Artificial discovery of lattice models for wave transport

Wave transport devices, such as amplifiers, frequency converters, and nonreciprocal devices, are essential for modern communication, signal processing, and sensing applications. Of particular interest are traveling wave setups, which offer excellent gain and bandwidth properties. So far, the design process of traveling wave setups or, more generally, periodic structures has either relied on human ingenuity or black‑box inverse design methods. A significant challenge and opportunity is to devise automated methods that not only produce solutions but also conceptual understanding, an aspiration central to the field of artificial scientific discovery.

In the spirit of artificial scientific discovery, we present in our work [1] a new approach to automate the design of periodic coupled-mode lattices. Our approach identifies automatically the simplest lattices that achieve a desired transport functionality, and we apply it to discover new schemes for directional amplifiers, isolators, and frequency demultiplexers. Leveraging symbolic regression tools, we find closed analytical expressions that facilitate the discovery of generalizable construction rules. Moreover, we utilize important conceptual connections between the devices’ transport properties and non-Hermitian topology. The resulting structures can be implemented on a variety of platforms, including microwave, optical, and optomechanical systems.

[1] J. Landgraf, C. Wanjura, V. Peano, and F. Marquardt, arXiv:2508.10693.