Physics-Constrained Spatio-Temporal Attention FusionGAN: End-to-End Gridded Sea Surface Wind Fusion Over China Seas From Multimission GNSS-R Observations

To fully exploit the advantages of GNSS-R small satellites (large quantity, short revisit cycle) and address key challenges of multisource GNSS-R data&#x2014;track-wise distribution, uneven spatial coverage, and observation gaps, this study proposes a FusionGAN model integrating spatio-temporal attention mechanisms and physical constraints. This model enables end-to-end reconstruction of full-coverage gridded sea surface wind fields directly from sparse GNSS-R observations in the China Seas region. A two-stage training strategy is adopted: pretraining using 31+ years of cross-calibrated multiplatform wind dataset to lay a foundation for learning how to fill data gaps based on input orbit data, followed by fine-tuning with real GNSS-R observations from Cyclone Global Navigation Satellite System, FY-3 series satellites, and Tianmu-1 to enhance adaptability to practical data. Experimental results, validated through comparisons across low-to-medium wind, high wind, and typhoon scenarios, demonstrate the effectiveness of the proposed model: Finetuned-FusionGAN achieves an overall Bias of &#x2013;0.03 m/s, a root-mean-square errors (RMSE) of 1.38 m/s (22&#x0025; reduction), and a correlation coefficient <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> of 0.90. Specifically, by leveraging physics-constrained losses and spatio-temporal attention, the model reduces input GNSS-R observational data RMSE by 28.5&#x0025; to 1.18 m/s and improves <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> by 8.2&#x0025; to 0.92. In nonorbit regions, it generates physically consistent wind fields with an RMSE of 1.45 m/s, a correlation coefficient <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> of 0.89, comparable to input GNSS-R observational data accuracy. Moreover, benefiting from its physics-constrained design, the proposed model effectively mitigates observational discrepancies in multisource GNSS-R observations, fills spatial gaps, providing an effective solution for multisource GNSS-R sea surface wind field fusion.