Physics-informed neural networks for inverse problems in nano-optics and metamaterials

TL;DR

This paper demonstrates the use of physics-informed neural networks (PINNs) to solve inverse scattering problems in nano-optics and metamaterials, enabling more accurate design of nanostructures by accounting for complex physical effects.

Contribution

It introduces mesh-free PINNs for retrieving effective permittivity in complex nano-optic systems, validated by FEM simulations, advancing inverse problem solutions in nanophotonics.

Findings

PINNs successfully retrieve permittivity parameters in complex systems

Method validated against FEM simulations

Enables design of novel nanostructures considering finite-size effects

Abstract

In this paper we employ the emerging paradigm of physics-informed neural networks (PINNs) for the solution of representative inverse scattering problems in photonic metamaterials and nano-optics technologies. In particular, we successfully apply mesh-free PINNs to the difficult task of retrieving the effective permittivity parameters of a number of finite-size scattering systems that involve many interacting nanostructures as well as multi-component nanoparticles. Our methodology is fully validated by numerical simulations based on the Finite Element Method (FEM). The development of physics-informed deep learning techniques for inverse scattering can enable the design of novel functional nanostructures and significantly broaden the design space of metamaterials by naturally accounting for radiation and finite-size effects beyond the limitations of traditional effective medium theories.