Wave Retrieval Under Typhoon Conditions Using a Machine Learning Method Applied to Gaofen-3 SAR Imagery

Abstract

The spatial resolution of Chinese Gaofen-3 (GF-3) Synthetic Aperture Radar (SAR) image, a pixel size of 500 m at azimuth/flight direction for Global Observation (GLO) and 100 m for Wide ScanSAR (WSC) modes, is relatively coarse, and waves shorter than 100 m are undetectable. In this study, SAR images collected under typhoon conditions by the GF-3 mission are exploited for wave retrieval purposes. In detail, six imagery collected during 2017 and 2018 over the China Seas captured four typhoons. The GLO and WSC modes images are collocated with simulated wave fields using a numeric wave model, called WAVEWATCH-III (WW3) and are processed using a machine learning method to retrieve sea surface waves. In this work, the criterion for the training completion in the process of machine learning is set as 0.15 m of Root mean Square Error (RMSE) for the Significant Wave Height (SWH). Then, the retrieved SWH is compared with measurements collected by the Jason-2 altimeter, showing a 0.61 m RMSE. The proposed algorithm is shown to outperform empirical approaches developed to retrieve the SWH using GF-3 SAR imagery acquired in the GLO and WSC imaging modes.