Accurate detection and counting of wheat spikes are crucial for yield estimation and variety selection in precision agriculture. However, challenges such as complex field environments, morphological variations, and small target sizes hinder the performance of existing models in real-world applications. This study proposes FEWheat-YOLO, a lightweight and efficient detection framework optimized for deployment on agricultural edge devices. The architecture integrates four key modules: (1) FEMANet, a mixed aggregation feature enhancement network with Efficient Multi-scale Attention (EMA) for improved small-target representation; (2) BiAFA-FPN, a bidirectional asymmetric feature pyramid network for efficient multi-scale feature fusion; (3) ADown, an adaptive downsampling module that preserves structural details during resolution reduction; and (4) GSCDHead, a grouped shared convolution detection head for reduced parameters and computational cost. Evaluated on a hybrid dataset combining GWHD2021 and a self-collected field dataset, FEWheat-YOLO achieved a COCO-style AP of 51.11%, AP@50 of 89.8%, and AP scores of 18.1%, 50.5%, and 61.2% for small, medium, and large targets, respectively, with an average recall (AR) of 58.1%. In wheat spike counting tasks, the model achieved an R² of 0.941, MAE of 3.46, and RMSE of 6.25, demonstrating high counting accuracy and robustness. The proposed model requires only 0.67 M parameters, 5.3 GFLOPs, and 1.6 MB of storage, while achieving an inference speed of 54 FPS. Compared to YOLOv11n, FEWheat-YOLO improved AP@50, AP_s, AP_m, AP_l, and AR by 0.53%, 0.7%, 0.7%, 0.4%, and 0.3%, respectively, while reducing parameters by 74%, computation by 15.9%, and model size by 69.2%. These results indicate that FEWheat-YOLO provides an effective balance between detection accuracy, counting performance, and model efficiency, offering strong potential for real-time agricultural applications on resource-limited platforms.

Accurate and non-destructive acquisition of leaf chlorophyll content (LCC) in cotton plant canopies is of significant importance for real-time monitoring of cotton growth and implementing precise water and nitrogen management in cotton fields. This study utilized UAV-based RGB imagery combined with real-time kinematic (RTK) technology to efficiently and accurately retrieve LCC under different nitrogen application levels in a cotton field, employing 6 machine learning algorithms: Least Absolute Shrinkage and Selection Operator regression (LASSO), Multiple Linear Regression (MLR), Partial Least Squares Regression (PLSR), Random Forest Regression (RFR), Ridge Regression (Ridge), and Support Vector Regression (SVR). Among these, the SVR model demonstrated the best overall performance, with coefficient of determination (R²), root mean square error (RMSE), relative root mean square error (rRMSE), and mean absolute percentage error (MAPE) values of 0.82, 0.14 mg/g, 8.91%, and 6.99% for the training set, and 0.75, 0.14 mg/g, 8.90%, and 7.83% for the testing set, respectively. Furthermore, the SVR model was applied to retrieve LCC pixel-by-pixel from UAV imagery, and pseudo-color rendering techniques were used to generate spatial distribution maps of LCC in the cotton canopy, visually presenting the spatial variability characteristics of LCC within the field. The results indicate that the cotton canopy LCC estimation method based on UAV RGB imagery combined with RTK technology achieves comparable accuracy to the more expensive multispectral and hyperspectral techniques, without a significant reduction in precision. This approach provides an efficient, low-cost, and reliable method for detecting canopy LCC in small-scale cotton fields.

Background/Objectives: Reductive soil disinfestation (RSD) is increasingly viewed as a viable alternative to chemical fumigation, yet the role of organic amendment quality in regulating greenhouse gas (GHG) fluxes, soil organic carbon (SOC) dynamics, and net climate forcing remains poorly understood. Methodology: In a 30-day anaerobic incubation experiment, we set up three treatments—a flooded control (CK), soil amended with wheat straw (WS, C/N = 55.5), and soil amended with kiwifruit branches (KB, C/N = 110.8)—each replicated three times under identical conditions. Results: Both WS and KB additions strongly stimulated CO₂ and CH₄ production, while suppressing N₂O emissions by over 85% relative to CK. The WS treatment exhibited a substantially higher global warming potential (GWP, 823.52 t ha⁻¹) than KB (636.23 t ha⁻¹), with CH₄ accounting for more than 99% of total GWP. Although WS surpassed KB in short-term carbon sequestration efficiency (25.79% vs. 20.11%) and showed greater hydrolytic enzyme activities (βG, CBH, and XYL), the two organic amendments diverged clearly in carbon fraction distribution: C_mic was 17.9% higher under WS, whereas C_min was 16.2% higher under KB. When factoring in the CO₂ equivalent benefit derived from carbon sequestration, the net GWP (NGWP) indicated that both RSD treatments remained net GHG sources. Notably, KB yielded a markedly lower NGWP (611.60 t CO₂-eq ha⁻¹) than WS (798.19 t CO₂-eq ha⁻¹), highlighting a fundamental trade-off: WS favored rapid SOC accumulation at the expense of elevated methane emissions, whereas KB achieved a smaller climatic footprint despite more moderate carbon retention. Conclusions: These findings underscore that selecting organic amendments for field RSD requires balancing the competing goals of carbon sequestration and GHG mitigation.