Will Accurate Fields Mislead Photonic Design? FromGlobal Accuracy to Port Readout

2026-06-01

AI Summary

This work addresses a critical limitation in existing neural surrogate models for photonic device simulation: despite accurately predicting global optical fields, they often misrank device performance due to neglecting local interference effects and window-integrated readout mechanisms at ports. To resolve this, the authors propose the Propagation-Aligned Neural Operator (PaNO), which explicitly encodes boundary geometry, transverse modes, axial propagation, and intermodal coupling in its latent representation through decoupled field modeling, intermediary propagation, and port readout stages. Furthermore, an output-aware feedback mechanism, PaNO-R2, is introduced to refine residual fields in port regions. Evaluated on a 15-wavelength-tunable 3×3 multimode interferometer benchmark, PaNO reduces port power error from 0.2018 to 0.0739, while PaNO-R2 further decreases power and output profile errors by 72.7% and 72.5%, respectively, revealing for the first time a fundamental inconsistency between global field accuracy and design-relevant port performance.

Abstract

Neural field surrogates can accelerate photonic design loops, but a surrogate that looks accurate in global field error can still mis-rank candidate devices when the final decision depends on localized output-port readouts. This risk is acute in propagation-dominated MMI splitters and couplers, where port power, splitting, phase, and coupling are determined by accumulated modal interference and output-window aggregation rather than by average field similarity alone. We study this field-to-design mismatch through a Field/Mediator/Readout view that separates dense complex-field error from propagation-profile and output-window errors before port aggregation. To align the surrogate with this chain, we propose PaNO, a propagation-aligned neural operator that keeps the full-field prediction interface while organizing latent states around local boundary structure, transverse modal content, axial propagation, and cross-mode interaction. We also evaluate PaNO-R2, an output-aware feedback variant for residual field components near the port region. On a 15-wavelength tunable $3{\times}3$ MMI benchmark with 4608 held-out fields, PaNO lowers NeurOLight's port-power error from 0.2018 to 0.0739 despite slightly higher cMAE, showing that global field accuracy alone is not sufficient for design-relevant readout fidelity. PaNO-R2 attains the best cMAE, propagation-profile error, output-profile error, and port-power error, reducing NeurOLight's port-power and output-profile errors by 72.7\% and 72.5\%.

Problem

• photonic design
• neural field surrogate
• port readout
• field-to-design mismatch
• output-port accuracy

Innovation

• neural operator
• photonic design
• port readout
• field-to-design mismatch
• propagation alignment