Accurate Sea Surface Parameter Retrieval via a Dynamic Graph Physical Residual Network

Satellite data often exhibit spatial discontinuities, and the unstructured nature of these data makes it difficult for researchers to use structured spatial analysis methods such as convolutional neural networks (CNNs) in studies of sea surface parameters retrieval. To address these issues, we propose a dynamic graph physical residual network (DGPRN) for retrieving sea surface vector winds and sea surface temperatures (SSTs) via data from the microwave radiation imager (MWRI) onboard the Fengyun-3 (FY-3) satellite. This model consists of a position encoder, a dynamic adjacency matrix generator, a graph convolution module, and a physical residual module. The results indicate that the DGPRN model performs better than traditional retrieval algorithms under complex wind conditions. The DGPRN incorporates the radiative transfer equation as an inductive bias to convert relative wind direction information into brightness temperature residuals, thereby increasing the retrieval accuracy. Moreover, we capture the spatial distribution characteristics of sea surface wind speed (SSWS) and sea surface wind direction (SSWD) and retrieve continuous wind fields in areas with complex topography and cyclonic circulation. Extensive experiments indicate that the DGPRN model outperforms other competing methods in both retrieval accuracy and generalization performance. Specifically, DGPRN model achieves root mean square error (RMSE) values of 0.87 m/s for the wind speed, 14.80° for the wind direction, and 0.81 K for the SST, with correlation coefficients exceeding 0.93.