Improving heavy Dirac neutrino prospects at future hadron colliders using machine learning

Abstract

Abstract In this work, by using the machine learning methods, we study the sensitivities of heavy pseudo-Dirac neutrino N in the inverse seesaw at the high-energy hadron colliders. The production process for the signal is pp → ℓ → 3ℓ + E T miss $$ {E}_T^{\mathrm{miss}} $$ , while the dominant background is pp → WZ → 3ℓ + E T miss $$ {E}_T^{\mathrm{miss}} $$ . We use either the Multi-Layer Perceptron or the Boosted Decision Tree with Gradient Boosting to analyse the kinematic observables and optimize the discrimination of background and signal events. It is found that the reconstructed Z boson mass and heavy neutrino mass from the charged leptons and missing transverse energy play crucial roles in separating the signal from backgrounds. The prospects of heavy-light neutrino mixing |V ℓN | 2 (with ℓ = e, μ) are estimated by using machine learning at the hadron colliders with s $$ \sqrt{s} $$ = 14 TeV, 27 TeV, and 100 TeV, and it is found that |V ℓN | 2 can be improved up to O $$ \mathcal{O} $$ (10 −6) for heavy neutrino mass m N = 100 GeV and O $$ \mathcal{O} $$ (10 −4) for m N = 1 TeV.

Keywords

• Specific BSM Phenomenology
• Sterile or Heavy Neutrinos