Improving the performance of optical inverse design of multilayer thin films using CNN-LSTM tandem neural networks

TL;DR

This paper enhances optical inverse design of multilayer thin films by developing a CNN-LSTM tandem neural network, improving accuracy and efficiency over traditional methods and other neural network configurations.

Contribution

It introduces a novel CNN-LSTM tandem neural network architecture for inverse design, combining strengths of CNN and LSTM to optimize accuracy and speed.

Findings

LSTM-LSTM TNN achieves highest accuracy but slowest training.

CNN-LSTM TNN offers the best balance of accuracy and speed.

Proposed method reduces reliance on extensive simulations.

Abstract

Optical properties of thin film are greatly influenced by the thickness of each layer. Accurately predicting these thicknesses and their corresponding optical properties is important in the optical inverse design of thin films. However, traditional inverse design methods usually demand extensive numerical simulations and optimization procedures, which are time-consuming. In this paper, we utilize deep learning for the inverse design of the transmission spectra of SiO2/TiO2 multilayer thin films. We implement a tandem neural network (TNN), which can solve the one-to-many mapping problem that greatly degrades the performance of deep-learning-based inverse designs. In general, the TNN has been implemented by a back-to-back connection of an inverse neural network and a pre-trained forward neural network, both of which have been implemented based on multilayer perceptron (MLP) algorithms. In this paper, we propose to use not only MLP, but also convolutional neural network (CNN) or long short-term memory (LSTM) algorithms in the configuration of the TNN. We show that an LSTM-LSTM-based TNN yields the highest accuracy but takes the longest training time among nine configurations of TNNs. We also find that a CNN-LSTM-based TNN will be an optimal solution in terms of accuracy and speed because it could integrate the strengths of the CNN and LSTM algorithms.