PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulation

Optical simulation plays an important role in photonic hardware design flow. The finite-difference time-domain (FDTD) method is widely adopted to solve time-domain Maxwell equations. However, FDTD is known for its prohibitive runtime cost as it iteratively solves Maxwell equations and takes minutes...

Full description

Saved in:
Bibliographic Details
Main Authors: Pingchuan Ma, Haoyu Yang, Zhengqi Gao, Duane S. Boning, Jiaqi Gu
Format: Article
Language:English
Published: AIP Publishing LLC 2025-03-01
Series:APL Photonics
Online Access:http://dx.doi.org/10.1063/5.0242728
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259361035714560
author Pingchuan Ma
Haoyu Yang
Zhengqi Gao
Duane S. Boning
Jiaqi Gu
author_facet Pingchuan Ma
Haoyu Yang
Zhengqi Gao
Duane S. Boning
Jiaqi Gu
author_sort Pingchuan Ma
collection DOAJ
description Optical simulation plays an important role in photonic hardware design flow. The finite-difference time-domain (FDTD) method is widely adopted to solve time-domain Maxwell equations. However, FDTD is known for its prohibitive runtime cost as it iteratively solves Maxwell equations and takes minutes to hours to simulate a single device. Recently, AI has been applied to realize orders-of-magnitude speedup in partial differential equation solving. However, AI-based FDTD solvers for photonic devices have not been clearly formulated. Directly applying off-the-shelf models to predict the optical field dynamics shows unsatisfying fidelity and efficiency since the model primitives are agnostic to the unique physical properties of Maxwell equations and lack algorithmic customization. In this work, we thoroughly investigate the synergy between neural operator designs and the physical property of Maxwell equations and introduce a physics-inspired AI-based FDTD prediction framework PIC2O-Sim. PIC2O-Sim features a causality-aware dynamic convolutional neural operator as its backbone model that honors the space–time causality constraints via careful receptive field configuration and explicitly captures the permittivity-dependent light propagation behavior via an efficient dynamic convolution operator. Meanwhile, we explore the trade-offs among prediction scalability, fidelity, and efficiency via a multi-stage partitioned time-bundling technique in autoregressive prediction. Multiple key techniques have been introduced to mitigate iterative error accumulation while maintaining efficiency advantages during autoregressive field prediction. Extensive evaluations on three challenging photonic device simulation tasks have shown the superiority of our PIC2O-Sim method, showing 51.2% lower roll-out prediction error, 23.5 times fewer parameters than state-of-the-art neural operators, providing 133–310× or 31–89× higher simulation speed than an open-source single-process or eight-process parallel FDTD numerical solver.
format Article
id doaj-art-b279e8b1779c4a0b98e88ed3eec74e44
institution OA Journals
issn 2378-0967
language English
publishDate 2025-03-01
publisher AIP Publishing LLC
record_format Article
series APL Photonics
spelling doaj-art-b279e8b1779c4a0b98e88ed3eec74e442025-08-20T01:55:52ZengAIP Publishing LLCAPL Photonics2378-09672025-03-01103036104036104-1710.1063/5.0242728PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulationPingchuan Ma0Haoyu Yang1Zhengqi Gao2Duane S. Boning3Jiaqi Gu4School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, Arizona 85281, USANVIDIA Inc., 11001 Lakeline Blvd. Suite #100 Bldg. 2, Austin, Texas 78717, USADepartment of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Boston, Massachusetts 02139, USADepartment of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Boston, Massachusetts 02139, USASchool of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, Arizona 85281, USAOptical simulation plays an important role in photonic hardware design flow. The finite-difference time-domain (FDTD) method is widely adopted to solve time-domain Maxwell equations. However, FDTD is known for its prohibitive runtime cost as it iteratively solves Maxwell equations and takes minutes to hours to simulate a single device. Recently, AI has been applied to realize orders-of-magnitude speedup in partial differential equation solving. However, AI-based FDTD solvers for photonic devices have not been clearly formulated. Directly applying off-the-shelf models to predict the optical field dynamics shows unsatisfying fidelity and efficiency since the model primitives are agnostic to the unique physical properties of Maxwell equations and lack algorithmic customization. In this work, we thoroughly investigate the synergy between neural operator designs and the physical property of Maxwell equations and introduce a physics-inspired AI-based FDTD prediction framework PIC2O-Sim. PIC2O-Sim features a causality-aware dynamic convolutional neural operator as its backbone model that honors the space–time causality constraints via careful receptive field configuration and explicitly captures the permittivity-dependent light propagation behavior via an efficient dynamic convolution operator. Meanwhile, we explore the trade-offs among prediction scalability, fidelity, and efficiency via a multi-stage partitioned time-bundling technique in autoregressive prediction. Multiple key techniques have been introduced to mitigate iterative error accumulation while maintaining efficiency advantages during autoregressive field prediction. Extensive evaluations on three challenging photonic device simulation tasks have shown the superiority of our PIC2O-Sim method, showing 51.2% lower roll-out prediction error, 23.5 times fewer parameters than state-of-the-art neural operators, providing 133–310× or 31–89× higher simulation speed than an open-source single-process or eight-process parallel FDTD numerical solver.http://dx.doi.org/10.1063/5.0242728
spellingShingle Pingchuan Ma
Haoyu Yang
Zhengqi Gao
Duane S. Boning
Jiaqi Gu
PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulation
APL Photonics
title PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulation
title_full PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulation
title_fullStr PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulation
title_full_unstemmed PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulation
title_short PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulation
title_sort pic2o sim a physics inspired causality aware dynamic convolutional neural operator for ultra fast photonic device time domain simulation
url http://dx.doi.org/10.1063/5.0242728
work_keys_str_mv AT pingchuanma pic2osimaphysicsinspiredcausalityawaredynamicconvolutionalneuraloperatorforultrafastphotonicdevicetimedomainsimulation
AT haoyuyang pic2osimaphysicsinspiredcausalityawaredynamicconvolutionalneuraloperatorforultrafastphotonicdevicetimedomainsimulation
AT zhengqigao pic2osimaphysicsinspiredcausalityawaredynamicconvolutionalneuraloperatorforultrafastphotonicdevicetimedomainsimulation
AT duanesboning pic2osimaphysicsinspiredcausalityawaredynamicconvolutionalneuraloperatorforultrafastphotonicdevicetimedomainsimulation
AT jiaqigu pic2osimaphysicsinspiredcausalityawaredynamicconvolutionalneuraloperatorforultrafastphotonicdevicetimedomainsimulation