Metaheuristic optimization of hybrid silicon nitride grating couplers

Grating couplers are essential building blocks to form low-loss photonic chip interfaces. Optical coupling between submicrometric waveguides and standard optical fibers remains a practical hurdle, because of geometrical, material, and modal mismatches. Grating couplers on low-index contrast platforms like silicon nitride (Si₃N₄) suffer from low directionality and poor fiber-to-grating field overlap, thus overall efficiency is limited. To address this, Si₃N₄ couplers with high-index overlays are appealing solution to improve coupling performance, yet with cost-effective fabrication. However, adding extra layers increases the design complexity, resulting in unintuitive operation and time-consuming manual device optimization. To overcome this, machine learning (ML) optimization emerges as an attractive lever to design integrated photonic devices. In this work, we present a comparative study of three metaheuristic optimization techniques - particle swarm optimization (PSO), gray wolf optimization (GWO), and genetic algorithm (GA) – to enhance the coupling performance in hybrid α-Si/SiN grating couplers. The devices are studied for transverse electric (TE) polarization at telecom waveband, centered around 1550 nm wavelength. Employing metaheuristic optimization with Ansys Lumerical finite difference time domain (FDTD) solver, we obtained sub-decibel fiber-chip coupling loss (<1 dB). Proposed strategy presents an effective design approach to develop low-loss and scalable grating couplers on hybrid Si₃N₄ platform for telecom applications.