Abstract
We demonstrate that embedding physics-driven constraints into machine learning process can dramatically improve accuracy and generalizability of the resulting model. Physics-informed learning is illustrated on the example of analysis of optical modes propagating through a spatially periodic composite. The approach presented can be readily utilized in other situations mapped onto an eigenvalue problem, a known bottleneck of computational electrodynamics. Physics-informed learning can be used to improve machine-learning-driven design, optimization, and characterization, in particular in situations where exact solutions are scarce or are slow to come up with.