Bidirectional Adversarial Autoencoders for the design of Plasmonic Metasurfaces
This work addresses a specific challenge in photonic metasurface design for applications in advanced optics, representing an incremental improvement over prior methods.
The paper tackled the problem of designing photonic metasurfaces by predicting topology from photoluminescent spectra, where existing methods often fail to generate structures with multiple peaks; the proposed Bidirectional Adversarial Autoencoder successfully generated such structures in several cases.
Deep Learning has been a critical part of designing inverse design methods that are computationally efficient and accurate. An example of this is the design of photonic metasurfaces by using their photoluminescent spectrum as the input data to predict their topology. One fundamental challenge of these systems is their ability to represent nonlinear relationships between sets of data that have different dimensionalities. Existing design methods often implement a conditional Generative Adversarial Network in order to solve this problem, but in many cases the solution is unable to generate structures that provide multiple peaks when validated. It is demonstrated that in response to the target spectrum, the Bidirectional Adversarial Autoencoder is able to generate structures that provide multiple peaks on several occasions. As a result the proposed model represents an important advance towards the generation of nonlinear photonic metasurfaces that can be used in advanced metasurface design.