Wave Interpolation Neural Operator: Interpolated Prediction of Electric Fields Across Untrained Wavelengths

Joonhyuk Seo, Chanik Kang, Dongjin Seo, Haejun Chung

Keywords: surrogate solver, neural operator, interpolation, wavelength, meta optics

TL;DR: WINO is a novel surrogate solver that enables efficient and accurate electric field predictions across a continuous spectrum of broadband wavelengths, outperforming traditional methods in speed and accuracy.

Abstract: Existing surrogate solvers are limited to performing inference at fixed simulation conditions, such as wavelengths, and require retraining for different conditions. To address this, we propose Wave Interpolation Neural Operator (WINO), a novel surrogate solver enabling simulation condition interpolation across a continuous spectrum of broadband wavelengths. WINO introduces the Fourier Group Convolution Shuffling operator and a new conditioning method to efficiently predict electric fields from both trained and untrained wavelength data, achieving significant improvements in parameter efficiency and spectral interpolation performance.

Submission Number: 8