High Wind Speed Correction for HY-2 Satellite microwave scatterometer based on Broad Learning System

To address the need for high wind speed correction of HY-2 series satellite microwave scatterometer, this study utilized the HY-2 wind speed of nine tropical cyclones between 2021 and 2022 as the data source. The Stepped Frequency Microwave Radiometer (SFMR) wind speed measurements served as the ground truth. A modeling dataset was constructed through spatiotemporal matching and randomly divided into a training set and a testing set at a 7:3 ratio. Subsequently, the Broad Learning System (BLS) was employed to do the regression analysis and develop a high-wind-speed correction model. Validation results demonstrate that the corrected HY-2 wind speeds achieved a root mean square error (RMSE) of 4.65 m/s, representing a 51% improvement compared to the uncorrected data. For wind speeds exceeding 25 m/s, the corrected RMSE and correlation coefficient reached 5.59 m/s and 0.68, respectively, marking significant enhancements over the original values of 13.69 m/s and 0.55. Additionally, a comparative analysis using Typhoon Chanthu (2021) as a case study revealed that the corrected HY-2C maximum wind speed increased from 22.09 m/s to 32.73 m/s. Further validation through wind speed profile comparisons confirmed the effectiveness of the proposed model.