New AI Could Make Coastal Flood Forecasts Faster and Cheaper

Researchers introduced DU-NO (Double U-shaped Neural Operator), a parameter-efficient neural operator for phase-resolving wave modeling — the class of nearshore simulation that resolves the shoaling, refraction, and breaking of individual waves. Traditional phase-resolving models like FUNWAVE-TVD are the accuracy standard for nearshore dynamics, but their cost rules them out for the ensembles, uncertainty quantification, and real-time warning that operational forecasting demands. Neural operators promise solver-level accuracy at a fraction of that cost, yet on wave-dominated fields the accurate ones are large: hybrid spectral-convolutional operators such as U-FNO, the strongest baseline in the study after DU-NO, buy their fidelity with tens of millions of parameters.

DU-NO takes a different route, attaching lightweight convolutional U-Net branches only at its two shallowest encoder and decoder levels. The placement follows a sampling argument: high-wavenumber content exists only on fine grids, so the local, full-band pathways go where that content lives, while the coarse, band-limited levels stay purely spectral. A depth-decaying mode schedule holds the model to 3.64M parameters — an order of magnitude below U-FNO.

On the authors' publicly released FUNWAVE-TVD benchmark, DU-NO attained the best autoregressive rollout error of six identically trained architectures, improving on U-FNO by 14.9% with 10.8x fewer parameters. A frequency-band analysis showed the gain holds across all bands, including the high-wavenumber band where truncated-spectral operators collapse. Parameter-matched controls confirm the gain is architectural: rescaled to the same 3.6M budget, the best baseline still trails DU-NO by 28.6%. The advantage carries beyond nearshore waves — DU-NO matches the strongest baselines on 2D Navier-Stokes and wins clearly on PDEBench shallow-water rollouts. Code, trained models, and evaluation artifacts are available.