Improving conditional generative adversarial networks for inverse design of plasmonic structures

TL;DR

This paper enhances conditional GANs for inverse nanophotonic design, significantly improving accuracy and training speed, enabling more efficient creation of plasmonic structures based on spectral data.

Contribution

Introducing label projection and a novel embedding network into conditional GANs to improve inverse design performance and training efficiency for plasmonic nanostructures.

Findings

Error estimates reduced by an order of magnitude

Training converges over three times faster

Achieves comparable or better spectral predictions

Abstract

Deep learning has emerged as a key tool for designing nanophotonic structures that manipulate light at sub-wavelength scales. We investigate how to inversely design plasmonic nanostructures using conditional generative adversarial networks. Although a conventional approach of measuring the optical properties of a given nanostructure is conceptually straightforward, inverse design remains difficult because the existence and uniqueness of an acceptable design cannot be guaranteed. Furthermore, the dimensionality of the design space is often large, and simulation-based methods become quickly intractable. Deep learning methods are well-suited to tackle this problem because they can handle effectively high-dimensional input data. We train a conditional generative adversarial network model and use it for inverse design of plasmonic nanostructures based on their extinction cross section spectra. Our main result shows that adding label projection and a novel embedding network to the conditional generative adversarial network model, improves performance in terms of error estimates and convergence speed for the training algorithm. The mean absolute error is reduced by an order of magnitude in the best case, and the training algorithm converges more than three times faster on average. This is shown for two network architectures, a simpler one using a fully connected neural network architecture, and a more complex one using convolutional layers. We pre-train a convolutional neural network and use it as surrogate model to evaluate the performance of our inverse design model. The surrogate model evaluates the extinction cross sections of the design predictions, and we show that our modifications lead to equally good or better predictions of the original design compared to a baseline model. This provides an important step towards more efficient and precise inverse design methods for optical elements.