Deep learning based inverse design of nonreciprocal multilayer photonic structures

Abstract Nonreciprocal structures play an important role in optical physics and applications. Conventional approaches for designing nonreciprocal optical structures rely heavily on extensive numerical simulation and parameter tuning, leading to high computational cost and low efficiency. Here, we apply deep learning to the design of nonreciprocal multilayer photonic structures. Three neural-network models—a forward neural network (FNN), an inverse design network (IDN), and a variational autoencoder (VAE)—are employed to learn the complex mapping between structural/material parameters and nonreciprocal spectral characteristics. We show that the FNN can rapidly and accurately predict the nonreciprocal electromagnetic response of a given structure, achieving a mean squared error (MSE) of 0.0049 on the test dataset and about 58 times faster than the conventional transfer matrix method. The IDN can directly generate suitable structural parameters for target spectral responses with a MSE of 0.0074. Furthermore, the VAE can generate band-limited inverse design under practical performance constraints, facilitating efficient exploration of multiple feasible structures that meet different threshold requirements within specified frequency bands, such as structures with differential transmittance above 0.83 over 12–14 GHz. Our work highlights the potential of deep learning for the advanced design of nonreciprocal optical structures and devices.