoquarks during present and next LHC operations.
Mathematics Subject Classification: 12.60.Fr / 14.80.Fd
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2026
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
