The leaf area index (LAI) is a critical biophysical parameter that reflects crop growth conditions and the canopy photosynthetic potential, serving as a cornerstone in precision agriculture and dynamic crop monitoring. However, traditional LAI estimation methods relying on single-source remote sensing data and often suffer from insufficient accuracy in high-density vegetation scenarios, limiting their capacity to reflect crop growth variability comprehensively. To overcome these limitations, this study introduces an innovative multi-source feature fusion framework utilizing unmanned aerial vehicle (UAV) multispectral imagery for precise LAI estimation in winter wheat. RGB and multispectral datasets were collected across seven different growth stages (from regreening to grain filling) in 2024. Through the extraction of color attributes, spatial structural information, and eight representative vegetation indices (VIs), a robust multi-source dataset was developed to integrate diverse data types. A convolutional neural network (CNN)-based feature extraction backbone, paired with a multi-source feature fusion network (MSF-FusionNet), was designed to effectively combine spectral and spatial information from both RGB and multispectral imagery. The experimental results revealed that the proposed method achieved superior estimation performance compared to single-source models, with an R² of 0.8745 and RMSE of 0.5461, improving the R² by 36.67% and 5.54% over the RGB and VI models, respectively. Notably, the fusion method enhanced the accuracy during critical growth phases, such as the regreening and jointing stages. Compared to traditional machine learning techniques, the proposed framework exceeded the performance of the XGBoost model, with the R² rising by 4.51% and the RMSE dropping by 12.24%. Furthermore, our method facilitated the creation of LAI spatial distribution maps across key growth stages, accurately depicting the spatial heterogeneity and temporal dynamics in the field. These results highlight the efficacy and potential of integrating UAV multi-source data fusion with deep learning for precise LAI estimation in winter wheat, offering significant insights for crop growth evaluation and precision agricultural management.

The fruit industry is a significant economic sector in China, with modern orchards gradually transitioning to trellis orchards. For mechanized orchard operations, automatic vehicle navigation is essential. However, in trellis orchards, the shading from trees results in low average light intensity and large variations in lighting, posing challenges for path navigation. To address this, a path navigation algorithm for trellis orchards is proposed based on the UNet-CBAM model. The network structures of UNet, FCN, and SegNet are compared to identify and select the optimal structure for further improvement. Among the three attention mechanisms of channel attention, spatial attention, and combined attention, the most effective mechanism is identified. The optimal attention mechanism is incorporated into the optimized network to enhance the model’s ability to detect path edges and improve detection performance. To validate the effectiveness and generalizability of the model, a total of 400 images were collected under varying lighting intensities. The experimental results show that this method achieves an accuracy of 97.63%, a recall of 93.94%, and an Intersection over Union (IoU) of 92.19%. These results significantly enhance path recognition accuracy in trellis orchards, particularly under low light under conditions. Compared to the FCN and SegNet algorithms, this method provides higher detection accuracy and offers a new theoretical foundation and research approach for path recognition in low-light environments.

Soybean–maize intercropping involves the simultaneous planting of maize and soybean. Compound planting sprayers are equipped with a dual-spraying system, particularly for herbicide application, where isolation between crops is essential. To isolate the spraying, it is necessary to select appropriate nozzles that minimize the interference between spray boundaries while ensuring spray uniformity. This study focuses on soybean–maize intercropping systems and investigates the variation patterns of spray boundary under different nozzle arrangement types. Eccentric nozzles (i.e., spray pattern is asymmetric fan-shaped) and fan-shaped nozzles (i.e., spray pattern is symmetric fan-shaped) were evaluated at a working pressure of 0.3 MPa. The results showed that the eccentric nozzle achieved a coefficient of variation (CV) of 0.57 and a compactness of 0.43, while the fan-shaped nozzle had a CV of 0.50 and a compactness of 0.52. This indicates the eccentric nozzle maintains uniformity with a narrower boundary. In addition, this validation was conducted at 0.4 MPa, having similar observations. In soybean–maize intercropping, the maize row width ranges from 40 to 80 cm and where the maize plants exceed 2 m in height, two-eccentric nozzles are required, tested at spacing intervals of 50 cm, 70 cm, and 90 cm. At 0.3 MPa, the CV reached its minimum value (0.3) at a spacing of 70 cm. Additionally, the spray volume on the eccentric nozzle side decreased as the spacing increased. The soybean row width ranges from 160 to 240 cm, requiring eccentric nozzles on both sides and a fan-shaped nozzle in the middle. The spacing between the eccentric and fan-shaped nozzles is chosen to be 50, 70, and 90 cm. A combination of eccentric and fan-shaped nozzles was tested at the same spacing intervals. The results showed that the CV consistently decreased with increasing spacing, and the spray volume on the eccentric nozzle side also declined. Overall, the optimal nozzle configuration for maize zones is two eccentric nozzles at a spacing of 70 cm, while for soybean zones, combining an eccentric nozzle with a fan-shaped nozzle at a spacing of 90 cm effectively ensures both spray uniformity and boundary compactness when variation in windspeed and direction are ignored.