The soil moisture of the Qinghai-Tibet Plateau plays a crucial role in global atmospheric circulation and climate change. The cyclone global navigation satellite system (CYGNSS), utilizing global navigation satellite system reflectometry (GNSS-R), provides a novel method to monitor soil moisture on the Qinghai-Tibet Plateau; however, the complex topographic environment of the plateau hinders the direct use of CYGNSS reflectivity for soil moisture retrieval. This paper proposes a spaceborne GNSS-R soil moisture machine learning inversion model, which integrates five characteristic parameters: corrected CYGNSS reflectivity, CYGNSS incident angle, and terrain parameters (elevation, slope, surface roughness). First, the CYGNSS reflectance is corrected for two aspects: systematic errors in transmit power, and attenuation induced by surface vegetation and surface roughness. Then, the corrected reflectivity (along with the other four aforementioned parameters) is adopted as input feature quantities, and SMAP soil moisture data is used for model verification. For data partitioning, the 2020 thaw period (June–September) data are randomly split into a training set and a verification set at a 5∶5 ratio. On this basis, two soil moisture inversion models (random forest (RF) and artificial neural network (ANN)) are established specifically for the Qinghai-Tibet Plateau. Use the data from the 2021 thaw period as a test set to examine the generalization ability of the model. The results of the random forest model are better than the artificial neural network model, the inversion result yielding a root mean square error (RMSE) of 0.0586 $\text{c}{\text{m}}^{\text{3}}\text{/c}{\text{m}}^{\text{3}}$ and Pearson correlation coefficient of 0.7033 on the test set. The model exhibits strong generalization performance: the spatial variation of the inverted soil moisture is consistent with the spatial variation trend of precipitation over the Qinghai-Tibet Plateau. Finally, a comparison between the CYGNSS-derived soil moisture and the in-situ measured soil moisture (from Naqu) shows high accuracy, with a RMSE of 0.070 cm³/cm³. The research results show that the inversion model, which integrates corrected CYGNSS reflectance, CYGNSS incident angle, and topography parameters, achieves a more accurate invert of soil moisture in a large range of the Qinghai-Tibet Plateau.

The cyclone global navigation satellite system (CYGNSS) provides high-quality global navigation satellite system reflectometry (GNSS-R) data that can be reliably used for the retrieval of significant wave height (SWH). Due to the high dynamic nature of CYGNSS, the received signal is easily affected by environmental factors, and the complexity of sea conditions makes it difficult for simple models to accurately retrieve SWH. To address the above issues, this article proposed an SWH retrieval model based on multivariate machine learning. According to the mechanism of wave formation and the analysis of the correlation between CYGNSS parameters and SWH, relevant parameters were selected, and three training schemes were designed, involving five parameters, nine parameters, and 17 parameters, respectively. Random forest (RF) and convolutional neural network (CNN) were used to train and verify the retrieval model, and the SWH retrieval results were compared with the reference values of the European Centre for Medium-Range Weather Forecasts (ECMWF). The best retrieval model among them was the 17-parameter CNN retrieval model, with root mean square error（RMSE）was 0.184 0 m and $R^2$= 0.948 5. Compared with the 17-parameter CNN retrieval model, the 9-parameter CNN retrieval model reduced training time by 24% and has minimal accuracy loss. However, the 9-parameter retrieval model performed poorly in terms of generalization evaluation compared to the 17-parameter retrieval model. To improve the generalization ability of the model, wind speed was added as a parameter to the 17-parameter retrieval model, resulting in a 17 + 1-parameter generalization model. The best generalization model among them was the 17 + 1 parameter RF generalization model, with RMSE was 0.497 1 m and $R^2$= 0.584 6. This effectively proves that the model proposed in this article has good potential in SWH retrieval.