A Hybrid Strategy for the Discovery and Design of Photonic Structures

Metasurfaces and metamaterials are playing a growing role in the control of electromagnetic waves in the application of communication, display, and sensing technologies. However, designing photonic structures as the building blocks of these systems is typically a tedious trial-and-error process that requires extensive simulations with iterative sweeps in a multi-dimensional parameter space. To circumvent this conventional approach and substantially expedite the discovery and development of photonic structures, here we develop a framework leveraging both a deep generative model and a modified evolution strategy to automate the inverse design of engineered photonic materials and devices. The capacity of the proposed methodology is tested through the application to a case study, where metasurfaces in either continuous or discrete topologies are generated in response to customer-defined spectra at the input. Through a variational autoencoder, all potential patterns of unit structures are encoded into a continuous latent space. An evolution strategy is applied to vectors in the latent space to identify an optimized vector whose corresponding metasurface fulfills the design objective. The evaluation shows that over 95% accuracy can be achieved for all the unit patterns of the metasurfaces in the test dataset. Our scheme requires no prior knowledge of the geometry of the photonic structures, and, in principle, allows joint optimization of the dimensional parameters. As such, our work represents an efficient, on-demand, and automated approach for the inverse design of photonic structures with subwavelength features.