Saved in:
Bibliographic Details
Main Authors: Guo, Ziheng, Wu, Fang, Zhao, Maoxiong, Fang, Chaoqun, Bu, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.05361
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917127351435264
author Guo, Ziheng
Wu, Fang
Zhao, Maoxiong
Fang, Chaoqun
Bu, Yang
author_facet Guo, Ziheng
Wu, Fang
Zhao, Maoxiong
Fang, Chaoqun
Bu, Yang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FieldSeer I: Physics-Guided World Models for Long-Horizon Electromagnetic Dynamics under Partial Observability
Guo, Ziheng
Wu, Fang
Zhao, Maoxiong
Fang, Chaoqun
Bu, Yang
Optics
Machine Learning
Computational Physics
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.
title FieldSeer I: Physics-Guided World Models for Long-Horizon Electromagnetic Dynamics under Partial Observability
topic Optics
Machine Learning
Computational Physics
url https://arxiv.org/abs/2512.05361