Large-scale soil salinity surveys are time-costly and labor-intensive, and it is also more difficult to investigate historical salinity, while in arid and semi-arid regions, the investigation of the spatial and temporal characteristics of salinity can provide a scientific basis for the scientific prevention of salinity, With this objective, this study uses multi-source data combined with ensemble learning and Google Earth Engine to build a monitoring model to observe the evolution of salinization in the Werigan–Kuqa River Oasis from 1996 to 2021 and to analyze the driving factors. In this experiment, three ensemble learning models, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), were established using data collected in the field for different years and some environmental variables, After the accuracy validation of the model, XGBoost had the highest accuracy of salinity prediction in this study area, with RMSE of 17.62 dS m⁻¹, R² of 0.73 and RPIQ of 2.45 in the test set. In this experiment, after Spearman correlation analysis of soil Electrical Conductivity (EC) with environmental variables, we found that the near-infrared band in the original band, the DEM in the topographic factor, the vegetation index based on remote sensing, and the salinity index soil EC had a strong correlation. The spatial distribution of salinization is generally characterized by good in the west and north and severe in the east and south. Non-salinization, light salinization, and moderate salinization gradually expanded southward and eastward from the interior of the western oasis over 25 years. Severe and very severe salinization gradually shifted from the northern edge of the oasis to the eastern and southeastern desert areas during the 25 years. The saline soils with the highest salinity class were distributed in most of the desert areas in the eastern part of the Werigan–Kuqa Oasis study area as well as in smaller areas in the west in 1996, shrinking in size and characterized by a discontinuous distribution by 2021. In terms of area change, the non-salinized area increased from 198.25 in 1996 to 1682.47 km² in 2021. The area of saline soil with the highest salinization level decreased from 5708.77 in 1996 to 2246.87 km² in 2021. overall, the overall salinization of the Werigan–Kuqa Oasis improved.

With high spatial resolution remote sensing images being increasingly used in precision agriculture, more details of the row structure of row crops are captured in the corresponding images. This phenomenon is a challenge for the estimation of the fractional vegetation cover (FVC) of row crops. Previous studies have found that there is an overestimation of FVC for the early growth stage of vegetation in the current algorithms. When the row crops are a form in the early stage of vegetation, their FVC may also have overestimation. Therefore, developing an algorithm to address this problem is necessary. This study used World-View 3 images as data sources and attempted to use the canopy reflectance model of row crops, coupling backward propagation neural networks (BPNNs) to estimate the FVC of row crops. Compared to the prevailing algorithms, i.e., empirical method, spectral mixture analysis, and continuous crop model coupling BPNNs, the results showed that the calculated accuracy of the canopy reflectance model of row crops coupling with BPNNs is the highest performing (RMSE = 0.0305). Moreover, when the structure is obvious, we found that the FVC of row crops was about 0.5–0.6, and the relationship between estimated FVC of row crops and NDVI presented a strong exponential relationship. The results reinforced the conclusion that the canopy reflectance model of row crops coupled with BPNNs is more suitable for estimating the FVC of row crops in high-resolution images.

Soil salinization is a serious global issue; by 2050, without intervention, 50% of the cultivated land area will be affected by salinization. Therefore, estimating and predicting future soil salinity is crucial for preventing soil salinization and investigating potential arable land resources. In this study, several machine learning methods (random forest (RF), Light Gradient Boosting Machine (LightGBM), Gradient Boosting Decision Tree (GBDT), and eXtreme Gradient Boosting (XGBoost)) were used to estimate the soil salinity in the Werigan–Kuqa River Delta Oasis region of China from 2001 to 2021. The cellular automata (CA)–Markov model was used to predict soil salinity types from 2020 to 2050. The LightGBM method exhibited the highest accuracy, and the overall prediction accuracy of the methods had the following order: LightGBM > RF > GBRT > XGBoost. Moderately saline, severely saline, and saline soils were dominant in the east and south of the research area, while non-saline and mildly saline soils were widely distributed in the inner oasis area. A marked decreasing trend in the soil salt content was observed from 2001 to 2021, with a decreasing rate of 4.28 g/kg·10 a⁻¹. The primary change included the conversion of mildly and severely saline soil types to non-saline soil. The generalized difference vegetation index (51%), Bio (30%), and temperature vegetation drought index (27%) had the greatest influence, followed by variables associated with soil attributes (soil organic carbon and soil organic carbon stock) and terrain (topographic wetness index, slope, aspect, curvature, and topographic relief index). Overall, the CA–Markov simulation resulted exhibited suitable accuracy (kappa = 0.6736). Furthermore, areas with non-saline and mildly saline soils will increase while areas with other salinity levels will continue to decrease from 2020 to 2050. From 2046 to 2050, numerous areas with saline soil will be converted to non-saline soil. These results can provide support for salinization control, agricultural production, and soil investigations in the future. The gradual decline in soil salinization in the research area in the past 20 years may have resulted from large-scale land reclamation, which has turned saline alkali land into arable land and is also related to effective measures taken by the local government to control salinization.

To assess the carbon balance of terrestrial ecosystems, it is crucial to consider the net primary productivity (NPP) of vegetation. Understanding the response of NPP in Xinjiang’s vegetation to climate factors and human activities is essential for ecosystem management, the Belt and Road Initiative, and achieving carbon neutrality goals. Based on the CASA model, this study uses meteorological data, DEM data, and land cover data, employing trend analysis and partial derivative analysis methods to investigate the temporal trends and spatial distribution of NPP in Xinjiang from 2000 to 2020. Additionally, it quantifies the contributions of climate factors and human activities to NPP fluctuations. The key findings are: (1) The average annual NPP is 101.52 gC/m², with an upward trend, showing an overall growth rate of 0.447 gC/m²/yr. Spatially, NPP is higher in northern Xinjiang than in the south, and in mountainous areas compared to basins. (2) Over 21 years, climate factors contributed an average of 1.054 gC/m²/yr, while human activities contributed 0.239 gC/m²/yr to NPP changes. Among climate factors, temperature, precipitation, and sunshine duration contributed 0.003, 0.169, and 0.588 gC/m²/yr, respectively, all showing positive effects on NPP. (3) Forests have the highest average NPP at 443.96 gC/m², with an annual growth rate of 2.69 gC/m²/yr. When forest is converted to cropland, the net loss in NPP is −1.94 gC/m², and the loss is even greater in conversion to grassland, reaching −17.33 gC/m². (4) The changes in NPP are driven by both climate factors and human activities. NPP increased in 77.25% of the area, while it decreased in 22.69%. Climate factors have a greater positive impact than human activities.

In order to investigate the mechanism of environmental factors in soil salinization, this study focused on analyzing the temporal-spatial variation of soil salinity in the Ogan-Kuqa River Oasis in Xinjiang, China. The research aimed to predict soil salinity using a combination of satellite data, environmental covariates, and advanced modeling techniques. Firstly, Boruta and ReliefF algorithms were employed to select variables that significantly affect soil salinity from the Sentinel-2 satellite data and environmental covariates. Subsequently, a soil salinity inversion model was established using three advanced strategies: comprehensive variable analysis, a Boruta-based variable selection algorithm, and a ReliefF-based variable selection algorithm. Each strategy was modeled using a Light Gradient Boosting Machine (LightGBM), an Extreme Learning Machine (ELM), and a Support Vector Machine (SVM). Finally, the Boruta-LightGBM strategy was proven to be the most effective in predicting soil electrical conductivity (EC), with a coefficient of determination ($R^2$) of 0.72 and a Root Mean Square Error (RMSE) of 12.49 ds/m. The experimental results show that the red-edge band index is the foremost variable in predicting soil salinity, succeeded by the salinity index and soil attribute data, while the topographic index has the least influence, which further demonstrates that proper variable selection could significantly improve model functionality and predictive precision. Furthermore, the Multiscale Geographically Weighted Regression (MGWR) model was utilized to reveal the influence and temporal-temporal-spatial heterogeneity of environmental factors such as soil organic carbon (SOC), precipitation (PRE), pH value, and temperature (TEM) on soil EC. This research offers not just a viable methodological framework for monitoring soil salinization but also new perspectives on the environmental drivers of soil salinity changes, which have implications for sustainable land management and provide valuable information for decision-making in soil salinity control and mitigation efforts.

Glaciers, often regarded as “frozen reservoirs”, play a crucial role in replenishing numerous rivers in arid regions, contributing to ecological balance and managing river flow. Recently, the rapid shrinkage of the glaciers in the East Tianshan Mountains has affected the water quantity in the Karez system. However, studies on glacier changes in this region are limited, and recent data are scarce. This study utilizes annual Landsat composite images from 1990 to 2022 obtained via the Google Earth Engine (GEE). It utilizes a ratio threshold approach in conjunction with visual analysis to gather the glacier dataset specific to the Turpan–Hami region. The Open Global Glacier Model (OGGM) is used to model the flowlines and mass balance of around 300 glaciers. The study analyzes the glacier change trends, distribution characteristics, and responses to climate factors in the Turpan–Hami region over the past 30 years. Additionally, future glacier changes through the end of the century are projected using CMIP6 climate data. The findings indicate that the following: (1) From 1990 to 2022, glaciers in the research area underwent considerable retreat. The total glacier area decreased from 204.04 ± 0.887 km² to 133.52 ± 0.742 km², a reduction of 70.52 km², representing a retreat rate of 34.56%. The number of glaciers also decreased from 304 in 1990 to 236 in 2022. The glacier length decreased by an average of 7.54 m·a⁻¹, with the average mass balance at −0.34 m w.e.·a⁻¹, indicating a long-term loss of glacier mass. (2) Future projections to 2100 indicate that under three climate scenarios, the area covered by glaciers could diminish by 89%, or 99%, or even vanish entirely. In the SSP585 scenario, glaciers are projected to nearly disappear by 2057. (3) Rising temperatures and solar radiation are the primary factors driving glacier retreat in the Turpan–Hami area. Especially under high emission scenarios, climate warming will accelerate the glacier retreat process.