The assessment of soil health relies on key parameters such as soil aggregates and organic matter content. Therefore, examining the impact of irrigation water ion composition and variations in salinity on soil aggregates and organic matter is imperative, which is key to developing a theoretical basis for the sustainable utilization of saline water resources, particularly in extremely arid regions. This experiment was conducted to investigate the impact of different irrigation water salinity treatments (T3: 3 g/L, T5: 5 g/L, and T7: 7 g/L) on the root zone soil of cotton fields. Each salinity treatment included three variations of the sodium adsorption ratio (SAR) at S10: 10 (mmol/L)^1/2, S15: 15 (mmol/L)^1/2, and S20: 20 (mmol/L)^1/2. Local freshwater irrigation served as the control, resulting in a total of 10 treatments. Our findings show that the soil Ca²⁺ and Mg²⁺ content increased with higher irrigation water salinity but decreased with increasing irrigation water SAR. The relative macroaggregate stability and the content of water-stable macroaggregates and soil organic matter (SOM) decreased as the irrigation water salinity and SAR increased. In comparison to T3S20, T5S10 did not improve the soil Na⁺ content but significantly increased the soil Ca²⁺ content by 147.76%, while the water-stable aggregate and SOM saw a notable increase of 7.66% and 9.86%, respectively. Reducing the SAR in brackish water lessens its negative impact on soil aggregates in cotton fields. This is primarily because Ca²⁺ counteracts the dispersive effect of high Na⁺ concentrations and promotes aggregate formation. Irrigation water with a salinity of 3 g/L and an SAR of 10 (mmol/L)^1/2 positively affected the stabilization of soil aggregates and organic matter.

Reasonable development and utilization of brackish-water resources can alleviate the pressure of freshwater scarcity in dryland areas and safeguard crop growth, but there are significant differences in brackish-water ions in different regions. Thus, exploring the mechanism of brackish-water irrigation considering brackish-water ionic differences on the growth and development of saline and alkaline dryland crops has an important production guidance value. In this study, the ionic differences in irrigated brackish water were characterized by sodium adsorption ratio using under-membrane drip-irrigated cotton as the research object, and three levels of mineralized irrigation water were designed, which were 3 g·L⁻¹ (T3), 5 g·L⁻¹ (T5), and 7 g·L⁻¹ (T7), respectively. Three different levels of sodium adsorption ratio (SAR) were set under each level of mineralization, which were 10 (mmol·L⁻¹)¹/² (S10), 15 (mmol·L⁻¹)¹/² (S15), and 20 (mmol·L⁻¹)¹/² (S20). The local freshwater irrigation was used as a control treatment. The results showed that brackish-water irrigation increased soil salt accumulation and soil water content, induced oxidative damage and disruption of ionic homeostasis in the cells, and decreased leaf photosynthetic rate. Brackish-water irrigation also significantly reduced dry matter mass by 11.04–50.12%. Reduced irrigation water SAR (S10 and S15) enhanced antioxidant enzyme activities such as superoxide dismutase (SOD), peroxidase (POD), and catalase (CAT), and reduced malondialdehyde (MDA) content by 14.29% and 9.09%, respectively, compared with high irrigation water SAR (S20). Leaf K⁺ uptake was increased by 5.29% and 1.57% in S10 and S15, respectively, compared with S20, while Na⁺ uptake was significantly suppressed. The K⁺/Na⁺ ratio increased by 45.07%, which resulted in improved leaf photosynthetic efficiency by 25.25% and 11.91%, and significantly enhanced dry matter accumulation by 24.81% and 11.20%, respectively. In addition, compared with T3S20, the T5S10 treatment reduced the irrigation water SAR. It contributed to a significant increase in SOD, POD, and CAT activities by 30.42%, 60.70%, and 99.20%, respectively, and in plant K⁺ content and K⁺/Na⁺ by 2.48% and 38.85%, respectively, although the irrigation water mineralization increased by 66.67%. Reducing SAR could enhance photosynthesis and dry matter accumulation through the dual regulation of “antioxidant damage + ion homeostasis” in salt-stressed cotton, laying a foundation for the realization of stable and high yields of cotton under brackish-water irrigation, and providing a new perspective for the management of brackish-water resources and the sustainable development of agriculture in Xinjiang and other arid regions.

Accurate estimation of crop evapotranspiration (ET) is essential for achieving efficient agricultural water use in the North China Plain. Although machine learning techniques have demonstrated considerable potential for ET simulation, a systematic evaluation of model-architecture suitability and hyperparameter optimization strategies specifically for summer soybean ET estimation in this region is still lacking. To address this gap, we systematically compared several machine learning architectures and their hyperparameter optimization schemes to develop a high-accuracy daily ET model for summer soybean in the North China Plain. Synchronous observations from a large-scale weighing lysimeter and an automatic weather station were first used to characterize the day-to-day dynamics of soybean ET and to identify the key driving variables. Four algorithms—support vector regression (SVR), Random Forest (RF), extreme gradient boosting (XGBoost), and a stacking ensemble—were then trained for ET simulation, while Particle Swarm Optimization (PSO), Genetic Algorithms (GAs), and Randomized Grid Search (RGS) were employed for hyperparameter tuning. Results show that solar radiation (R_S), maximum air temperature (T_max), and leaf area index (LAI) are the dominant drivers of ET. The Stacking-PSO-F3 combination, forced with Rs, T_max, LAI, maximum relative humidity (RH_max), and minimum relative humidity (RH_min), achieved the highest accuracy, yielding R² values of 0.948 on the test set and 0.900 in interannual validation, thereby demonstrating excellent precision, stability, and generalizability. The proposed model provides a robust technical tool for precision irrigation and regional water resource optimization.

Plastic mulching is widely used in arid and semi-arid cotton systems to improve soil hydrothermal conditions and water–nutrient use efficiency. However, residual mulch and its potential contribution to microplastic inputs pose growing environmental and soil-quality risks, highlighting the need for high-resolution and automated approaches to support plastic waste management, targeted retrieval, and precision field operations. Taking a mulched cotton field in Alar, Xinjiang, as the study area, this study proposes a novel plastic mulch extraction method that integrates Unmanned Aerial Vehicle (UAV)-based hyperspectral imagery with deep learning semantic segmentation. The Jeffries–Matusita (JM) distance was employed to select highly separable optimal bands and their combinations for discriminating plastic mulch, bare soil, and cotton canopy, which were then used to drive UNet, DeepLabV3+, and PSPNet models for plastic mulch mapping. The results indicate that the PSPNet model driven by the 402 nm single-band reflectance, Normalized Difference Index (NDI) (861 nm, 410 nm), and NDI (757 nm, 676 nm) achieved the best performance for plastic mulch identification (Intersection over Union (IoU) = 80.28%), significantly outperforming the RGB-based model (IoU = 76.51%). This study enables accurate, spatially explicit assessments of residual mulch, providing actionable evidence for plastic waste monitoring and management, while supporting sustainable agriculture and precision farmland management.

In global drought-prone cotton-growing (Gossypium hirsutum L.) areas, saline water irrigation has become a key strategy to alleviate the shortage of freshwater resources. Against this backdrop, the synergistic effect of mineralization degree (MD) and sodium adsorption ratio (SAR) on the rhizosphere microecological regulation mechanism remains unclear. To address this issue, this study constructed an experimental framework of the interaction between MD and SAR, aiming to explore their effects on the bacterial community structure in the rhizosphere of cotton and the soil environment. The soil type in the study area is saline–sodic sandy loam. In the experimental design, three MD levels (3 g/L, 5 g/L, 7 g/L) were set, and under each mineralization condition, three SAR levels (10 (mmol/L)^1/2, 15 (mmol/L)^1/2, 20 (mmol/L)^1/2) were arranged. In addition, local freshwater irrigation was used as the control group (CG), resulting in a total of 10 treatment schemes. The aim of this study was to investigate the effects of varying levels of irrigation water MD and SAR on the structure of bacterial communities in cotton rhizosphere soil and the soil environment. The results indicated that saline water irrigation could enhance the diversity and richness of the bacterial community in the rhizosphere soil of cotton and alter its community structure. Under treatment with the MD of 3 g/L and the SAR of 10 (mmol/L)^1/2, the diversity and richness of the bacterial community in the cotton rhizosphere reached their peak levels. Compared with the CG, the Chao1 index significantly increased by 260 units, while the Shannon index increased by 0.464. When the MD does not exceed 5 g/L, reducing SAR can enhance the diversity and network stability of the rhizosphere bacterial community, thereby synergistically promoting the accumulation of soil nutrients. The key soil environmental factors driving changes in the rhizosphere bacterial community structure mainly include soil moisture content, total nitrogen, nitrate nitrogen, and total organic carbon. The concentrations of total nitrogen, nitrate nitrogen, available phosphorus, and available potassium significantly increased by 19.66%, 26.10%, 89.41%, and 49.76% respectively (p < 0.05). This study provides a theoretical basis for sustainable irrigation and microbial regulation strategies in saline–alkali cotton fields at the theoretical level, and offers a new perspective for revealing the mutual feedback mechanism between bacterial community assembly and soil environment under saline conditions. From a practical perspective, this research offers valuable hands-on experience for optimizing agricultural ecological management in saline–alkali sandy loam soils, thereby contributing to the sustainable development of agriculture on such lands.