基于物理约束的模型可从部分观测中预测电磁场长期演化。
FieldSeer I: Physics-Guided World Models for Long-Horizon Electromagnetic Dynamics under Partial Observability
- 用几何感知世界模型融合观测与结构信息，实现闭环推演。
- 在三种场景下均优于GRU和确定性基线，最高达80%保真度。
- 支持修改结构后无需重读取即可继续推演，适合光子设计交互应用。
我们提出FieldSeer I，一种几何感知的世界模型，可在二维TE波导中从部分观测预测电磁场动态。该模型接收一段观测场序列，结合标量源作用和结构/材料图，生成物理域内的闭环推演。训练采用对称对数域以保证数值稳定。在可复现的FDTD基准测试（200次独立模拟，按结构划分）上，FieldSeer I在三种实际场景中均表现出更高后缀保真度：(i) 软件闭环滤波（64×64，P=80→Q=80），(ii) 离线单文件推演（80×140，P=240→Q=40），(iii) 离线多结构推演（80×140，P=180→Q=100）。关键优势在于无需重新同化即可实现前缀后的几何修改。结果表明，几何条件化世界模型为光子设计交互式数字孪生提供了可行路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。