Soil moisture (SM) is a critical parameter in Earth’s water cycle, significantly impacting hydrological, agricultural, and meteorological research fields. The challenge of estimating surface soil moisture from synthetic aperture radar (SAR) data is compounded by the influence of vegetation coverage. This study focuses on the Weigan River and Kuche River Delta Oasis in Xinjiang, employing high-resolution Sentinel-1 and Sentinel-2 images in conjunction with a modified Water Cloud Model (WCM) and the grayscale co-occurrence matrix (GLCM) for feature parameter extraction. A soil moisture inversion method based on stacked ensemble learning is proposed, which integrates random forest, CatBoost, and LightGBM. The findings underscore the feasibility of using multi-source remote sensing data for oasis moisture inversion in arid regions. However, soil moisture content estimates tend to be overestimated above 10% and underestimated below 5%. The CatBoost model achieved the highest accuracy (R² = 0.827, RMSE = 0.014 g/g) using the top 16 feature parameter groups. Additionally, the R² values for Stacking1 and Stacking2 models saw increases of 0.008 and 0.016, respectively. Thus, integrating multi-source remote sensing data with Stacking models offers valuable support and reference for large-scale estimation of surface soil moisture content in arid oasis areas.

Soil salinization is a significant global threat to sustainable agricultural development, with soil salinity serving as a crucial indicator for evaluating soil salinization. Remote sensing technology enables large-scale inversion of soil salinity, facilitating the monitoring and assessment of soil salinization levels, thus supporting the prevention and management of soil salinization. This study employs multi-source remote sensing data, selecting 8 radar polarization combinations, 10 spectral indices, and 3 topographic factors to form a feature variable dataset. By applying a normalized weighted variable optimization method, highly important feature variables are identified. AdaBoost, LightGBM, and CatBoost machine learning methods are then used to develop soil salinity inversion models and evaluate their performance. The results indicate the following: (1) There is generally a strong correlation between radar polarization combinations and vegetation indices, and a very high correlation between various vegetation indices and the salinity index S3. (2) The top five feature variables, in order of importance, are Aspect, VH², Normalized Difference Moisture Index (NDMI), VH, and Vegetation Moisture Index (VMI). (3) The method of normalized weighted importance scoring effectively screens important variables, reducing the number of input feature variables while enhancing the model’s inversion accuracy. (4) Among the three machine learning models, CatBoost performs best overall in soil salt content (SSC) prediction. Combined with the top five feature variables, CatBoost achieves the highest prediction accuracy (R² = 0.831, RMSE = 2.653, MAE = 1.034) in the prediction phase. This study provides insights for the further development and application of methods for collaborative inversion of soil salinity using multi-source remote sensing data.

To reveal the spatiotemporal evolution characteristics and driving mechanisms of ecosystem patterns in the mine ecological restoration project area on the western margin of the Junggar Basin, spatial data of ecosystem types from 2015 to 2024 were utilized, and the evolution characteristics and driving factors were analyzed by comprehensively applying the PNTIL model, landscape pattern indices, and the Geodetector. The results indicated: (1) Approximately 70% of the study area was consistently occupied by bareland; a net increase of 163.52 km² (+61.63%) was recorded for grassland area, while a net decrease of 118.08 km² (−15.95%) was observed for farmland area. (2) For forest, grassland, and wetland ecosystems, the negative transformation rates were all higher than the positive transformation rates, and the highest negative transformation rate was recorded for grassland, at 8.56% (2020–2024). (3) At the landscape level, increases in patch number and patch density were observed; at the class level, fragmentation was increased for bareland and farmland, while grassland patches were found to be more aggregated. (4) Annual mean evapotranspiration (q = 0.746), per capita GDP (q = 0.677), and annual mean temperature (q = 0.518) were identified as the primary driving factors, and the interaction between annual mean evapotranspiration and annual mean precipitation was found to be the strongest interactive driving factor. The findings of this study can be used as a theoretical basis for similar historically abandoned mine ecological restoration project areas in terms of land use planning, ecological restoration practices, and sustainable development.