AI assisted optimization of integrated waveguide polarizers containing 2D reduced graphene oxide

TL;DR

This paper presents a machine learning framework using neural networks to efficiently optimize the design of graphene oxide-based waveguide polarizers, significantly reducing computational time while maintaining high accuracy.

Contribution

The study introduces a neural network-based approach to rapidly predict polarizer performance across large parameter spaces, improving design efficiency over traditional simulation methods.

Findings

Reduces computational time by over 4 orders of magnitude.

Achieves prediction accuracy with an average deviation below 0.05.

Enables high-resolution optimization of waveguide polarizer designs.

Abstract

Reduced graphene oxide (rGO) exhibits strong anisotropic light absorption and high compatibility with photonic integrated chips, making it a promising material for implementing high performance onchip polarization selective devices. The performance of rGO integrated waveguide polarizers is highly dependent on the waveguide geometry, and achieving optimal performance requires exploring a large parameter space, making conventional mode simulation methods computationally demanding. Here, we propose and demonstrate a machine learning framework based on fully connected neural networks (FCNNs) to map the dependence of the polarizer figure of merit (FOM) on the waveguide geometry. Once trained by using a small dataset of low resolution mode simulation results, the FCNN framework can rapidly and accurately predict FOM values across a large structural parameter space with high resolution. Results show that this method can reduce overall computing time by more than 4 orders of magnitude as compared to the mode simulation methods, and achieve high prediction accuracy with an average deviation (AD) below 0.05. These results highlight the FCNN based machine learning framework as an efficient tool for the design and optimization of rGO integrated waveguide polarizers.