Coastal Regions Sea Surface Salinity Retrieval of SMAP MISSION Based on Light Gradient Boosting Model

Sea surface salinity (SSS) as an important indicator of ocean water circulation, affects global ecology and climate change. However, the accuracy of L-band satellite sea surface salinity retrieval products has been severely affected in coastal regions due to factors such as Radio Frequency Interference (RFI) and Land Sea Continuation (LSC). In this study, coastal regions observational data from the Soil Motion Active Passive (SMAP) satellite, and established the LGBM model for SSS retrieval. The results indicated that LGBM performed excellently in the retrieval of SSS in coastal regions. In comparison to in-situ SSS, the LGBM SSS demonstrated a mean bias (MB) of 0.11psu, a root mean squares error (RMSE) of 0.68psu. This paper also added the bias between LGBM SSS and in situ SSS for secondary correction of LGBM. This correction reduced the MB to 0.03psu, the RMSE to 0.54psu. This study affirms the feasibility of using LGBM for SSS retrieval in coastal regions. Future efforts will focus on integrating more auxiliary data that may influence SSS in coastal regions, aiming to further enhance the precision of the coastal regions’ SSS retrieval product.