Sampling sea state using a diffusion model

2026-06-24

AI Summary

This study addresses the computational inefficiency of existing sea state forecasting methods, which struggle to support online coupling and probabilistic prediction, while most AI-based approaches are limited to deterministic outputs and single integrated variables. To overcome these limitations, this work proposes the first application of a conditional diffusion model to global sea state modeling. Trained on 30 years of WAVEWATCH-III reanalysis data, the model directly samples complex conditional distributions from five days of historical wind fields, enabling non-autoregressive and efficient probabilistic generation of full sea state fields. It simultaneously predicts partitioned wave parameters alongside derived quantities such as Stokes drift and mean square slope. Compared to conventional numerical spectral models, the proposed method achieves significant acceleration, delivers accurate predictions of integrated variables, and exhibits well-calibrated ensemble spread, offering a promising pathway for efficient coupling within Earth system models.

Abstract

Sea state prediction is essential for operational maritime applications and coupled earth system modeling, yet current spectral wave models remain computationally prohibitive for many use cases, including online coupling to climate simulations and making probabilistic (ensemble-based) predictions. While deep learning has recently demonstrated strong performance in weather forecasting, existing AI-based wave models are predominantly deterministic and largely limited to bulk variables such as significant wave height, leaving probabilistic sea state estimation largely unexplored. In this work, we propose a diffusion-based generative model for global sea state estimation that conditions on a relatively long history (5 days) of global wind forcing. This generative model directly samples the complex conditional distribution of sea state without autoregressive time-stepping. Unlike prior approaches, our framework naturally extends beyond bulk variables to estimate partition-related variables and derived quantities, such as Stokes drift and mean square slope. Trained on a 30-year global WAVEWATCH-III hindcast, the model achieves substantial computational acceleration compared with numerical spectral models while delivering skillful predictions and a calibrated ensemble spread for the bulk variables. Our results suggest that diffusion-based sea state sampling offers a promising path toward probabilistic wave forecasting and efficient coupling of sea state information into broader earth system models.

Problem

• sea state prediction
• probabilistic forecasting
• spectral wave models
• computational efficiency
• ensemble prediction

Innovation

• diffusion model
• probabilistic sea state estimation
• generative modeling
• ensemble forecasting
• computational acceleration