Tropical Cyclone Winds Retrieval Algorithm for the Cyclone Global Navigation Satellite System Mission

In this study, we propose a method for wind speed retrieval using a random forest (RF) algorithm for Cyclone Global Navigation Satellite System (CYGNSS) data. We first compared CYGNSS data with soil moisture active passive (SMAP) data and found a certain deviation in the CYGNSS young sea, limited fetch (YSLF) data product for high winds. Then, we used SMAP as the ground truth to train an RF model and applied it to the wind speed retrieval of CYGNSS data. The experimental results show that using the RF algorithm for wind speed retrieval can eliminate noise in the CYGNSS YSLF wind speed data and improve retrieval accuracy. In addition, we explored the impact of different input parameter combinations on model performance and found that using an 11-parameter model in CYGNSS wind speed retrieval can achieve optimal performance. This can provide a valuable reference for rapid near-real-time retrieval of tropical cyclones using CYGNSS.

Automated summary

This study proposes a method for wind speed retrieval using a random forest algorithm for Cyclone Global Navigation Satellite System (CYGNSS) data. By comparing CYGNSS data with soil moisture active passive (SMAP) data, certain deviations were found in the CYGNSS young sea, limited fetch (YSLF) data product for high winds. The random forest model was trained using SMAP as the ground truth and applied to the wind speed retrieval of CYGNSS data. Experimental results showed that the random forest algorithm improved retrieval accuracy and eliminated noise in the CYGNSS YSLF wind speed data. The study also investigated the impact of different input parameter combinations and found that an 11-parameter model achieved optimal performance. This provides valuable reference for rapid near-real-time retrieval of tropical cyclones using CYGNSS.