Reproduce “Wave Physics as Representation: Tensor-Structured Neural Reconstruction for Ocean Acoustic Fields” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yifan Sun, Panqi Chen, Weifeng Shi, Xiao Fu, Lei Cheng
TIDAL reconstructs three-dimensional complex ocean-acoustic fields from sparse horizontal and vertical transects. It represents the field as depth–range spatial components paired with angular factors, and uses depth- and range-wise attention to infer unobserved regions. In simulated tests, it achieves 0.269 ± 0.085 relative RMSE, versus 0.298 ± 0.078 for MxT; results are limited to held-out solver-generated fields.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.