research
A Wave Model Kept the Detail With One-Tenth the Parameters
DU-NO used 3.64 million parameters, improved rollout error 14.9% over U-FNO and preserved high-frequency wave structure.
Summary
DU-NO used 3.64 million parameters, improved rollout error 14.9% over U-FNO and preserved high-frequency wave structure.
Phase-resolving coastal models are accurate but too expensive for many ensembles and real-time forecasts. DU-NO places lightweight convolutional U-Net branches only on the fine encoder and decoder levels where high-wavenumber content exists, leaving coarser levels spectral. The resulting 3.64-million-parameter neural operator used 10.8 times fewer parameters than U-FNO while improving autoregressive rollout error by 14.9% on the authors’ FUNWAVE-TVD benchmark. A parameter-matched baseline still trailed by 28.6%, and tests extended to Navier–Stokes and shallow-water rollouts. Operational warning performance remains to be established.
Why it matters
DU-NO used 3.64 million parameters, improved rollout error 14.9% over U-FNO and preserved high-frequency wave structure.
Limits and context
- DU-NO places lightweight convolutional U-Net branches only on the fine encoder and decoder levels where high-wavenumber content exists, leaving coarser levels spectral.
Key claims
DU-NO used 3.64 million parameters, improved rollout error 14.9% over U-FNO and preserved high-frequency wave structure.
Qualification: DU-NO places lightweight convolutional U-Net branches only on the fine encoder and decoder levels where high-wavenumber content exists, leaving coarser levels spectral.
Evidence: source-2026-09-14-004
Sources
- arXiv preprint 2609.12115arXiv · primary research
Corrections
No corrections have been recorded for this story.