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

arXiv: https://arxiv.org/abs/2209.10098 · HTML: https://mlsanity.com/paper/2209.10098/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 43 references that are in the map.
- First posted on arXiv 19 Sep 2022.

## Builds on (most cited first, 16 of 16)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Neural Operator: Graph Kernel Network for Partial Differential Equations](https://mlsanity.com/paper/2003.03485/) (2020)
- [U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flow](https://mlsanity.com/paper/2109.03697/) (2021)
- [Factorized Fourier Neural Operators](https://mlsanity.com/paper/2111.13802/) (2021)
- [Multiwavelet-based Operator Learning for Differential Equations](https://mlsanity.com/paper/2109.13459/) (2021)
- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [Neuromorphic Silicon Photonic Networks](https://mlsanity.com/paper/1611.02272/) (2016)
- [CrossLight: A Cross-Layer Optimized Silicon Photonic Neural Network Accelerator](https://mlsanity.com/paper/2102.06960/) (2021)
- [Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets](https://mlsanity.com/paper/2003.13549/) (2020)
- [L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization](https://mlsanity.com/paper/2110.14807/) (2021)
- [A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning](https://mlsanity.com/paper/2111.06705/) (2021)
- [O-HAS: Optical Hardware Accelerator Search for Boosting Both Acceleration Performance and Development Speed](https://mlsanity.com/paper/2108.07538/) (2021)

## Built on by (most cited first, 17 of 17)

- [Neural Operators for Accelerating Scientific Simulations and Design](https://mlsanity.com/paper/2309.15325/) (2023)
- [Neural oscillators for generalization of physics-informed machine learning](https://mlsanity.com/paper/2308.08989/) (2023)
- [Towards General Neural Surrogate Solvers with Specialized Neural Accelerators](https://mlsanity.com/paper/2405.02351/) (2024)
- [Inverse Design in Nanophotonics via Representation Learning](https://mlsanity.com/paper/2507.00546/) (2025)
- [Separable Operator Networks](https://mlsanity.com/paper/2407.11253/) (2024)
- [PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices](https://mlsanity.com/paper/2411.03527/) (2024)
- [PIC2O-Sim: A Physics-Inspired Causality-Aware Dynamic Convolutional Neural Operator for Ultra-Fast Photonic Device FDTD Simulation](https://mlsanity.com/paper/2406.17810/) (2024)
- [MAPS: Multi-Fidelity AI-Augmented Photonic Simulation and Inverse Design Infrastructure](https://mlsanity.com/paper/2503.01046/) (2025)
- [Report for NSF Workshop on AI for Electronic Design Automation](https://mlsanity.com/paper/2601.14541/) (2026)
- [Generalizing Deep Surrogate Solvers for Broadband Electromagnetic Field Prediction at Unseen Wavelengths](https://mlsanity.com/paper/2408.02971/) (2024)
- [Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization](https://mlsanity.com/paper/2506.20056/) (2025)
- [Democratizing Electronic-Photonic AI Systems: An Open-Source AI-Infused Cross-Layer Co-Design and Design Automation Toolflow](https://mlsanity.com/paper/2601.00130/) (2025)
- [Harnessing Photonics for Machine Intelligence](https://mlsanity.com/paper/2604.10841/) (2026)
- [Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data](https://mlsanity.com/paper/2605.20514/) (2026)
- [APEX: Amplitude Anchors and Phase Priors for Target-Scarce Higher-Frequency Wave Prediction](https://mlsanity.com/paper/2605.26732/) (2026)
- [Will Accurate Fields Mislead Photonic Design? FromGlobal Accuracy to Port Readout](https://mlsanity.com/paper/2606.03038/) (2026)
- [DDSNet: Dual-domain Symmetry-aware Network for PCSEL Property Prediction](https://mlsanity.com/paper/2607.24785/) (2026)

## Abstract (arXiv)

Optical computing is an emerging technology for next-generation efficient artificial intelligence (AI) due to its ultra-high speed and efficiency. Electromagnetic field simulation is critical to the design, optimization, and validation of photonic devices and circuits. However, costly numerical simulation significantly hinders the scalability and turn-around time in the photonic circuit design loop. Recently, physics-informed neural networks have been proposed to predict the optical field solution of a single instance of a partial differential equation (PDE) with predefined parameters. Their complicated PDE formulation and lack of efficient parametrization mechanisms limit their flexibility and generalization in practical simulation scenarios. In this work, for the first time, a physics-agnostic neural operator-based framework, dubbed NeurOLight, is proposed to learn a family of frequency-domain Maxwell PDEs for ultra-fast parametric photonic device simulation. We balance the efficiency and generalization of NeurOLight via several novel techniques. Specifically, we discretize different devices into a unified domain, represent parametric PDEs with a compact wave prior, and encode the incident light via masked source modeling. We design our model with parameter-efficient cross-shaped NeurOLight blocks and adopt superposition-based augmentation for data-efficient learning. With these synergistic approaches, NeurOLight generalizes to a large space of unseen simulation settings, demonstrates 2-orders-of-magnitude faster simulation speed than numerical solvers, and outperforms prior neural network models by ~54% lower prediction error with ~44% fewer parameters. Our code is available at https://github.com/JeremieMelo/NeurOLight.