Global Inverse Design Across Multiple Photonic Structure Classes Using Generative Deep Learning

TL;DR

This paper introduces a deep learning framework that enables global inverse design of photonic structures, allowing simultaneous optimization of materials and geometries to achieve desired optical functionalities.

Contribution

It presents a conditional generative adversarial network that can identify and generate multiple design variants across different material and structural classes based on target spectra.

Findings

The model can produce multiple diverse designs with similar optical responses.

It effectively encodes material properties and geometries for inverse design.

The framework advances the ability to optimize photonic devices globally across classes.

Abstract

Understanding how nano- or micro-scale structures and material properties can be optimally configured to attain specific functionalities remains a fundamental challenge. Photonic metasurfaces, for instance, can be spectrally tuned through material choice and structural geometry to achieve unique optical responses. However, existing numerical design methods require prior identification of specific material-structure combinations, or device classes, as the starting point for optimization. As such, a unified solution that simultaneously optimizes across materials and geometries has yet to be realized. To overcome these challenges, we present a global deep learning-based inverse design framework, where a conditional deep convolutional generative adversarial network is trained on colored images encoded with a range of material and structural parameters, including refractive index, plasma frequency, and geometric design. We demonstrate that, in response to target absorption spectra, the network can identify an effective metasurface in terms of its class, materials properties, and overall shape. Furthermore, the model can arrive at multiple design variants with distinct materials and structures that present nearly identical absorption spectra. Our proposed framework is thus an important step towards global photonics and materials design strategies that can identify combinations of device categories, material properties, and geometric parameters which algorithmically deliver a sought functionality.