A Novel Method for Ocean Wave Spectra Retrieval Using Deep Learning From Sentinel-1 Wave Mode Data

Ocean wave is of great significance in marine environment prediction, maritime navigation, and global climate change. Synthetic aperture radar (SAR) is widely used in ocean wave spectra retrieval due to its 2-D high resolution, all-weather, and all-time advantages. Nevertheless, the nonlinear mapping between SAR and ocean waves, caused by velocity bunching, hinders the advancement of wave spectra inversion techniques, resulting in low-quality and incomplete wave spectra. To overcome the problem, a novel deep learning model SAR2WV for ocean wave spectra retrieval based on Pix2pix is proposed by constructing the nonlinear mapping relationship of SAR cross spectra and ocean wave spectra. A total of 106 844 Sentinel-1 wave mode dataset along with the corresponding European Centre for Medium-Range Weather Forecasts (ECMWF) ERA 5 wave data is processed and used for training the SAR2WV model. Experiments demonstrate that the proposed SAR2WV model can significantly improve the accuracy of the retrieved wave spectra and wave parameters, with the spectra similarity improved by 60.3%, root-mean-square error (RMSE) of significant wave height (SWH) decreased from 0.966 to 0.386 m, RMSE of mean wave period (MWP) decreased from 1.208 s to 0.811 s, and correlation coefficient of peak wave direction increased from 0.65 to 0.72, which achieves better performance than ocean swell wave spectra (OSW) algorithm and other methods.