Accelerated Time-Domain Simulation of Complex Photonic Structures with a Data-Aware Fourier Neural Operator

TL;DR

This paper introduces a Data-Aware Fourier Neural Operator that accelerates electromagnetic time-domain simulations in complex photonic structures, achieving significant speedups while maintaining high accuracy, and generalizes well to complex geometries.

Contribution

It presents a novel neural operator model that efficiently predicts electromagnetic field evolution and generalizes to complex geometries, improving simulation speed and accuracy.

Findings

Achieves 11x speedup over traditional methods.

Maintains about 95% accuracy across the C-band.

Generalizes well to complex and randomized geometries.

Abstract

Efficient and accurate time-domain simulation of electromagnetic fields in complex photonic devices is critical for designing broadband and ultrafast optical components, yet it is often limited by the high computational cost of conventional numerical methods like FDTD. While machine learning approaches show promise in accelerating these simulations, existing models still struggle to simultaneously capture the dynamic field evolution and generalize to complex geometries. In this paper, we introduce a Data-Aware Fourier Neural Operator (DA-FNO) as an innovative neural operator for solving electromagnetic simulations. Applied autoregressively, the model iteratively predicts the time-domain evolution of all field components and automatically terminates upon energy convergence. Our model not only generalizes to complex and randomized geometries but also shows good predictive consistency across the optical C-band (1530-1565nm) when evaluated on the test set. In a representative configuration, it achieves an 11* speedup over conventional methods while maintaining about 95% accuracy across the C-band. This approach provides a new pathway for C-band photonic simulations, potentially facilitating the research, development, and inverse design of novel photonic devices.