Quan Xu

Accurate crop classification requires effective representation of crop-growth dynamics and traceable classification decisions. This study proposes a prototype-matching framework guided by quantitative temporal and phenological features to establish explicit relationships between crop-growth representations and class-level references. Using multi-temporal Sentinel-2 imagery from an oasis agricultural region in Manas County, Xinjiang, China, four major crops were investigated: cotton, maize, spring wheat, and winter wheat. The framework integrates explicit temporal statistics, quantitative phenological descriptors, and their corresponding deep representations into a unified feature space. Class prototypes are constructed from the resulting representations, and final crop labels are assigned through explicit sample–prototype similarity or distance comparisons. Prototype-space relationships are further analysed to quantify class separability and examine potential classification ambiguity. The results demonstrate that temporal representations provide stronger class separation than phenological representations, while their integration enables continuous temporal dynamics and structured phenological characteristics to be examined within a unified prototype space. Prototype-space analysis reveals clearer separation for cotton and maize, whereas spring wheat exhibits the smallest similarity and distance margins. In the primary field-level classification experiment, the framework achieves an overall accuracy of 96.03%, a Kappa coefficient of 0.9356, a Balanced Accuracy of 86.05%, and a Macro-F1 of 86.26%. In a separate experiment under common training conditions, prototype matching achieves a Balanced Accuracy of 91.36% and a Macro-F1 of 89.53%, exceeding Transformer and random forest by 7.36 and 12.78 percentage points in Balanced Accuracy, respectively. The improvements are particularly evident for spring wheat. These findings demonstrate that the framework connects quantitative crop-growth representation with explicit prototype-based classification while providing measurable evidence for interpreting class-specific discrimination and classification ambiguity.

In arid regions, potentially toxic elements (PTEs) can accumulate in oasis farmland soils, posing risks to both ecosystems and human health and threatening the long-term sustainability of agricultural production. However, we still lack a clear understanding of how multiple elements co-accumulate and what non-linear processes drive their buildup. Here, we investigated typical agricultural soils in the Aksu area of Xinjiang. We measured 12 elements (As, Cr, Cu, Ni, Zn, Co, V, Se, F, Ba, Sn, Mn) in 28 surface samples. To assess the pollution levels, we used three indices: the single-factor index (P_i), the geo-accumulation index (I_geo), and the Nemerow composite index. Source apportionment was performed with positive matrix factorization (PMF). We then built an XGBoost model to predict the Nemerow index, and applied SHAP (Shapley additive explanations) to quantify the marginal contribution and non-linear response of each element. Our results show that the average concentrations of Se, F, and As are 1.47, 1.27, and 1.35 times the national background values, respectively. The exceedance rate (P_i > 1) for these elements ranges from 78.6% to 92.9%. Nevertheless, the overall pollution is mild: only one out of 28 sampling sites (3.6%) falls into the moderately polluted category. PMF resolved three major sources: (1) parent material plus evaporation enrichment (F, Mn, and Ba, ~45% of the total contribution); (2) agricultural and anthropogenic activities (As, Cr, V, Zn, ~40%); and (3) local industrial or waste inputs (Sn and Ba, ~15%). The XGBoost model shows good predictive performance on the test set (R² = 0.864, RMSE = 0.104). SHAP analysis reveals that Se, F, and As are the main drivers of the composite pollution index. Se has a clear threshold: once its concentration goes above 0.3 mg·kg⁻¹, its positive contribution jumps sharply. Overall, the farmland soils in Aksu show mild enrichment of several elements, with Se and F as the main indicators. Evaporation enrichment and farming practices are the dominant processes behind this enrichment. The integrated framework—pollution indices, PMF source apportionment, XGBoost prediction, and SHAP interpretation—provides a scientifically sound way to manage soil environments in arid regions.

The Aksu River Basin oasis, a typical arid ecological environment, faces considerable ecological and public health risks from fluoride accumulation in soil and groundwater. However, systematic investigations integrating soil–groundwater co-enrichment mechanisms with multi-pathway health risk assessments under environmentally relevant conditions remain scarce. We examined spatial fluoride distribution in the soil–groundwater system, associated health risks, and key driving mechanisms. Based on 2009 soil and 264 groundwater samples, we applied radial basis function (RBF) interpolation, Getis-Ord G_i* hotspot analysis, the geo-accumulation index (I_geo), the ecological risk index (ER), and the U.S. EPA health risk assessment model to evaluate pollution levels, ecological risks, and health impacts on adults and children. Spearman’s correlation analysis revealed relationships with 12 environmental factors, including topography, climate, soil properties, and vegetation. Key results are as follows: (1) High-fluoride soils (>700 mg·kg⁻¹) clustered in the eastern basin, while groundwater fluoride increased along a west–east gradient, with RBF interpolation yielding the highest accuracy; (2) soil fluoride was generally “unpolluted–moderate risk” (mean I_geo = −0.14, ER = 1.40), whereas groundwater posed the primary health risk, with a mean hazard quotient of 1.83 for children via drinking water, indicating non-carcinogenic risk; (3) soil enrichment was driven by evaporation–concentration–alkaline activation, while groundwater enrichment followed a convergence–concentration–evaporation mechanism, being negatively correlated with elevation. Groundwater fluoride presents a clear health risk, particularly to children, arising from high geological background levels and intense evaporation. Managing fluoride pollution and safeguarding drinking water quality in arid oasis regions is consequential. These findings provide a scientific basis for sustainable groundwater management and public health protection in arid oases.

Land-use changes significantly influence carbon storage capacity by altering the structure, layout, and function of terrestrial ecosystems. Predicting the relationship between future land-use changes and carbon storage is essential for optimizing land-use patterns and making rational, ecology-based decisions. Using multi-period land-use data from Xinjiang, we analyzed the spatial pattern of carbon storage. Based on land-use change patterns in Xinjiang from 2000 to 2020, we coupled the Markov-Future Land Use Simulation (FLUS)-Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model to simulate and predict land-use spatial patterns in Xinjiang for 2035 under two scenarios: natural growth and ecological protection. Carbon storage and its spatiotemporal dynamic changes under these scenarios were evaluated, and the Geodetector was employed to analyze the spatial heterogeneity of carbon storage from a statistical perspective, revealing the influence of various driving factors. The results showed that: (1) From 2000–2020, grassland and unused land were the primary land-use types in Xinjiang, accounting for over 28.85% and 60.17% of the total area, respectively. By 2035, cropland, forest, water, and construction land areas are expected to increase, while grassland and unused land areas are projected to decrease. Under the ecological protection scenario, cropland, forest land, and grassland—major main contributors to carbon storage—will be effectively conserved to some extent. (2) From 2000 to 2020, Xinjiang’s carbon storage capacity exhibited an overall increasing trend, with a cumulative increase of 137.515×10⁵ t and a growth rate of 1.58%. However, this capacity is projected to decline by 2035, with an estimated reduction of 168.344×10⁵ t compared to that in 2020. Ecological protection is anticipated to mitigate this decline, increasing carbon storage by 13.227×10⁵ t relative to the natural growth scenario. (3) Geodetector analysis indicated that land-use types had the greatest carbon storage explanatory power for carbon storage (q = 0.80), followed by soil types (q = 0.41), net primary productivity (q = 0.32), and geomorphology (q = 0.22). This highlights land-use types as the most critical environmental factor determining the spatial pattern of carbon storage. These findings provide scientific insights and recommendations for the sustainable development management and the enhancement of carbon storage functions.

Soil nutrient levels play a crucial role in determining crop yield. A comprehensive understanding of the spatial distribution patterns and evaluation grades of soil nutrients is of significant practical importance for informed fertilization practices, enhancing crop production, and optimizing agricultural land utilization. This study focuses on the urban area of Kashi Prefecture in Xinjiang as a case study. Utilizing soil sample data, GIS spatial interpolation analysis was conducted, incorporating plot boundary information to propose a comprehensive evaluation method for assessing soil nutrient levels at the plot level. Experimental findings revealed the following: (1) The average values of soil organic matter (SOM), total nitrogen (AN), total potassium (AK), and total phosphorus (AP) in the study area were determined to be 13.3 g/kg, 0.74 g/kg, 0.33 g/kg, and 0.03 g/kg, respectively. Among these, AN and SOM were classified as the fourth grade, indicating relatively deficient levels, while AK and AP were classified as the first and second grade, indicating relatively abundant levels. (2) The comprehensive evaluation of soil nutrient grades in the study area primarily fell within the third, fourth, and second grades, representing areas of 29.08 km², 25 km², and 4.05 km², accounting for 50.03%, 43%, and 6.97% of the total area, respectively. (3) The evaluation results of soil nutrient levels at the plot level emphasized the boundary characteristics and provided a more refined assessment grade. This evaluation method is better suited to meet the practical production requirements of farmers and is considered feasible. The outcomes of this study can serve as a reference for precision agriculture management.

The mixing of cotton seeds of different cultivars and qualities can lead to differences in growth conditions and make field management difficult. In particular, except for yield loss, it can also lead to inconsistent cotton quality and poor textile product quality, causing huge economic losses to farmers and the cotton processing industry. However, traditional cultivar identification methods for cotton seeds are time-consuming, labor-intensive, and cumbersome, which cannot meet the needs of modern agriculture and modern cotton processing industry. Therefore, there is an urgent need for a fast, accurate, and non-destructive method for identifying cotton seed cultivars. In this study, hyperspectral images (397.32 nm—1003.58 nm) of five cotton cultivars, namely Jinke 20, Jinke 21, Xinluzao 64, Xinluzao 74, and Zhongmiansuo 5, were captured using a Specim IQ camera, and then the average spectral information of seeds of each cultivar was used for spectral analysis, aiming to estab-lish a cotton seed cultivar identification model. Due to the presence of many obvious noises in the < 400 nm and > 1000 nm regions of the collected spectral data, spectra from 400 nm to 1000 nm were selected as the representative spectra of the seed samples. Then, various denoising techniques, including Savitzky-Golay (SG), Standard Normal Variate (SNV), and First Derivative (FD), were applied individually and in combination to improve the quality of the spectra. Additionally, a successive projections algorithm (SPA) was employed for spectral feature selection. Based on the full-band spectra, a Partial Least Squares-Discriminant Analysis (PLS-DA) model was established. Furthermore, spectral features and textural features were fused to create Random Forest (RF), Convolutional Neural Network (CNN), and Extreme Learning Machine (ELM) identification models. The results showed that: (1) The SNV-FD preprocessing method showed the optimal denoising performance. (2) SPA highlighted the near-infrared region (800–1000 nm), red region (620–700 nm), and blue-green region (420–570 nm) for identifying cotton cultivar. (3) The fusion of spectral features and textural features did not consistently improve the accuracy of all modeling strategies, suggesting the need for further research on appropriate modeling strategies. (4) The ELM model had the highest cotton cultivar identification accuracy, with an accuracy of 100% for the training set and 98.89% for the test set. In conclusion, this study successfully developed a highly accurate cotton seed cultivar identification model (ELM model). This study provides a new method for the rapid and non-destructive identification of cotton seed cultivars, which will help ensure the cultivar consistency of seeds used in cotton planting, and improve the overall quality and yield of cotton.

Timely and accurate information on crop planting structures is crucial for ensuring national food security and formulating economic policies. This study presents a method for high-precision crop classification using time-series UAV (unmanned aerial vehicle) images. Before constructing the time-series UAV images, Euclidian distance (ED) was utilized to calculate the separability of samples under various vegetation indices. Second, co-occurrence measures and the gray-level co-occurrence matrix (GLCM) were employed to derive texture characteristics, and the spectral and texture features of the crops were successfully fused. Finally, random forest (RF) and other algorithms were utilized to classify crops, and the confusion matrix was applied to assess the accuracy. The experimental results indicate the following: (1) Time-series UAV remote sensing images considerably increased the accuracy of crop classification. Compared to a single-period image, the overall accuracy and kappa coefficient increased by 26.65% and 0.3496, respectively. (2) The object-oriented classification method was better suited for the precise classification of crops. The overall accuracy and kappa coefficient increased by 3.13% and 0.0419, respectively, as compared to the pixel-based classification results. (3) RF obtained the highest overall accuracy and kappa coefficient in both pixel-based and object-oriented crop classification. RF’s producer accuracy and user accuracy for cotton, spring wheat, cocozelle, and corn in the study area were both more than 92%. These results provide a reference for crop area statistics and agricultural precision management.

This study analysed the spatial pattern change of land use from 2005 to 2015 in Xinjiang and proposed a Markov–Future Land Use Simulation composite model to predict land-use change by 2025 under natural growth and ecological protection scenarios. The Criteria Importance Though Intercrieria Correlation method was proposed to construct the landscape ecological risk index based on land-use data. By calculating the risk index centroid and standard deviation ellipses, the spatio-temporal patterns and changing characteristics of landscape ecological risk in different scenarios in 2005, 2015, and 2025 were evaluated, and the driving forces of their evolution were also analysed. The results indicated that: (1) The characteristics of land use pattern change under the natural growth scenario from 2015 to 2025 are similar to those from 2005 to 2015. Under an ecological protection scenario, restricting the expansion of construction land, forest land, and grassland, which are the central ecological lands, can be effectively protected. Compared to the natural growth scenario, these areas increased by 507 and 724 km², respectively. (2) From 2005 to 2015, landscape ecological risk in Xinjiang generally showed a decreasing trend. Compared to the natural growth scenario in 2025, ecological protection can effectively reduce the ecological risk of the landscape. The highest, higher, and medium ecological risks were reduced by 0.39%, 3.11%, and 4.43%, respectively, while the areas with the lowest and lower ecological risks increased by 0.16% and 7.77%, respectively. (3) Under the natural growth scenario from 2005 to 2025, the centroid of landscape ecological risk in Xinjiang generally shifted to the southwest. To some extent, the ecological protection scenario can make the distribution of the highest, the higher, and the medium ecological risk areas more dispersed and the distribution of the lower ecological risk areas more concentrated. (4) Temperature is positively correlated with landscape ecological risk, while rainfall, Digital Elevation Model, slope, and aspect are negatively correlated with landscape ecological risk. There is also a correlation between soil types and landscape ecological risk. This research can reference the theory and method of landscape ecological risk and provide decision support for the sustainable development of the ecological environment of Xinjiang.