Machine learning combined with multisource remote sensing data to assess soil moisture content (SMC) has attracted considerable attention in SMC studies, but the retrieval results still remain uncertain. The purpose of this study is to combine multiple single machine learning models with integrated learning algorithms and propose an SMC retrieval method based on multiple differentiated models under a stacking integrated learning architecture. First, 19 factors, including: radar backscattering coefficient, vegetation index, and drought index, that affect SMC were extracted from SENTINEL-1, LANDSAT, and terrain factors. Those with the highest importance scores were selected as retrieval factors using the Boruta algorithm combined with four single machine learning methods-classified regression tree, random forest, gradient boosting decision tree (GBDT), and extreme random tree. In addition, the two stacking ensemble models using least absolute shrinkage and selection operator (LASSO) and the generalized boosted regression model (GBM) were tested and applied to build the most reliable and accurate estimation model. The results showed that radar backscattering coefficient, temperature, vegetation drought index, land surface temperature, enhanced vegetation index, and solar local incident angle were the most important environmental variables for soil moisture retrieval. A comparison of the four machine learning methods in April and August showed that the GBDT model revealed the highest SMC retrieval accuracy, with root mean square error values of 1.87% and 1.64%, respectively. The stacking models were more accurate than the optimal single machine learning model, especially when using GBM. The multifactor integrated model constructed using spectral indices, radar backscatter coefficients, and topographic data exhibited high accuracy in soil surface moisture retrieval in an arid zone, providing a reference for land desertification studies and ecological environment management in the study region.

Ecosystem water use efficiency (eWUE) is a useful metric to examine the interactions between water and carbon cycles in ecosystems. To reveal the response and adaptation characteristics of different vegetation types within the context of global warming on a regional scale, the spatiotemporal characteristics and influencing factors of the seasonal eWUE of various vegetation types in Inner Mongolia from 2001 to 2020 were explored. Based on MODIS gross primary productivity (GPP), evapotranspiration (ET) data and meteorological data, in this study, we estimated eWUE in different seasons in Inner Mongolia and used trend analysis and correlation analysis methods to analyze the relationship between eWUE in spring, summer and autumn and the temperature–precipitation. From 2001 to 2020, in this region, the GPP and ET in spring, summer and autumn showed increasing trends. In addition, the growth rates of GPP and ET in spring and summer were higher than those in autumn. Under the combined effect of GPP and ET, eWUE in different seasons showed a significant decreasing trend (p < 0.05)—this is ascribed to the extent of ET increasing more than GPP, especially in summer, with the most obvious decreasing rate. In terms of spatial trend, in spring and summer, there is a decreasing trend from northeast to southwest. The effects of precipitation and temperature on the eWUE in Inner Mongolia were mainly negatively correlated in the northeastern part of Inner Mongolia with higher altitudes during the spring and autumn seasons. In total, 95.096% of the total area had positive correlations between eWUE and temperature in spring. In summer, the region in which the WUE of the vegetation had an inverse relationship with both the temperature and the amount of precipitation was the largest compared to these regions in spring and autumn.