Vegetation in natural desert hinterland oases is an important component of terrestrial ecosystems. Determining how desert vegetation responds to natural variability is critical for a better understanding of desertification processes and their future development. The aim of this study is to characterize the spatial distribution of vegetation in the natural desert hinterland and to reveal how different environmental factors affect vegetation changes. Taking a Taklamakan Desert hinterland oasis as our research object, we analyzed the effects of different environmental factors on desert vegetation using a time-series normalized difference vegetation index (NDVI) combined with meteorological, topographic, and hydrological data, including surface water and groundwater data. Vegetation was distributed in areas with high surface water frequency, shallow groundwater levels, relatively flat terrain, and dune basins. NDVI datasets show greening trends in oasis areas over the past 20 years. The frequency of surface water distribution influences water accessibility and effectiveness and shapes topography, thus affecting the spatial distribution pattern of vegetation. In this study, areas of high surface water frequency corresponded with vegetation distribution. The spatial distribution of groundwater depth supports the growth and development of vegetation, impacting the pattern of vegetation growth conditions. Vegetation is most widely distributed in areas where the groundwater burial depth is 3.5–4.5 m. This study provides data for restoring riparian vegetation, ecological water transfer, and sustainable development.

This study investigates a multimodal deep learning framework that integrates unmanned aerial vehicle (UAV) multispectral imagery with meteorological data to predict cotton yield. The study analyzes the impact of different neural network architectures, including the CNN feature extraction layer, the depth of the fully connected layer, and the method of integrating meteorological data, on model performance. Experimental results show that the model combining UAV multispectral imagery with weekly meteorological data achieved optimal yield prediction accuracy (RMSE = 0.27 t/ha; R² = 0.61). Specifically, models based on AlexNet (Model 9) and CNN2conv (Model 18) exhibited superior accuracy. ANOVA results revealed that deeper fully connected layers significantly reduced RMSE, while variations in CNN architectural complexity had no statistically significant effect. Furthermore, although the models exhibited comparable prediction accuracy (RMSE: 0.27–0.33 t/ha; R²: 0.61–0.69 across test datasets), their yield prediction spatial distributions varied significantly (e.g., Model 9 predicted a mean yield of 3.88 t/ha with a range of 2.51–4.89 t/ha, versus Model 18 at 3.74 t/ha and 2.33–4.76 t/ha), suggesting the need for further evaluation of spatial stability. This study underscores the potential of deep learning models integrating UAV and meteorological data for precision agriculture, offering valuable insights for optimizing spatiotemporal data integration strategies in future research.

Understanding the water use characteristics of vegetation is crucial for guiding the rational allocation of water resources and the restoration of sustainable vegetation in natural oases in arid desert areas. To analyze the water use characteristics of Populus euphratica Oliv. and Tamarix chinensis Lour. at different stages of growth in the Daliyabuyi natural pristine oasis in northwestern China, the δ¹⁸O values of plant xylem of 15 sample trees with different sizes per species, potential water sources (i.e., river water, soil water, and groundwater), and the δ¹³C values of plant leaves of sample trees were measured in August 2019 and June 2020. The results show that the δ¹⁸O values of the xylem water of P. euphratica at different growth stages were similar, but water uptake proportions from deep soil water changed in P. euphratica trees at different growth stages between years with (2019) and without (2020) river water. In contrast, the main water source of young T. chinensis shrubs was deep soil water, and those of mature and overmature shrubs were deep soil water and groundwater in 2020. However, the plant leaf water use efficiency (WUE) of the P. euphratica and T. chinensis were higher without river water. Overall, the water uptake proportion from groundwater and the WUE for T. chinensis were higher than those for P. euphratica, and thus, T. chinensis was more dependent on groundwater. This means that vegetation types and growth stages are the essential factors to be considered in ecological restoration management, which can enhance the effectiveness of vegetation restoration strategies.

Understanding the effect of flooding on groundwater quality is imperative for oasis vegetation protection and local ecological environment development. We used geochemical and remote sensing inversion methods to evaluate the effects of flood recharge on the groundwater hydrochemical and geochemical processes in the Daliyaboy Oasis. Groundwater samples were collected from 30 ecological observation wells in the study area before (PRF) and after (POF) the flood. Except for small changes in HCO₃⁻ and K⁺ and a decrease in pH, ion levels were higher POF than PRF, and the water chemistry was essentially unchanged. In the POF groundwater, HCO₃⁻ was correlated with Cl⁻, Na⁺, Mg²⁺, total soluble solids (TDS), and electrical conductivity (EC), but not with SO₄²⁻, Ca²⁺, K⁺, or pH, and was positively correlated with all other variables, while the remaining variables, except for pH, were strongly positively correlated with each other. PRF water chemistry was controlled by silicate and evaporite mineral weathering and evaporation processes, resulting in high groundwater TDS, EC, and a major ion content, while POF major groundwater ions were regulated by mineral weathering and flood recharge. We demonstrated the high accuracy of remote sensing inversion, confirming this as a reliable method for evaluating groundwater chemistry. The results of the study help to reshape and predict the history of the regional hydrogeological environment and hydrogeochemical development, and provide a theoretical basis for assessing the rational use of local water resources and protecting the ecological environment.

Accurate and non-destructive monitoring of leaf chlorophyll content (LCC) is essential for assessing crop photosynthetic activity and nitrogen status in precision agriculture. This study introduces a phenology-aware machine learning framework that combines hyperspectral reflectance data with various regression models to estimate leaf chlorophyll content (LCC) in cotton at six key reproductive stages. Field experiments utilized synchronized spectral and SPAD measurements, incorporating spectral transformations—such as vegetation indices (VIs), first-order derivatives, and trilateration edge parameters (TEPs, a new set of geometric metrics for red-edge characterization)—for evaluation. Five regression approaches were evaluated, including univariate and multivariate linear models, along with three machine learning algorithms: Random Forest, K-Nearest Neighbor, and Support Vector Regression. Random Forest consistently outperformed the other models, achieving the highest R² (0.85) and the lowest RMSE (4.1) during the bud stage. Notably, the optimal prediction accuracy was achieved with fewer than five spectral features. The proposed framework demonstrates the potential for scalable, stage-specific monitoring of chlorophyll dynamics and offers valuable insights for large-scale crop management applications.