Yi Shi

Wheat spike detection holds significant importance for agricultural production as it enhances the efficiency of crop management and the precision of operations. This study aims to improve the accuracy and efficiency of wheat spike detection, enabling efficient crop monitoring under resource-constrained conditions. To this end, a wheat spike dataset encompassing multiple growth stages was constructed, leveraging the advantages of MobileNet and ShuffleNet to design a novel network module, SeCUIB. Building on this foundation, a new wheat spike detection network, LGWheatNet, was proposed by integrating a lightweight downsampling module (DWDown), spatial pyramid pooling (SPPF), and a lightweight detection head (LightDetect). The experimental results demonstrate that LGWheatNet excels in key performance metrics, including Precision, Recall, and Mean Average Precision (mAP50 and mAP50-95). Specifically, the model achieved a Precision of 0.956, a Recall of 0.921, an mAP50 of 0.967, and an mAP50-95 of 0.747, surpassing several YOLO models as well as EfficientDet and RetinaNet. Furthermore, LGWheatNet demonstrated superior resource efficiency with a parameter count of only 1,698,529 and GFLOPs of 5.0, significantly lower than those of competing models. Additionally, when combined with the Slicing Aided Hyper Inference strategy, LGWheatNet further improved the detection accuracy of wheat spikes, especially for small-scale targets and edge regions, when processing large-scale high-resolution images. This strategy significantly enhanced both inference efficiency and accuracy, making it particularly suitable for image analysis from drone-captured data. In wheat spike counting experiments, LGWheatNet also delivered exceptional performance, particularly in predictions during the filling and maturity stages, outperforming other models by a substantial margin. This study not only provides an efficient and reliable solution for wheat spike detection but also introduces innovative methods for lightweight object detection tasks in resource-constrained environments.

Accurate detection of tomato leaf diseases is crucial for early prevention and ensuring agricultural production. This study addresses six tomato leaf diseases: bacterial spot, early blight, late blight, leaf mold, septoria leaf spot, and yellow leaf curl virus. A lightweight detection model, YOLO-LGS, is proposed to achieve efficient and automated disease detection. The dataset of tomato leaf diseases was first augmented to enrich the disease features, thereby improving the model's detection performance. The YOLO-LGS model is built on the YOLOv11 architecture, incorporating lightweight group attention net (LWGANet) to reconstruct the backbone network, replacing the convolutional block with parallel spatial attention mechanism with the grouped channel-wise self-attention (GCSA) mechanism, and introducing separated and enhanced attention module (SEAM) into the detection head to balance performance and efficiency. Experimental results show that the YOLO-LGS model achieves an mAP50 of 0.693 and an F1 score of 0.677, outperforming other YOLO models (YOLOv8s, YOLOv9s, YOLOv10s, and YOLOv11s). Additionally, the model's parameter size is only 6.333 M, and its GFLOPs is 13.4, representing reductions of 32.739% and 37.089%, respectively, compared to YOLOv11s, significantly lowering computational cost while maintaining detection performance. The results demonstrate the effectiveness of LWGANet, GCSA, and SEAM. The development of the YOLO-LGS model provides an efficient, lightweight solution for tomato leaf disease detection in resource-constrained environments.

Estimating soil moisture content in apple orchards using UAV remote sensing data: Application of LST/LAI two-stage feature space theory

Recalibration of four empirical reference crop evapotranspiration models using a hybrid Differential Evolution-Grey Wolf Optimizer algorithm

Simulation of the soil water content under different water deficits for apple trees via improved WOFOST-HYDRUS coupled model

Solar radiation is an important energy source, and accurately predicting it [daily global and diffuse solar radiation (R_s and R_d)] is essential for research on surface energy exchange, hydrologic systems, and agricultural production. However, R_s and R_d estimation relies on meteorological data and related model parameters, which leads to inaccuracy in some regions. To improve the estimation accuracy and generalization ability of the R_s and R_d models, 17 representative radiation stations in China were selected. The categorical boosting (CatBoost) feature selection algorithm was utilized to construct a novel stacking model from sample and parameter diversity perspectives. The results revealed that the characteristics related to sunshine duration (n) and ozone (O₃) significantly affect solar radiation prediction. The proposed new ensemble model framework had better accuracy than base models in root mean square error (RMSE), coefficient of determination (R²), mean absolute error (MAE), and global performance index (GPI). The solar radiation prediction model is more applicable to coastal areas, such as Shanghai and Guangzhou, than to inland regions of China. The range and mean of RMSE, MAE, and R² for R_s prediction are 1.5737–3.7482 (1.9318), 1.1773–2.6814 (1.4336), and 0.7597–0.9655 (0.9226), respectively; for R_d prediction, they are 1.2589–2.9038 (1.8201), 0.9811–2.1024 (1.3493), and 0.5153–0.9217 (0.7248), respectively. The results of this study can provide a reference for R_s and R_d estimation and related applications in China.

With the advancement of computer vision technology, the demand for fruit recognition in agricultural automation is increasing. To improve the accuracy and efficiency of recognizing young red pears, this study proposes an improved model based on the lightweight YOLOv9s, termed YOLOv9s-Pear. By constructing a feature-rich and diverse image dataset of young red pears and introducing spatial-channel decoupled downsampling (SCDown), C2FUIBELAN, and the YOLOv10 detection head (v10detect) modules, the YOLOv9s model was enhanced to achieve efficient recognition of small targets in resource-constrained agricultural environments. Images of young red pears were captured at different times and locations and underwent preprocessing to establish a high-quality dataset. For model improvements, this study integrated the general inverted bottleneck blocks from C2f and MobileNetV4 with the RepNCSPELAN4 module from the YOLOv9s model to form the new C2FUIBELAN module, enhancing the model’s accuracy and training speed for small-scale object detection. Additionally, the SCDown and v10detect modules replaced the original AConv and detection head structures of the YOLOv9s model, further improving performance. The experimental results demonstrated that the YOLOv9s-Pear model achieved high detection accuracy in recognizing young red pears, while reducing computational costs and parameters. The detection accuracy, recall, mean precision, and extended mean precision were 0.971, 0.970, 0.991, and 0.848, respectively. These results confirm the efficiency of the SCDown, C2FUIBELAN, and v10detect modules in young red pear recognition tasks. The findings of this study not only provide a fast and accurate technique for recognizing young red pears but also offer a reference for detecting young fruits of other fruit trees, significantly contributing to the advancement of agricultural automation technology.

The identification and enumeration of peach seedling fruits are pivotal in the realm of precision agriculture, greatly influencing both yield estimation and agronomic practices. This study introduces an innovative, lightweight YOLOv8 model for the automatic detection and quantification of peach seedling fruits, designated as YOLO-Peach, to bolster the scientific rigor and operational efficiency of orchard management. Traditional identification methods, which are labor-intensive and error-prone, have been superseded by this advancement. A comprehensive dataset was meticulously curated, capturing the rich characteristics and diversity of peach seedling fruits through high-resolution imagery at various times and locations, followed by meticulous preprocessing to ensure data quality. The YOLOv8s model underwent a series of lightweight optimizations, including the integration of MobileNetV3 as its backbone, the p2BiFPN architecture, spatial and channel reconstruction convolution, and coordinate attention mechanism, all of which have significantly bolstered the model’s capability to detect small targets with precision. The YOLO-Peach model excels in detection accuracy, evidenced by a precision and recall of 0.979, along with an mAP50 of 0.993 and an mAP50-95 of 0.867, indicating its superior capability for peach sapling identification with efficient computational performance. The findings underscore the model’s efficacy and practicality in the context of peach seedling fruit recognition. Ablation studies have shed light on the indispensable role of each component, with MobileNetV3 streamlining the model’s complexity and computational load, while the p2BiFPN architecture, ScConv convolutions, and coordinate attention mechanism have collectively enhanced the model’s feature extraction and detection precision for minute targets. The implications of this research are profound, offering a novel approach to peach seedling fruit recognition and serving as a blueprint for the identification of young fruits in other fruit species. This work holds significant theoretical and practical value, propelling forward the broader field of agricultural automation.

Chlorophyll a and b content (Cab) and leaf area index (LAI) are two key parameters of crops, and their quantitative inversions are important for growth monitoring and the field management of wheat. However, due to the close correlation between the spectral signals of these two parameters and the effects of soil and atmospheric conditions, as well as modeling errors, synchronous retrieval of LAI and Cab from remote sensing data is still a challenging task. In a previous study, we introduced the optimal estimation theory and established the inversion framework by coupling the PROSAIL (PROSPECT + SAIL) model with the unified linearized vector radiative transfer model (UNL-VRTM). The framework fully utilizes the simulated radiance spectra for synchronous retrieval of Cab and LAI at the UAV observation scale and has good convergence and self-consistency. In this study, based on this inversion framework, synchronized retrieval of Cab and LAI was carried out by real wheat UAV observation data and validated with the ground-measured data. By comparing with the empirical statistical model constructed by the PROSAIL model and coupled model, least squares support vector machine (LSSVM), and random forest (RF), the proposed method has the highest accuracy of Cab and LAI estimated from UAV multispectral data (for Cab, R² = 0.835, RMSE = 14.357; for LAI, R² = 0.892, RMSE = 0.564). Our proposed method enables the fast and efficient estimation of Cab and LAI in multispectral data without prior measurements and training.

Maize is one of the important grain crops grown globally, and growth will directly affect its yield and quality, so it is important to monitor maize growth efficiently and non-destructively. To facilitate the use of unmanned aerial vehicles (UAVs) for maize growth monitoring, comprehensive growth indicators for maize monitoring based on multispectral remote sensing imagery were established. First of all, multispectral image data of summer maize canopy were collected at the jointing stage, and meanwhile, leaf area index (LAI), relative chlorophyll content (SPAD), and plant height (VH) were measured. Then, the comprehensive growth monitoring indicators CGMI_CV and CGMI_CR for summer maize were constructed by the coefficient of variation method and the CRITIC weighting method. After that, the CGMI_CV and CGMI_CR prediction models were established by the partial least-squares (PLSR) and sparrow search optimization kernel extremum learning machine (SSA-KELM) using eight typical vegetation indices selected. Finally, a comparative analysis was performed using ground-truthing data, and the results show: (1) For CGMI_CV, the R² and RMSE of the model built by SSA-KELM are 0.865 and 0.040, respectively. Compared to the model built by PLSR, R² increased by 4.5%, while RMSE decreased by 0.3%. For CGMI_CR, the R² and RMSE of the model built by SSA-KELM are 0.885 and 0.056, respectively. Compared to the other model, R² increased by 4.6%, and RMSE decreased by 2.8%. (2) Compared to the models by single indicator, among the models constructed based on PLSR, the CGMI_CR model had the highest R². In the models constructed based on SSA-KELM, the R² of models by the CGMI_CR and CGMI_CV were larger than that of the models by SPAD (R² = 0.837), while smaller than that of the models by LAI (R² = 0.906) and models by VH (R² = 0.902). In summary, the comprehensive growth monitoring indicators prediction model established in this paper is effective and can provide technical support for maize growth monitoring.