Data-driven and physics-guided hindcasting of measured wave spectra
Abstract
Short-range hindcasts of measured wave spectra are evaluated using a recurrent model initialized by one hourly buoy spectrum and supplied with local wind, fetch and depth. Measurements from three Baltic Sea stations are combined for training in 2017--2020, validation in 2021 and testing in 2022. ERA5 reanalysis supplies winds throughout the twelve-hour prediction interval. The comparison examines supervision of spectral variance, peak frequency and peak amplitude, followed by empirical wind-sea bounds and a local relaxation constraint. Variance and peak-frequency supervision gives the lowest spectral error within the data-driven comparison, whereas additional peak-amplitude supervision gives the lowest wave-height error. In the matched physical comparison, relaxation reduces height RMSE by 5.01\% to \PhPtwoHs{}~cm. Extending this constraint through hours 13--24, without spectral targets at those hours, reduces primary spectral RMSE by 2.31\% to \PhPthreeSpec{}~unitE. Upper-bound constraints increase errors. Wind-condition comparisons show spectral gains from extended relaxation in increasing, decreasing and steady strong winds, with little change in steady weak winds. The results support modest, objective-dependent benefits from local physical guidance. Wave-height scores concern the retained frequency band, and operational forecasting and transfer to independent stations remain to be evaluated.
Related
- Meteorology-driven Causal Nowcasting of Fugitive Landfill Emissions from Measured Coupling Timescales
- A transparent constrained stochastic framework for urban expansion forecasting and future service-network screening: Cape Town demonstration using annual building evidence, empirical land constraints, spatial hindcasting, and multi-horizon ensembles
- Multi-Modal Surface Wave Inversion using Physics Guided Variational Autoencoders
- Accounting for Radiative Transfer Model Errors in Physics-Guided VAEs for Biophysical Variable Retrieval
- PhyTGNet: A Physics‐Prior‐Guided Interpretable Forecasting Method for Thunderstorm Gusts in the Beijing–Tianjin–Hebei Region
BibTeX
@misc{rikka2026datadriven,
title = {{Data-driven and physics-guided hindcasting of measured wave spectra}},
author = {Sander Rikka},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.29306},
eprint = {2610.29306},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.29306},
}
RIS
TY - UNPB
TI - Data-driven and physics-guided hindcasting of measured wave spectra
AU - Sander Rikka
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2610.29306
UR - https://arxiv.org/abs/2610.29306
AB - Short-range hindcasts of measured wave spectra are evaluated using a recurrent model initialized by one hourly buoy spectrum and supplied with local wind, fetch and depth. Measurements from three Baltic Sea stations are combined for training in 2017--2020, validation in 2021 and testing in 2022. ERA5 reanalysis supplies winds throughout the twelve-hour prediction interval. The comparison examines supervision of spectral variance, peak frequency and peak amplitude, followed by empirical wind-sea bounds and a local relaxation constraint. Variance and peak-frequency supervision gives the lowest spectral error within the data-driven comparison, whereas additional peak-amplitude supervision gives the lowest wave-height error. In the matched physical comparison, relaxation reduces height RMSE by 5.01\% to \PhPtwoHs{}~cm. Extending this constraint through hours 13--24, without spectral targets at those hours, reduces primary spectral RMSE by 2.31\% to \PhPthreeSpec{}~unitE. Upper-bound constraints increase errors. Wind-condition comparisons show spectral gains from extended relaxation in increasing, decreasing and steady strong winds, with little change in steady weak winds. The results support modest, objective-dependent benefits from local physical guidance. Wave-height scores concern the retained frequency band, and operational forecasting and transfer to independent stations remain to be evaluated.
ER -