As an important economic crop, tomato is highly susceptible to diseases that, if not promptly managed, can severely impact yield and quality, leading to significant economic losses. Traditional diagnostic methods rely on expert visual inspection, which is not only laborious but also prone to subjective bias. In recent years, object detection algorithms have gained widespread application in tomato disease detection due to their efficiency and accuracy, providing reliable technical support for crop disease identification. In this paper, we propose an improved tomato leaf disease detection method based on the YOLOv10n algorithm, named BED-YOLO. We constructed an image dataset containing four common tomato diseases (early blight, late blight, leaf mold, and septoria leaf spot), with 65% of the images sourced from field collections in natural environments, and the remainder obtained from the publicly available PlantVillage dataset. All images were annotated with bounding boxes, and the class distribution was relatively balanced to ensure the stability of training and the fairness of evaluation. First, we introduced a Deformable Convolutional Network (DCN) to replace the conventional convolution in the YOLOv10n backbone network, enhancing the model’s adaptability to overlapping leaves, occlusions, and blurred lesion edges. Second, we incorporated a Bidirectional Feature Pyramid Network (BiFPN) on top of the FPN + PAN structure to optimize feature fusion and improve the extraction of small disease regions, thereby enhancing the detection accuracy for small lesion targets. Lastly, the Efficient Multi-Scale Attention (EMA) mechanism was integrated into the C2f module to enhance feature fusion, effectively focusing on disease regions while reducing background noise and ensuring the integrity of disease features in multi-scale fusion. The experimental results demonstrated that the improved BED-YOLO model achieved significant performance improvements compared to the original model. Precision increased from 85.1% to 87.2%, recall from 86.3% to 89.1%, and mean average precision (mAP) from 87.4% to 91.3%. Therefore, the improved BED-YOLO model demonstrated significant enhancements in detection accuracy, recall ability, and overall robustness. Notably, it exhibited stronger practical applicability, particularly in image testing under natural field conditions, making it highly suitable for intelligent disease monitoring tasks in large-scale agricultural scenarios.

The rapid and accurate estimation of the nitrogen content of fruit trees helps to achieve a precise management of orchards. Hyperspectral data were collected from leaves of apple tree canopies at different fertility stages through field experiments to investigate the relationship between the nitrogen content and spectral reflectance of apple canopy leaves. Two different preprocessing methods, Savitzky–Golay (SG) smoothing and multiple scattering correction (MSC), were used to extract the feature bands by combining the successive projection method (SPA) and the competitive adaptive weighting algorithm–partial least squares (CARS-PLS). The reflectance values of the feature bands screened via these two methods were used as inputs to construct the multi-factor inversion models of apple canopy leaf nitrogen content based on the long- and short-term memory (LSTM) network, the support vector regression (SVR) and the Least Squares Support Vector Machine Regression (RIME-LSSVM). The study compared the ability of three algorithmic models to estimate leaf nitrogen content, and the results showed that the model constructed with the reflectance values of the characteristic bands screened by the CARS-PLS algorithm as inputs was more effective in predicting the nitrogen content of leaves. Furthermore, the accuracy of the model constructed using RIME-LSSVM was significantly higher than that of the model constructed using the long- and short-term memory network and support vector regression, in which the coefficient of determination of the test set (R-squared) is 0.964 and the root-mean-squared error (RMSE) is 0.052. Finally, the CARS-PLS algorithm combined with the RIME-LSSVM model has a higher prediction accuracy. The study demonstrated the feasibility and reliability of hyperspectral techniques for the estimation of nitrogen content of apple leaves in the Aksu region.

Fractional Vegetation Cover (FVC) is an important indicator to evaluate the quality of the regional ecological environment. Alar City is a typical desert oasis region. Investigating the spatial and temporal changes in its vegetation cover at different stages is a guide to the ecological balance and sustainable green development of the Tarim River basin. Based on the Google Earth Engine (GEE) cloud platform, this study analyzed the spatial and temporal characteristics and trends of vegetation cover changes in Alar City from 1990 to 2020 using the Hurst index and coefficient of variation. The results show that the spatial distribution of vegetation in the study area in the last 30 years shows a wave-like characteristic with an overall apparent upward trend. The vegetation cover in the study area is predominantly increasing and the spatial distribution shows a phased and regional character. Compared with 1990, there is a significant increase in the area of cultivated land in 2020. Among them, the areas of vegetation growth mainly occur in the basin around the Tarim River. Human activities have weakened the influence of natural factors on FVC. The results of the study suggest that the GEE platform can be an effective tool for permanently monitoring vegetation.

Chlorophyll is crucial for pear tree growth and fruit quality. In order to integrate the unmanned aerial vehicle (UAV) multispectral vegetation indices and textural features to realize the estimation of the SPAD value of pear leaves, this study used the UAV multispectral remote sensing images and ground measurements to extract the vegetation indices and textural features, and analyze their correlation with the SPAD value of leaves during the fruit expansion period of the pear tree. Finally, four machine learning methods, namely XGBoost, random forest (RF), back-propagation neural network (BPNN), and optimized integration algorithm (OIA), were used to construct inversion models of the SPAD value of pear trees, with different feature inputs based on vegetation indices, textural features, and their combinations, respectively. Moreover, the differences among these models were compared. The results showed the following: (1) both vegetation indices and textural features were significantly correlated with SPAD values, which were important indicators for estimating the SPAD values of pear leaves; (2) combining vegetation indices and textural features significantly improved the accuracy of SPAD value estimation compared with a single feature type; (3) the four machine learning algorithms demonstrated good predictive ability, and the OIA model outperformed the single model, with the model based on the OIA inversion model combining vegetation indices and textural features having the best accuracy, with $R^2$ values of 0.931 and 0.877 for the training and validation sets, respectively. This study demonstrated the efficacy of integrating multiple models and features to accurately invert SPAD values, which, in turn, supported the refined management of pear orchards.

Multi-robot motion planning (MRMP) requires each robot to possess strong local planning capabilities while maintaining global consistency. However, existing research often fails to address both global and local planning simultaneously, resulting in conflicts in real-time path execution. The A* algorithm is widely used for global path planning due to its adaptability and search efficiency, while the Timed Elastic Band (TEB) algorithm excels in local trajectory optimization and real-time dynamic obstacle avoidance. This paper presents a novel motion planning framework integrating an improved A* algorithm with an enhanced TEB strategy to address both levels of planning collaboratively. The proposed improvements include the introduction of steering costs and dynamic weights into the A* algorithm to enhance path smoothness and efficiency, and a hierarchical obstacle treatment in TEB for improved local avoidance. Simulation and real-world experiments conducted with ROS confirmed the feasibility and effectiveness of the method. Compared to the traditional A* algorithm, the proposed framework reduces the average path length by 5.2%, shortens completion time by 11.5%, and decreases inflection points by 66.7%, demonstrating superior performance for multi-robot systems in dynamic environments.

In order to explore the optimal remote sensing salinity monitoring index model for the inversion of soil salinization in the Alar reclamation area, based on the Sentinel-2 images and field measured data, the salinity index 1 (SI1), the normalized difference vegetation index in a green–red band (GRNDVI), the normalized vegetation index of greenness (GNDVI), and the normalized difference vegetation index (NDVI) were selected to construct the remote sensing-based salinization 1 detection index (S1DI) model. Next, the cotton field soil salinization information in the Alar reclamation area was extracted, and the accuracy of the model was verified to obtain the optimal remote sensing salinity monitoring index model. The results show that the overall classification accuracy of the S1DI1 (SI1-GRNDVI), S1DI2 (SI1-GNDVI), S1DI3 (SI1-NDVI), and S1DI4 (SI1-DVI) models for salinity monitoring is 83.35%, 83.10%, 82.96%, and 80.25%, respectively. The S1DI1 model is most suitable for retrieving the degree of soil salinization in the cotton field in the Alar reclamation area, and the S1DI2, S1DI3, and S1DI4 models are also very useful for monitoring soil salinization in the Alar reclamation area. Using the S1DI1 model to invert the soil salinization level of the cotton fields in the Alar reclamation area, it was found that the cotton field in the reclamation area is dominated by non-saline soil, and the light saline soil and moderate saline soil are mainly distributed in the 9th and 12th clusters of the reclamation area. As the S1DI1 model possesses the highest accuracy in extracting the soil salinization information of the cotton fields in the Alar reclamation area, it can be used as a remote sensing salinity 1 monitoring index model for the inversion of the soil salinization of the cotton fields in the reclamation area, which is expected to provide an effective reference value for soil salinization monitoring.