High-Freedom Inverse Design with Deep Neural Network for Metasurface Filter in the Visible

TL;DR

This paper introduces a deep neural network-based inverse design method for metasurface filters in the visible spectrum, offering faster and more accurate device generation compared to traditional iterative approaches.

Contribution

The proposed neural network enables rapid inverse design of metasurfaces with high spectral accuracy, handling real and artificial spectra, surpassing traditional methods in speed and quality.

Findings

Faster design process than traditional methods

Ability to handle real and artificial spectra

High accuracy in spectral matching

Abstract

In order to obtain a metasurface structure capable of filtering the light of a specific wavelength in the visible band, traditional method usually traverses the space consisting of possible designs, searching for a potentially satisfying device by performing iterative calculations to solve Maxwell's equations. In this paper, we propose a neural network that can complete an inverse design process to solve the problem. Compared with the traditional method, our method is much faster while competent of generating better devices with the desired spectrum. One of the most significant advantages is that it can handle a real spectrum as well as an artificial one. Besides, our method encompasses a high degree of freedom to generate devices, ensuring their generated spectra resemble desired ones and meeting the accuracy requirements without losing practicability in the manufacturing process.