PIC2O-Sim: A physics-inspired causality-aware dynamic convolutional neural operator for ultra-fast photonic device time-domain simulation
Name
036104_1_5.0242728.pdf
Description
Published version
Size
11.82 MB
Format
Adobe PDF
Checksum (MD5)
a6e571431ee19dbb74fb8352f54d21dd
Author(s)
Ma, Pingchuan
Yang, Haoyu
Gao, Zhengqi
Boning, Duane S
Gu, Jiaqi
Date Issued
March 3, 2025
Journal
APL Photonics
Publisher
AIP Publishing
Citation
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 1 March 2025; 10 (3): 036104.
Version
Final published version
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1063/5.0242728
