Deep-learning jet flavor tagging for precision hadronic Higgs measurements at future $e^+e^-$ Higgs factories

TL;DR

This paper demonstrates that deep learning techniques significantly improve jet flavor tagging accuracy, enabling more precise measurements of Higgs decay modes at future electron-positron colliders, thereby advancing Higgs physics research.

Contribution

The study introduces advanced deep neural network taggers combined with global classifiers to enhance Higgs decay mode identification at future $e^+e^-$ colliders, achieving improved measurement precision.

Findings

Projected measurement precisions for Higgs decay modes are significantly improved.

Deep learning-based jet flavor tagging enhances sensitivity to rare Higgs decays.

The approach achieves about 42% and 26% improvements over previous methods for $H\to c\bar c$ and $H\to gg$.

Abstract

Precise measurements of Higgs decays into quarks and gluons are essential for probing the Yukawa couplings of the Higgs boson and testing the flavor structure of the Standard Model. We investigate the process $e^+e^- \to ZH$ at $\sqrt{s}=240~\mathrm{GeV}$ at a future $e^+e^-$ Higgs factory, taking the CEPC design as a benchmark. The analysis focuses on events with $Z\to\nu\bar\nu$ and hadronic Higgs decays $H\to b\bar b$, $c\bar c$, $s\bar s$ and $gg$. Jet flavor is identified using state-of-the-art particle-level deep neural network taggers (ParticleNet, Particle Transformer and More-Interaction Particle Transformer), whose per-jet outputs are combined with global event observables in a two-stage analysis employing XGBoost classifiers to separate the four Higgs decay modes from the dominant two- and four-fermion Standard Model backgrounds. Assuming an integrated luminosity of $20\,\mathrm{ab}^{-1}$, we obtain projected relative precision on $\sigma(ZH)\times\mathrm{Br}(H\to X)$ of 0.18% for $X=b\bar b$, 1.07% for $c\bar c$, 0.52% for $gg$ and 78% for $s\bar s$. Compared with the CEPC published results, the precisions for $H\to c\bar c$ and $H\to gg$ are improved by about $42%$ and $26%$, respectively. For $H\to s\bar s$ we present a quantitative sensitivity estimation corresponding to a statistical significance of about $1.3\sigma$. These results highlight the potential of deep-learning-based jet flavor tagging for precision studies of Higgs decays at future $e^+e^-$ Higgs factories.