Search for Long-lived Particles at Future Lepton Colliders Using Deep Learning Techniques

TL;DR

This paper demonstrates that deep learning techniques significantly enhance the detection efficiency of long-lived particles at future lepton colliders, achieving near-perfect background rejection and setting new sensitivity limits for Higgs decays into LLPs.

Contribution

It introduces a deep neural network approach for LLP searches at lepton colliders, improving signal efficiency and background rejection in Higgs decay analyses.

Findings

Deep neural networks achieve up to 95% signal efficiency.

Background rejection is effectively complete.

Higgs decay branching ratio sensitivity reaches 1.0 x 10^{-6}.

Abstract

Long-lived particles (LLPs) provide an unambiguous signal for physics beyond the Standard Model (BSM). They have a distinct detector signature, with decay lengths corresponding to lifetimes of around nanoseconds or longer. Lepton colliders allow LLP searches to be conducted in a clean environment, and such searches can reach their full physics potential when combined with machine learning (ML) techniques.This experimental study, utilizing comprehensive full simulation data samples, focuses on LLP searches resulting from Higgs decay in $e^+e^-\to ZH$. We demonstrate that, by employing deep neural network approaches the LLP signal efficiency can be improved up to 95\% for an LLP mass around 50 GeV and a lifetime of approximately 1 nanosecond, while rejecting all SM backgrounds. Furthermore, the signal sensitivity for the branching ratio of Higgs decaying into LLPs reaches a state-of-art limit of $1.0 \times 10^{-6}$ with a statistics of $4 \times 10^{6}$ Higgs.