AI based design of 2D material integrated optical polarizers

Abstract

On-chip integration of highly anisotropic two-dimensional (2D) materials offers new opportunities for realizing high performance polarization selective devices. Obtaining optimized designs for such devices requires extensively sweeping large parameter spaces, which in conventional approaches relies on massive mode simulations that demand considerable computational resources. Here, we address this limitation by developing a machine learning (ML) model based on fully connected neural networks (FCNNs). Trained by using mode simulation results for low resolution structural parameters, the FCNN model can accurately predict polarizer figures of merits (FOMs) for high resolution parameters and rapidly map the global variation trend across the entire parameter space. We test the performance of the FCNN model using two types of polarizers with 2D graphene oxide (GO) and molybdenum disulfide (MoS2). Results show that, compared to conventional mode simulation approach, our approach can not only reduce the overall computing time by about 4 orders of magnitude, but also achieve highly accurate FOM predictions with an average deviation of less than 0.04. In addition, the measured FOM values for the fabricated devices show good agreement with the predicted ones, with discrepancies remaining below 0.2. These results validate artificial intelligence (AI) as an effective approach for designing and optimizing 2D-material based optical polarizers with high efficiency.

33 pages, 5 figures, 74 references

References in corpus (20)

• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Outlook for inverse design in nanophotonics
• 11 TeraFLOPs per second photonic convolutional accelerator for deep learning optical neural networks
• A Generative Model for Inverse Design of Metamaterials
• Electro-optically tunable microring resonators in lithium niobate
• Deep neural networks for the evaluation and design of photonic devices
• Deep learning in nano-photonics: inverse design and beyond
• Integrated polarizers based on graphene oxide in waveguides and ring resonators
• Chalcogenide Glass-on-Graphene Photonics
• Sagnac interference in integrated photonics for reflection mirrors, gyroscopes, filters, and wavelength interleavers
• Inverse-Designed Diamond Photonics
• High-responsivity graphene photodetectors integrated on silicon microring resonators
• Photonic integrated circuit polarizers based on 2D materials
• Inverse-designed Silicon Carbide Quantum and Nonlinear Photonics
• Graphene oxide two dimensional films for thermo-optic photonic integrated devices
• Novel functions in silicon photonic chips incorporated with graphene oxide thin films
• Integrated nanophotonic polarizers in silicon waveguides and ring resonators using graphene oxide 2D films
• Integrated microring resonator and waveguide polarizers based on partially photo-reduced 2D graphene oxide thin films
• Soliton microcombs in X-cut LiNbO3 microresonators
• Modeling of photonic integrated resonators using advanced scattering matrix methods