Broadband Electromagnetic Field Prediction at Unseen Wavelengths via Physics‐Guided Neural Operators
Joonhyuk Seo, Chanik Kang, Dongjin Seo, Haejun Chung · 2026
Read Broadband Electromagnetic Field Prediction at Unseen Wavelengths via Physics‐Guided Neural Operators by Joonhyuk Seo, Chanik Kang, Dongjin Seo, Haejun Chung (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13642526.txt.
Description
Seo and colleagues present in 2026 a physics-guided neural operator. This machine learning model predicts how electromagnetic fields spread through tiny optical devices at any wavelength in the visible band, even wavelengths it never saw in training. Slow full-wave simulations are a bottleneck in designing such devices.
Two ideas drive the model. Spectral consistency ties how fields change with wavelength to spatial frequency, and a conditional embedding feeds the model a refined wave prior for the requested wavelength. Tested on three platforms, a single-layer metalens, a five-layer spectrum splitter, and a freeform waveguide, the solver cut field prediction error sharply. Against earlier operator-learning methods the cut reached up to about four fifths on the simplest platform. It runs about forty-two times faster than a standard numerical solver with far fewer parameters.
Catalog record
| CREATOR | Joonhyuk Seo, Chanik Kang, Dongjin Seo, Haejun Chung |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |