In this study, seven filter algorithms were compared. The Lee sigma method was more suitable for estimating SM than the other filtering methods under different land cover types. Firstly, we used a combination of roughness and the dual-polarized Sentinel-1A backscattering coefficients (VV and VH) to estimate SM in bare soil areas. Secondly, we employed water cloud model (WCM) to remove the influence of vegetation signals on the land surface backscattering and estimate SM in vegetation-covered areas. SM was also retrieved by Modified soil moisture monitoring index (MSMMI) and Modified perpendicular drought index (MPDI) of Sentinel-2A images. The results show that MSMMI can more accurately monitor SM in bare soil areas, which was slightly better than SAR results. The SAR backscattering coefficients after the removal of vegetation influence by WCM can more precisely estimate SM in vegetation-covered areas, which is significantly better than MSMMI and MPDI, especially in high vegetation cover areas. Optics and SAR differ in their abilities to estimate SM under different land cover, but the powerful fitting ability of machine learning can make full use of their advantages. We employed the generalized regression neural network (GRNN), support vector regression (SVR), random forest regression (RFR), and deep neural network (DNN) algorithms to estimate SM combining Sentinel-1A with Sentinel-2A images. The estimation accuracies of SM by regression algorithms were higher than those by the semi-empirical SAR and optical models. The accuracy of estimated SM by DNN was higher than that of GRNN and RFR, which were better than SVR.

This article aims to explore the applicability of SMMI (soil moisture monitoring index), MSMMI (modified soil moisture monitoring index), PDI (perpendicular drought index), and MPDI (modified perpendicular drought index) in estimating soil moisture (SM) in farmland. The random forest classifier was used to obtain two-stage land cover types maps. The sensitivity of Sentinel-2 spectral bands to the measured SM at a depth of 0-5 cm was optimized by random forest regression. According to the sensitive bands, SMMI and PDI from different feature spaces were constructed to explore their feasibility for monitoring SM under different land cover types. Second, fractional vegetation cover (FVC) in the study area was estimated by nine kinds of FVC estimation models and compared with the measured FVC. The effects of different FVC methods on estimating SM by MSMMI and MPDI were evaluated. The results show that red edge and short-wave infrared (SWIR) bands of Sentinel-2 had irreplaceable effects on the land cover classification. In terms of monitoring SM in bare soil areas, the SM indices with SWIR bands had high correlations with measured SM. For vegetation-covered areas, MSMMI from the FVCgr model (dimidiate pixel model with red edge bands) and the Short wave infrared1-Short wave infrared2 feature space had the highest correlation with the measured 0-5 cm depth SM. Whether vegetation-covered areas or bare soil areas, the combination of red edge and SWIR bands can effectively improve the estimation accuracy of SM. MSMMI can be used as the best SMMI in the study area. Sentinel-2 images, with great potential, can effectively estimate SM at a depth of 0-5 cm in farmland with complex environments.

Mapping soil organic carbon (SOC) plays a crucial role in agricultural productivity and water management. This study discusses the potential of active and passive remote sensing for SOC estimation modeling in agricultural areas, incorporating synthetic aperture radar (SAR) data (L-band quad-polarization and C-band dual-polarization), multi-spectrum (MS) data, and brightness temperature (TB) data. The performance of five advanced machine learning regression (MLR) models for SOC modeling was assessed, focusing on spatial interpolation accuracy and cross-spatial transfer accuracy, using two field observation datasets for modeling and validation. Results indicate that the SOC estimation accuracy when using MS data alone is comparable to that of using TB data alone, and both perform slightly better than SAR data. Radar cross-polarization ratio index, microwave polarization difference index, shortwave infrared reflectance, and soil parameters (elevation and soil moisture) demonstrate high correlation with the measured SOC. Incorporating temporal features, as opposed to single-phase features, allows each regression model to reach its upper limit of SOC estimation accuracy. The spatial interpolation accuracy of each MLR algorithm is satisfactory, with the Gaussian process regression (GPR) model demonstrating optimal modeling performance. When SAR, MS, or TB data are used individually in modeling, the estimation errors (RMSE) for SOC are 0.637 g/kg, 0.492 g/kg, and 0.229 g/kg for the SMAPVEX12 sampling campaign, and 0.706 g/kg, 0.454 g/kg, and 0.474 g/kg for the SMAPVEX16-MB sampling campaign, respectively. After incorporating soil moisture and topographic factors, the above RMSEs for SOC are further reduced by 57.8%, 35.6%, and 3.5% for the SMAPVEX12, and by 18.4%, 8.8%, and 3.4% for the SMAPVEX16-MB, respectively. However, cross-spatial transfer accuracy of the regression models remains limited (RMSE = 0.866–1.043 g/kg and 0.995–1.679 g/kg for different data sources). To address this, this study reduces uncertainties in SOC cross-spatial transfer by introducing terrain factors sensitive to SOC (RMSE = 0.457–0.516 g/kg and 0.799–1.198 g/kg for different data sources). The proposed SOC estimation and transfer framework, based on active and passive remote sensing data, provides guidance for high-resolution regional-scale SOC mapping and applications.

Validating the potential of multi-frequency synthetic aperture radar (SAR) data for multi-layer and profile soil moisture (SM) estimation modeling, we conducted an airborne multi-frequency SAR joint observation experiment (AMFSEX) over the Liao River Basin in China. The experiment simultaneously acquired airborne high spatial resolution quad-polarization (quad-pol) SAR data at five frequencies, including the Ka-, X-, C-, S-, and L-band. A preliminary “vegetation–soil” parameter estimation model based on the multi-frequency SAR data was established. Theoretical penetration depths of the multi-frequency SAR data were analyzed using the Dobson empirical model and the Hallikainen modified model. On this basis, a water cloud model (WCM) constrained by multi-polarization weighted and penetration depth weighted parameters was used to analyze the estimation accuracy of the multi-layer and profile SM (0–50 cm depth) under different vegetation types (grassland, farmland, and woodland). Overall, the estimation error (root mean square error, RMSE) of the surface SM (0–5 cm depth) ranged from 0.058 cm³/cm³ to 0.079 cm³/cm³, and increased with radar frequency. For multi-layer and profile SM (3 cm, 5 cm, 10 cm, 20 cm, 30 cm, 40 cm, 50 cm depth), the RMSE ranged from 0.040 cm³/cm³ to 0.069 cm³/cm³. Finally, a multi-input multi-output regression model (Gaussian process regression) was used to simultaneously estimate the multi-layer and profile SM. For surface SM, the overall RMSE was approximately 0.040 cm³/cm³. For multi-layer and profile SM, the overall RMSE ranged from 0.031 cm³/cm³ to 0.064 cm³/cm³. The estimation accuracy achieved by coupling the multi-source data (multi-frequency SAR data, multispectral data, and soil parameters) was superior to that obtained using the SAR data alone. The optimal SM penetration depth varied across different vegetation cover types, generally falling within the range of 10–30 cm, which holds true for both the scattering model and the regression model. This study provides methodological guidance for the development of multi-layer and profile SM estimation models based on the multi-frequency SAR data.