Mapping the Design Space of Photonic Topological States via Deep Learning

TL;DR

This paper introduces a deep learning framework that effectively maps the complex design space of topological states in photonic crystals, overcoming traditional optimization challenges and enabling better design of photonic topological materials.

Contribution

It develops a novel deep learning approach with specialized neural networks to accurately model and invert the design space of photonic topological states, addressing high-dimensional and non-unique mapping issues.

Findings

The framework successfully captures the complex design space.

It significantly reduces prediction errors in inverse design.

The approach outperforms conventional optimization methods.

Abstract

Topological states in photonics offer novel prospects for guiding and manipulating photons and facilitate the development of modern optical components for a variety of applications. Over the past few years, photonic topology physics has evolved and unveiled various unconventional optical properties in these topological materials, such as silicon photonic crystals. However, the design of such topological states still poses a significant challenge. Conventional optimization schemes often fail to capture their complex high dimensional design space. In this manuscript, we develop a deep learning framework to map the design space of topological states in the photonic crystals. This framework overcomes the limitations of existing deep learning implementations. Specifically, it reconciles the dimension mismatch between the input (topological properties) and output (design parameters) vector spaces and the non-uniqueness that arises from one-to-many function mappings. We use a fully connected deep neural network (DNN) architecture for the forward model and a cyclic convolutional neural network (cCNN)for the inverse model. The inverse architecture contains the pre-trained forward model in tandem, thereby reducing the prediction error significantly.