Objectives:GNSS-IR (Global Interferometric Reflectometry) is a new passive remote sensing technique for determining surface environment parameters, which places an important part in the inversion of earth's surface properties, such as soil moisture monitoring, snow parameter retrieval, and vegetation remote sensing, etc. The GNSS-IR offers several benefits over the traditional soil moisture inversion approach, including all-weather capability, high temporal precision, and cheap cost. Method:Considering the fact that the existing soil moisture inversion algorithms only utilize one single feature of GNSS reflected signal and from the perspective of increasing data availability, this paper proposes a GNSS-IR soil moisture inversion approach that integrates multi-type feature data by utilizing phase, amplitude, and frequency extracted GNSS signals reflected by soil. The main work is to effectively filter all available features extracted from the original GNSS SNR observations. The feasibility and effect of the suggested method are compared and evaluated using three machine learning models, including LSSVM (Least Squares Support Vector Machine), RF (Random Forest), and BPNN (Back Propagation Neural Network). Results:Comparing the inversion effects of the above three models, the BP neural network model has the best inversion effect, followed by the random forest (RF) model, and the least squares support vector machine (LSSVM) model is the worst. The results showed that the correlation coefficients between the reference value and soil moisture inversed by the multi-feature fusion method LSSVM, RF, And BPNN models are 0.823, 0.944, and 0.955, respectively, and the corresponding root mean square errors (RMSE) are 0.045, 0.035 and 0.032cm3
. Conclusions:Compared with the single feature inversion method, the soil moisture inversion accuracy is increased by 6-14%, and the correlation coefficient is increased by 2-7%. The results demonstrated that the proposed method has higher inversion accuracy and reliability than the single feature inversion method.