Fu Zhao

Mung bean (Vigna radiata (L.) Wilczek) seed pretreatment commonly involves biological and chemical methods, whereas physical pretreatments such as static magnetic field pretreatment (SMFP) have attracted attention because they are noncontact and offer adjustable treatment parameters. To clarify the effects of SMFP on multiple traits of mung bean across several developmental stages, seeds were exposed to magnetic flux densities of 5 and 10 mT for magnetic treatment durations of 10, 20, and 30 min. Laboratory germination tests and field experiments showed that, under the tested conditions, most SMFP combinations at these low magnetic flux densities resulted in a higher germination rate (GR) than the control. Responses of basal stem diameter (BSD), straw dry weight (SDW), straw-to-grain ratio (SGR), and harvest index (HI) varied among traits and were nonmonotonic. Mean relative chlorophyll content (RCC) fluctuated across observation weeks, and treatment differences were observed for some combinations of observation week and canopy position. No magnetic treatment significantly increased grain yield per unit area (GY) or grain component yields per unit area (GCY) relative to the control. Grain starch content (SC) generally increased, whereas crude protein content (CPC) decreased in most treatments. The interaction between magnetic flux density and magnetic treatment duration significantly affected the maximum shear force of the basal stem (MSFB) and the maximum bending force of the basal stem (MBFB). For paired measurements obtained from individual plants, BSD was positively associated with both maximum force values. Overall, the effects of SMFP on mung bean traits differed among traits, depended on the treatment parameters, and were nonmonotonic; no single treatment combination was suitable for all indicators. These exploratory findings provide a basis for further research across multiple cultivars, locations, and growing seasons.

To address the challenges of narrow, confined spaces in traditional closed-canopy orchards, where complex terrain between and within rows hinders the operation of large and medium-sized mowers. A self-propelled intra-plant obstacle-avoiding oscillating mower was developed. Its core innovation is an integrated oscillating mechanism that achieves one-pass, full-coverage operation by coordinating a 110° fan-shaped cutting path for inter-row areas with an adaptive flipping contour-cutting action for intra-plant areas. The power and transmission systems were optimized according to the shear and bending forces of three common weed species. The integrated prototype was then built and subjected to field tests. The results showed that the shear and bending forces of all three weed species peaked at 30 mm from the root and stabilized beyond 50 mm. Field tests demonstrated a 100% intra-plant obstacle passage rate, 96.9% cutting width utilization rate, 92.07% stubble height stability coefficient, and a 1.66% missed-cutting rate, which meets the operational requirements of closed-canopy orchards.

The chlorophyll content is an important index reflecting the growth status and nutritional level of plants. The rapid, accurate and nondestructive monitoring of the SPAD content of apple trees can provide a basis for large-scale monitoring and scientific management of the growth status of apple trees. In this study, the canopy leaves of apple trees at different growth stages in the same year were taken as the research object, and remote sensing images of fruit trees in different growth stages (flower-falling stage, fruit-setting stage, fruit expansion stage, fruit-coloring stage and fruit-maturing stage) were acquired via a DJI MAVIC 3 multispectral unmanned aerial vehicle (UAV). Then, the spectral reflectance was extracted to calculate 15 common vegetation indexes as eigenvalues, the 5 vegetation indexes with the highest correlation were screened out through Pearson correlation analysis as the feature combination, and the measured SPAD values in the leaves of the fruit trees were gained using a handheld chlorophyll meter in the same stages. The estimation models for the SPAD values in different growth stages were, respectively, established through five machine learning algorithms: multiple linear regression (MLR), partial least squares regression (PLSR), support vector regression (SVR), random forest (RF) and extreme gradient boosting (XGBoost). Additionally, the model performance was assessed by selecting the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE). The results show that the SPAD estimation results vary from stage to stage, where the best estimation model for the flower-falling stage, fruit-setting stage and fruit-maturing stage is RF and those for the fruit expansion stage and fruit-coloring stage are PLSR and MLR, respectively. Among the estimation models in the different growth stages, the model accuracy for the fruit expansion stage is the highest, with R² = 0.787, RMSE = 0.87 and MAE = 0.644. The RF model, which outperforms the other models in terms of the prediction effect in multiple growth stages, can effectively predict the SPAD value in the leaves of apple trees and provide a reference for the growth status monitoring and precise management of orchards.

The colors of walnut fruits and leaves are similar in the oil transformation period, and the fruits are easily blocked by the branches and leaves. On the basis of the improved YOLOv7-tiny, a detection model is proposed and integrated into an Android application to solve the problem of walnut identification. Ablation experiments conducted with three improved strategies show that the strategies can effectively enhance the performance of the model. In terms of combinatorial optimization, the YOLOv7-tiny detection model that combines FasterNet and LightMLP modules works excellently. Its AP₅₀ and AP_50–95 are 3.1 and 4 percentage points (97.4% and 77.3%, respectively) higher than those of the original model. YOLOv7-tiny’s model size and number of parameters are reduced by 14.6% and 14.4%, respectively, relative to those of the original model, and its detection time decreases to 15.4 ms. The model has good robustness and generalization ability and can provide a technical reference for intelligent real-time detection of walnuts during the oil conversion period.