POST: Photonic Swin Transformer for Automated and Efficient Prediction of PCSEL

TL;DR

POST is a photonic transformer model that rapidly and accurately predicts optical properties of PCSELs, significantly reducing simulation costs and enabling efficient design and optimization of complex photonic structures.

Contribution

This work introduces POST, a Vision Transformer-based model that predicts photonic crystal properties with high speed and accuracy, surpassing traditional simulation methods.

Findings

Achieves R-squared of 0.909 for Quality Factor prediction.

Predicts nearly 5,000 structures per second.

Reduces simulation costs and accelerates photonic design processes.

Abstract

This work designs a model named POST based on the Vision Transformer (ViT) approach. Across single, double, and even triple lattices, as well as various non-circular complex hole structures, POST enables prediction of multiple optical properties of photonic crystal layers in Photonic Crystal Surface Emitting Lasers (PCSELs) with high speed and accuracy, without requiring manual intervention, which serves as a comprehensive surrogate for the optical field simulation. In the predictions of Quality Factor (Q) and Surface-emitting Efficiency (SE) for PCSEL, the R-squared values reach 0.909 and 0.779, respectively. Additionally, it achieves nearly 5,000 predictions per second, significantly lowering simulation costs. The precision and speed of POST predictions lay a solid foundation for future ultra-complex model parameter tuning involving dozens of parameters. It can also swiftly meets designers' ad-hoc requirements for evaluating photonic crystal properties. The database used for training the POST model is derived from predictions of different photonic crystal structures using the Coupled-Wave Theory (CWT) model. This dataset will be made publicly available to foster interdisciplinary research advancements in materials science and computer science.