Frequent monitoring of crop moisture levels can significantly improve crop production efficiency and optimise water resource utilisation. The aim of the present study was to generate moisture status maps using thermal infrared imagery, centring on the development of a predictive model for the cotton leaf water potential. The model was constructed using particle swarm optimisation (PSO) in conjunction with the least squares support vector machine (LS-SVM). Traditional SVM models suffer from high computational complexity, long training times, and inequality constraints in predicting leaf water potential. To address such issues, the PSO algorithm was introduced to improve the performance of the LS-SVM model. The PSO-optimised LS-SVM model exhibited notable improvements in performance when evaluated on two distinct test datasets (Alaer and Tumushuke). The research results indicate that the predictive accuracy of the PSO-LS-SVM model significantly improved, as evidenced by an increase of 0.05 and 0.04 in the $R^2$ values, both of which reached 0.95. This improvement is reflected in the corresponding RMSE values, which were reduced to 0.100 and 0.103. Furthermore, a model was established based on data from three cotton growth stages, achieving high predictive accuracy even with fewer training samples. By using the PSO-LS-SVM model to predict leaf water potential information, the predicted data were mapped onto drone images, enabling the transformation of the leaf water potential from a point to an area. The present findings contribute to a more comprehensive understanding of the cotton leaf water potential by visually representing the spatial distribution of crop water status on a large scale. The results hold substantial significance for the improvement of crop irrigation management.

This study investigates the effects of varying durations of aerated irrigation, administered at a consistent frequency, on the growth of greenhouse grape seedlings and the structure of the rhizosphere soil microbial community. Using two-year-old ‘Flame Seedless’ grape seedlings as the test material, we established a control group with no aeration (CK) and three treatment groups with aeration durations of 10 min (T1), 20 min (T2), and 30 min (T3), respectively. We determined grape seedling growth under different aerating durations. Additionally, changes in the rhizosphere soil microbial community of the plants were analyzed using 16S and ITS high-throughput genome sequencing to further explore the correlation between microbial diversity and plant growth. The results revealed that: (1) Aerated irrigation significantly enhanced plant growth, with the T2 treatment yielding superior increases in plant height, above-ground dry weight, below-ground dry weight, total root length, and root volume compared to T1 and T3 treatments. (2) Aeration treatments notably elevated the Shannon and Chao1 indices of the rhizosphere soil fungal community, with the T2 treatment exhibiting the most substantial effects, and the Shannon index of the bacterial community was also significantly higher under the T2 treatment. (3) The T2 treatment significantly increased the relative abundance of beneficial aerobic bacterial genera such as Flavobacterium, Ellin6067, and Coniochaeta, while decreasing the relative abundance of detrimental fungal genera like Fusarium and Gibberella. In conclusion, a 20 min aeration duration can effectively promote grape seedling growth, enhance the diversity of rhizosphere soil microbial communities, increase beneficial aerobic microorganisms, and reduce harmful ones. This study provides a theoretical basis for optimizing aerated irrigation practices in facility grape cultivation.

In response to the challenges posed by soil degradation in the arid regions of Xinjiang, China, green and organic management practices have emerged as effective alternatives to conventional agricultural management methods, helping to mitigate soil degradation by promoting natural soil recovery and ecological balance. However, most of the existing studies focus on a single management practice or indicator and lack a systematic assessment of the effects of integrated orchard management in arid zones. This study aims to investigate how different agricultural management practices influence soil physicochemical properties and inter-root microbial communities in apple orchards in Xinjiang and to identify the main physicochemical factors affecting the composition of inter-root microbial communities. Inter-root soil samples were collected from apple orchards under green management (GM), organic management (OM), and conventional management (CM) in major apple-producing regions of Xinjiang. Microbial diversity and community composition of the samples were analyzed using high-throughput amplicon sequencing. The results revealed significant differences (p < 0.05) in soil physicochemical properties across different management practices. Specifically, GM significantly reduced soil pH and C:N compared with OM. Both OM and GM significantly decreased soil available nutrient content compared with CM. Moreover, GM and OM significantly increased bacterial diversity and changed the community composition of bacteria and fungi. Proteobacteria and Ascomycota were identified as the dominant bacteria and fungi, respectively, in all management practices. Linear discriminant analysis (LEfSe) showed that biomarkers were more abundant under OM, suggesting that OM may contribute to ecological functions through specific microbial taxa. Co-occurrence network analysis (building a network of microbial interactions) demonstrated that the topologies of bacteria and fungi varied across different management practices and that OM increased the complexity of microbial co-occurrence networks. Mantel test analysis (analyzing soil factors and microbial community correlations) showed that C:N and available potassium (AK) were significantly and positively correlated with the community composition of bacteria and fungi, and that C:N, soil organic carbon (SOC), and alkaline hydrolyzable nitrogen (AN) were significantly and positively correlated with the diversity of fungi. Redundancy analysis (RDA) further indicated that SOC, C:N, and AK were the primary soil physicochemical factors influencing the composition of microbial communities. This study provides theoretical guidance for the sustainable management of orchards in arid zones.

To achieve high-precision and high-efficiency estimation of the Leaf Area Index (LAI) of jujube trees using drone remote sensing, and to overcome the limitations of traditional vegetation index methods, such as saturation in the later stages of crop growth, sensitivity to background noise, and difficulty in capturing temporal dynamics, this study proposes a parallel hybrid deep learning framework using CNN-GRU. The model adaptively extracts spatial-spectral local features from drone RGB images through a convolutional neural network (CNN) branch, while a gated recurrent unit (GRU) branch learns the sequential evolution of LAI during key phenological periods. Finally, a meta-learner integrates spatial-temporal information for decision-making. To verify the model’s effectiveness and prediction performance, the study systematically collected multi-temporal ground-measured LAI data and synchronized drone remote sensing images during critical growth stages of jujube trees in two independent years: 2024 (Bachu, Xinjiang) and 2025 (Alaer, Xinjiang). A series of spectral and texture indices were extracted as model inputs. The experimental results show that the proposed CNN-GRU model exhibits excellent learning and fitting capabilities on the training set, with an R ² value of 0.839. On the test set, after optimization with data augmentation strategies, the model’s prediction accuracy is significantly improved, with prediction accuracy reaching its best level, with an R ² of 0.83 and an RMSE of 0.150. All error metrics outperform mainstream comparative models such as Transformer, KNN, MLP, and CNN. This study demonstrates that the hybrid deep learning architecture, combining spatial feature extraction and time-series modeling, is an effective approach for accurate and robust remote sensing inversion of crop LAI in complex agricultural scenarios, providing a reliable technical tool for the digital management of smart orchards and precise agricultural decision-making.