FieldSeer I: Physics-Guided World Models for Long-Horizon Electromagnetic Dynamics under Partial Observability

2025/12/05 by Guo, Ziheng, Wu, Fang, Zhao, Maoxiong +2
#Computational Physics (physics.comp-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Optics (physics.optics)

paper · doi:10.48550/arxiv.2512.05361

Abstract

We introduce FieldSeer I, a geometry-aware world model that forecasts electromagnetic field dynamics from partial observations in 2-D TE waveguides. The model assimilates a short prefix of observed fields, conditions on a scalar source action and structure/material map, and generates closed-loop rollouts in the physical domain. Training in a symmetric-log domain ensures numerical stability. Evaluated on a reproducible FDTD benchmark (200 unique simulations, structure-wise split), FieldSeer I achieves higher suffix fidelity than GRU and deterministic baselines across three practical settings: (i) software-in-the-loop filtering (64x64, P=80->Q=80), (ii) offline single-file rollouts (80x140, P=240->Q=40), and (iii) offline multi-structure rollouts (80x140, P=180->Q=100). Crucially, it enables edit-after-prefix geometry modifications without re-assimilation. Results demonstrate that geometry-conditioned world models provide a practical path toward interactive digital twins for photonic design.

Citations

• GAIA-1: A Generative World Model for Autonomous Driving
• Fourier Neural Operator for Parametric Partial Differential Equations
• Neural Ordinary Differential Equations

Related

• PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices
• WaveY-Net: Physics-augmented deep learning for high-speed electromagnetic simulation and optimization
• Generalizing Deep Surrogate Solvers for Broadband Electromagnetic Field Prediction at Unseen Wavelengths
• Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
• Meent: Differentiable Electromagnetic Simulator for Machine Learning