AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation

Jiaqi Gu, Zhengqi Gao, Chenghao Feng, Hanqing Zhu, Ray Chen, Duane S Boning, David Z. Pan

NeurIPS 2022 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural operators for general geometries · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use NeurOLight instead of prior neural modelsPhotonic device field prediction · Tunable MMI and Etched MMItest prediction error: 53.8% lower prediction errorImproved
use NeurOLight instead of other prediction modelsPhotonic device field prediction · Etched MMIprediction error: 42% lower errorImproved
use superposition-based mixupNeurOLight · Multi-source inference on MMI devicesprediction fidelityImproved
use only single-source training examples without mixup (ablation)NeurOLight · Multi-source inference on MMI devicesgeneralizationHurt
use superposition-based mixup with reduced training dataNeurOLight · MMI devices with 10% training datageneralization: 10% training dataImproved
replace fixed-domain encoding with joint PDE encoding using permittivity and wave prior (ablation)NeurOLight · Unseen simulation settingstest errorImproved
add raw wavelength and domain information to the joint PDE representation (ablation)NeurOLight · Photonic device simulationtest errorHurt
use raw PDE parameters rather than a compact joint representation (ablation)NeurOLight · Photonic device simulationtest errorHurt
use inadequate Fourier modes (ablation)NeurOLight · Terahertz optical field predictiontest errorHurt
use all Fourier modes (ablation)NeurOLight · Photonic device simulationtest errorHurt
add a parallel convolution path (ablation)NeurOLight · Photonic device simulationruntime: 20% runtime penaltyHurt
use a convolutional FFN instead of simple BatchNorm-GELU (ablation)NeurOLight · Photonic device simulationtest errorImproved

Later papers that compared with this method

1 later accepted paper reports NeurOLight as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy