SageNet: Fast Neural Network Emulation of the Stiff-amplified Gravitational Waves from Inflation

Understand

Accurate modeling of the inflationary gravitational waves (GWs) requires time-consuming, iterative numerical integrations of differential equations to take into account their backreaction on the expansion history.

• To improve computational efficiency while preserving accuracy, we present SageNet (Stiff-Amplified Gravitational-wave Emulator Network), a deep learning framework designed to replace conventional numerical solvers.
• SageNet employs a Long Short-Term Memory architecture to emulate the present-day energy density spectrum of the inflationary GWs with possible stiff amplification, $\Omega_\mathrm{GW}(f)$.
• Trained on a data set of 25,689 numerically generated solutions, SageNet allows accurate reconstructions of $\Omega_\mathrm{GW}(f)$ and generalizes well to a wide range of cosmological parameters; 89.3% of the test emulations with randomly distributed parameters exhibit errors of under 4%.