arXiv cs.AI· Yifan Sun, Panqi Chen, Weifeng Shi, Xiao Fu, Lei Cheng·· 11 小时前AI 评分18
TIDAL：用波物理张量表示重建三维海洋声场
Wave Physics as Representation: Tensor-Structured Neural Reconstruction for Ocean Acoustic Fields
AI 导读
研究者提出 TIDAL 神经重建器，从 Helmholtz 方程与简正波传播中导出 S/c 空间-角度张量表示，在低秩特化下化为 rank-(L,L,1) 块项张量分解，并将其作为结构化解码的归纳偏置。该方法无需传统物理反演所需的已知环境参数，在三种结构化采样几何下取得最佳重建性能与最快推理速度，且在数据与模型容量受限时仍受益于物理导出表示。
正文 · 原文
Abstract:Reconstructing three-dimensional (3D) complex ocean acoustic fields from sparse measurements is challenging due to highly oscillatory wave structures and restricted sensing patterns/routes. Learning-based approaches fall into two categories. First, purely data-driven models can learn complex field patterns, but do not explicitly exploit wave physics that may enhance interpretability and reduce training costs. Second, physics-informed methods impose a specified physical equation as a reconstruction constraint, but often require environment-dependent parameters that are difficult to acquire. As a result, practical 3D acoustic field reconstruction that is both physically grounded and robust to uncertain environmental information remains largely unexplored. This work takes an alternative route: instead of solving a fully specified wave equation, it extracts a structured representation from wave physics and learns its components from data. From the Helmholtz equation and normal mode propagation, we derive a structured spatial-angular tensor representation, termed the S/c representation. Under a low-rank specialization, it takes the form of a rank-(L,L,1) block-term tensor decomposition, which connects structured sampling patterns/routes used in ocean sensing to sufficient conditions for field recovery. Building on this tensor representation, we propose TIDAL, a neural reconstructor that uses the S/c representation as an inductive bias for structured decoding and aligns information aggregation with the sampling geometry. The neural learner removes the need for known model parameters required by conventional physics-based recovery methods. Experiments across three structured sampling geometries show that TIDAL achieves the best reconstruction performance and fastest inference among baselines, with benefits from the physics-derived representation under limited data and model capacity.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Sound (cs.SD); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2611.01680 [cs.LG] |
| (or arXiv:2611.01680v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01680 arXiv-issued DOI via DataCite |
Submission history
From: Yifan Sun [view email]
[v1]
Sun, 1 Nov 2026 07:58:49 UTC (1,250 KB)
[v2]
Wed, 4 Nov 2026 07:19:28 UTC (1,250 KB)
来源：arXiv cs.AI · arxiv.org