Abstract In the grand tapestry of Physics, the magnetic monopole is a holy grail. Therefore, numerous efforts
are underway in search of this hypothetical particle at CMS, ATLAS and MoEDAL experiments of LHC
by employing different production mechanisms. The cornerstone of our comprehension of monopoles lies
in Dirac’s theory which outlines their characteristics and dynamics. Within this theoretical framework, an
effective U (1) gauge field theory, derived from conventional models, delineates the interaction between spin
magnetically-charged fields and ordinary photons under electric-magnetic dualization.
The focus of this paper is the production of magnetic monopoles through Drell-Yan and the Photon-Fusion
mechanisms to generate velocity-dependent scalar, fermionic, and vector monopoles of spin angular mo-
mentum 0, 1
2 , 1 respectively at LHC. A computational study compares the monopole pair-production cross-
sections for both methods at various center-of-mass energies (√s) with different magnetic dipole moments.
The comparison of kinematic distributions of monopoles at Parton and reconstructed level are demonstrated
for both DY and PF mechanisms.
Extracted results showcase how modern machine-learning techniques can be used to study the production
of magnetic monopoles at the Future proton-proton Particle Colliders at 100 TeV. We demonstrate the ob-
servability of magnetic monopoles against the most relevant Standard Model background using multivariate
methods such as Boosted Decision Trees (BDT), Likelihood, and Multilayer Perceptron (MLP). This study
compares the performance of these classifiers with traditional cut-based and counting approaches, proving
the superiority of our methods