Saved in:
Bibliographic Details
Main Authors: Park, Junho, Kim, Taehan, Ali, Mohammad, Liang, Di
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.22176
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915824036478976
author Park, Junho
Kim, Taehan
Ali, Mohammad
Liang, Di
author_facet Park, Junho
Kim, Taehan
Ali, Mohammad
Liang, Di
contents As an increasingly powerful technique in integrated photonics, inverse design uses optimization algorithms to automatically create compact, high-performance photonic structures, often yielding non-intuitive layouts far more compact than conventional designs. While adjoint-based inverse design is a prominent optimization method, the resulting free-form layouts are difficult to interpret or diagnose under fabrication variability, even for experienced photonic device designers. We present an experimentally validated interpretability workflow that produces pixel-level sensitivity maps directly on the binary mask of an inverse-designed device. Using wavelength-division demultiplexers (WDMs) at 1310/1550 nm as examples, we train a lightweight convolutional surrogate to regress figures of merit (FoMs) and apply Integrated Gradients (IG) to attribute predicted transmission to individual pixels. We demonstrate that high-attribution hotspots correspond to physically meaningful substructures, such as splitter hubs and high-curvature edges. Experimental results show that controlled perturbations in these high-sensitivity regions result in up to an 11x higher excess insertion loss compared to perturbations in non-sensitive regions, consistent with full-wave simulations. This approach adds a practical explainability layer to existing pipelines, offering a clear pathway for foundry-compatible design-rule checking and fabrication-aware constraint allocation without modifying the underlying electromagnetic solver.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22176
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpretable Geometry Sensitivity for Inverse Design of Integrated Photonics
Park, Junho
Kim, Taehan
Ali, Mohammad
Liang, Di
Optics
Computational Physics
As an increasingly powerful technique in integrated photonics, inverse design uses optimization algorithms to automatically create compact, high-performance photonic structures, often yielding non-intuitive layouts far more compact than conventional designs. While adjoint-based inverse design is a prominent optimization method, the resulting free-form layouts are difficult to interpret or diagnose under fabrication variability, even for experienced photonic device designers. We present an experimentally validated interpretability workflow that produces pixel-level sensitivity maps directly on the binary mask of an inverse-designed device. Using wavelength-division demultiplexers (WDMs) at 1310/1550 nm as examples, we train a lightweight convolutional surrogate to regress figures of merit (FoMs) and apply Integrated Gradients (IG) to attribute predicted transmission to individual pixels. We demonstrate that high-attribution hotspots correspond to physically meaningful substructures, such as splitter hubs and high-curvature edges. Experimental results show that controlled perturbations in these high-sensitivity regions result in up to an 11x higher excess insertion loss compared to perturbations in non-sensitive regions, consistent with full-wave simulations. This approach adds a practical explainability layer to existing pipelines, offering a clear pathway for foundry-compatible design-rule checking and fabrication-aware constraint allocation without modifying the underlying electromagnetic solver.
title Interpretable Geometry Sensitivity for Inverse Design of Integrated Photonics
topic Optics
Computational Physics
url https://arxiv.org/abs/2510.22176