Buckwheat is an important minor grain crop with medicinal and edible functions. The accurate judgment of buckwheat maturity is beneficial to reduce harvest losses and improve yield. With the rapid development of unmanned aerial vehicle (UAV) technology, it has been widely used to predict the maturity of agricultural products. This paper proposed a method using recursive feature elimination cross-validation (RFECV) combined with multiple regression models to predict the maturity of buckwheat in UAV-RGB images. The images were captured in the buckwheat experimental field of Shanxi Agricultural University in Jinzhong, Northern China, from September to October in 2021. The variety was sweet buckwheat of “Jinqiao No. 1”. In order to deeply mine the feature vectors that highly correlated with the prediction of buckwheat maturity, 22 dimensional features with 5 vegetation indexes, 9 color features, and 8 texture features of buckwheat were selected initially. The RFECV method was adopted to obtain the optimal feature vector dimensions and combinations with six regression models of decision tree regression, linear regression, random forest regression, AdaBoost regression, gradient lifting regression, and extreme random tree regression. The coefficient of determination ($R^2$) and root mean square error (RMSE) were used to analyze the different combinations of the six regression models with different feature spaces. The experimental results show that the single vegetation index performed poorly in the prediction of buckwheat maturity; the prediction result of feature space “5” combined with the gradient lifting regression model performed the best; and the $R^2$ and RMSE were 0.981 and 1.70 respectively. The research results can provide an important theoretical basis for the prediction of the regional maturity of crops.

Non-destructive, fast, and accurate prediction of soil organic matter content in farmland is of great significance for soil fertility assessment and rational fertilization. In the process of soil organic matter prediction, it is important to give full play to the advantages of different prediction models and to integrate different prediction models to innovatively construct a combined prediction model of soil organic matter content so as to improve the prediction accuracy and generalization ability of the model. In this study, the soil organic matter content of agricultural soils was taken as the research object, and the visible near-infrared hyperspectral curves of soils were measured by the Starter Kit indoor mobile scanning platform (Headwall Photonics, Bolton, MA, USA), and the original spectral curves were firstly de-noised by Savitzky–Golay (S-G) smoothing. Secondly, the smoothed and denoised spectral data were subjected to a first-order differential transform, and the features were selected based on the first-order differential transformed spectral data using the L1-paradigm algorithm features. Then, secondly, eight algorithms based on the selected feature bands, such as LASSO Regression (LASSO) (Model 1), Multilayer Perceptron (MLP) (Model 2), Random Forest (RF) (Model 3), Gaussian Kernel Regression (GKR) (Model 4), Ridge Regression (Model 5), Long Short-Term Memory (LSTM) (Model 6), Convolutional Neural Networks (CNN) (Model 7), and Support Vector Regression (SVR) (Model 8), were applied to construct a single-prediction model of soil organic matter content. Finally, a superior linear combination-prediction model was proposed by the eight single-prediction models constructed, and the standard deviation-based prediction validity was added to test the model. The results showed the following: (1) the weights of the eight single-prediction models in the combined prediction model were ${\omega }_1^{*}=0.099$, ${\omega }_2^{*}=0.202$, ${\omega }_3^{*}=0.000$, ${\omega }_4^{*}=0.357$, ${\omega }_5^{*}=0.088$, ${\omega }_6^{*}=0.089$, ${\omega }_7^{*}=0.000$, ${\omega }_8^{*}=0.165$, respectively; (2) The average precision E of the predicted values of soil organic matter content constructed based on the eight single-prediction models was 0.856; the average standard deviation σ was 0.181, and the average prediction validity M was 0.702; (3) The accuracy E of the predicted value of soil organic matter content of the combined model was 0.893, which was 4.322% higher than the average accuracy of the single model; the standard deviation of the combined model was 0.129, which was 28.333% lower than the average standard deviation of the single model, and the prediction validity M of the combined model was 0.778, which was 10.826% higher than the average prediction validity of the single model. The combined model can be used for the effective estimation of soil organic matter content in farmland with visible near-infrared spectral data, which can provide a basis and reference for the rapid detection of soil organic matter content in farmland.

Mechanical weeding is an important technical means for organic and regenerative agricultural systems. Current weed control equipment has a variety of problems, such as difficulty adapting to high-stalk crops and poor operational quality. A high-clearance mid-tillage weeder (HMTW) has been developed to meet the mechanical weed control needs of high-stalk crops. The weeder mainly comprises a suspension device, a frame, parallel four-rod profiling mechanisms, weeding operation components, and depth-limiting soil-cutting devices. Based on the agronomic requirements of dryland flat planting, the overall structure of the HMTW was determined, and the weeding unit and flat shovel hoe were designed. Theoretical analysis was conducted on the depth stability of the HMTW, and an optimization mathematical model of the HMTW was established to further improve its tillage depth stability for agronomic requirements. The optimization objective was to minimize the deflection angle (∆β) of the profiling rod on a vertical plane, and the parameters of the parallel four-rod profiling mechanism were optimized. Based on the optimized structural parameters, a prototype of the HMTW was developed and evaluated. The test results show that the optimized HMTW exhibited a good weeding effect, and the tillage depth stability was within the design operating range. When the driving speed was 1.0 m/s and the tillage depth was 8 cm, the weed removal rate, seedling injury rate, seedling burial rate, and qualified rate of tillage depth were 90.8%, 3.2%, 4.1%, and 94%, respectively. The proposed HMTW successfully meets the weeding agronomic requirements of high-stalk crops for dryland farming, and the performance analysis and optimization models provide technical references for the design and development of such structures.

Mechanical threshing can cause damage to oats, and the nutritional quality of the damaged kernels easily changes during storage. The current research on oats with regard to threshing damage and nutritional quality falls into two separate research areas, but they are inextricably linked. It is necessary to combine these two types of studies. In order to explore the damage mechanism of oat threshing and its effect on the nutritional components, a three-dimensional model of oat–nail-tooth impact was established, and a finite element analysis of the dynamic impact process was performed using LS-DYNA. The changes in the von Mises stress, contact force, energy, critical velocity, and damage characteristics during impact on different surfaces of the kernel were analyzed. A threshing test was carried out, and the kernels were classified according to their different damage types. The differences in the nutrient compositions and contents of oats with different damage types were analyzed by means of near-infrared spectroscopy and physicochemical testing. The results showed that the von Mises stress and contact force tended to first increase and then decrease during impact. When the impact velocity was 12 m/s, for the top, bottom, front, back, and left sides of the oat impacted by the nail tooth, the maximum von Mises stresses were 10.05, 10.46, 8.60, 9.28, and 8.49 MPa, respectively. The maximum contact forces were 25.09, 18.57, 34.29, 38.37, and 35.19 N, respectively. The critical velocities of impact damage were 13.38, 13.10, 13.40, 14.64, and 16.00 m/s, respectively. The threshing damage could be divided into four typical types: transverse fracture, bottom breakage, side fracture, and back crack. The chemical compositions of oat kernels with different damage types were basically the same, but their nutrient contents were different. These results provide a theoretical basis for optimizing oat threshing devices, reducing threshing damage, and improving oat quality.