Temporal-Spatial Soil Moisture Estimation from CYGNSS Using Machine Learning Regression with a Pre-Classification Approach

Global Navigation Satellite System-Reflectometry (GNSS-R) can retrieve Earth's surface parameters, such as soil moisture (SM) using the reflected signals from GNSS constellations with advantages of non-contact, all-weather, real-time, and continuity, particularly the space-borne Cyclone GNSS (CYGNSS) mission. However, the accuracy and efficiency of SM estimation from CYGNSS still need to improve. In this paper, the global SM is estimated using Machine Learning (ML) regression aided by a pre-classification strategy. The total observations are classified by land types and corresponding subsets are built for constructing ML regression submodels. Ten-fold cross-validation technique is adopted. The overall performance of SM estimation with/without pre-classification are compared, and the results show that the SM estimations using different ML algorithms all have substantial improvement with the pre-classification strategy. Then the optimal XGBoost predicted model with root mean square error (RMSE) of 0.052 cm3/cm3 is adopted. In addition, the satisfactory daily and seasonal SM prediction outcomes with an overall correlation coefficient value of 0.86, and an RMSE value of 0.056 cm3/cm3 are achieved at a global scale, respectively. Furthermore, the extensive temporal and spatial variations of CYGNSS SM predictions are evaluated. It shows that the reflectivity plays a main role among the predictors in SM estimation, and the next is vegetation. In some extremely dry places, the roughness may become more important. The value of SM is positively correlated with RMSE and also another limit condition that will constrain the variation of predictors, thus affecting correlation coefficient R and RMSE. Also, we compare both SMAP and CYGNSS SM predictions against in situ SM measurements from 301 stations. Similar low median unbiased RMSEs are obtained, and the daily averaged CYGNSS-based SM against the in situ networks is 0.049 cm3/cm3. The presented approach succeeds in providing SM estimation at a global scale with employing the least ancillary data with superior results and this paper reveals the spatio-temporal heterogeneity for SM estimation using CYGNSS data.