Physically Consistent Reconstruction of Sparse Scatterometer Ocean Surface Wind Fields Based on Physics‐Guided Generative Learning

Abstract

Accurate and timely reconstruction of sea surface wind fields from available scatterometer‐derived observations is essential for rapid‐response forecasting and operational oceanography. In this study, we explore a novel physics‐guided generative learning network to reconstruct sea surface wind vector fields directly from sparse scatterometer‐like inputs. The proposed method integrates data‐driven learning with physics‐based guiding. The discriminator is designed to assess the physical plausibility of reconstructed wind fields through physics consistency scores, while the generator is guided by a composite loss function incorporating tailored physical terms to ensure physically faithful and dynamically coherent outputs. Experimental results show that the proposed method achieves fast, structurally preservative, and physically consistent reconstructions, even under significant data sparsity. Notably, during Typhoon Merbok (September 2022), the generative learning network effectively recovered the vortex structure with a wind speed RMSE no more than 2 m/s, demonstrating strong capability in handling extreme events.