In recent years, the delay in sowing has become a major obstacle to high wheat yield in Jiangsu Province, one of the major wheat producing areas in China; hence, it is necessary to screen wheat varieties are resilient for late sowing. This study aimed to provide an effective, fast, and non-destructive monitoring method of soil plant analysis development (SPAD) values, which can represent leaf chlorophyll contents, for late-sown winter wheat variety screening. This study acquired multispectral images using an unmanned aerial vehicle (UAV) at the overwintering stage of winter wheat growth, and further processed these images to extract reflectance of five single spectral bands and calculated 26 spectral vegetation indices. Based on these 31 variables, this study combined three variable selection methods (i.e., recursive feature elimination (RFE), random forest (RF), and Pearson correlation coefficient (r)) with four machine learning algorithms (i.e., random forest regression (RFR), linear kernel-based support vector regression (SVR), radial basis function (RBF) kernel-based SVR, and sigmoid kernel-based SVR), resulted in seven SVR models (i.e., RFE-SVR_linear, RF-SVR_linear, RF-SVR_RBF, RF-SVR_sigmoid, r-SVR_linear, r-SVR_RBF, and r-SVR_sigmoid) and three RFR models (i.e., RFE-RFR, RF-RFR, and r-RFR). The performances of the 10 machine learning models were evaluated and compared with each other according to the achieved coefficient of determination (R²), residual prediction deviation (RPD), root mean square error (RMSE), and relative RMSE (RRMSE) in SPAD estimation. Of the 10 models, the best one was the RF-SVR_sigmoid model, which was the combination of the RF variable selection method and the sigmoid kernel-based SVR algorithm. It achieved high accuracy in estimating SPAD values of the wheat canopy (R² = 0.754, RPD = 2.017, RMSE = 1.716 and RRMSE = 4.504%). The newly developed UAV- and machine learning-based model provided a promising and real time method to monitor chlorophyll contents at the overwintering stage, which can benefit late-sown winter wheat variety screening.

Leaf area index (LAI) is one of the indicators measuring the growth of rice in the field. LAI monitoring plays an important role in ensuring the stable increase of grain yield. In this study, the canopy reflectance spectrum of rice was obtained by ASD at the elongation, booting, heading and post-flowering stages of rice, and the correlations between the original reflectance (OR), first-derivative transformation (FD), reciprocal transformation (1/R), and logarithmic transformation (LOG) with LAI were analyzed. Characteristic bands of spectral data were then selected based on the successive projections algorithm (SPA) and Pearson correlation. Moreover, ridge regression (RR), partial least squares (PLS), and multivariate stepwise regression (MSR) were conducted to establish estimation models based on characteristic bands and vegetation indices. The research results showed that the correlation between canopy spectrum and LAI was significantly improved after FD transformation. Modeling using SPA to select FD characteristic bands performed better than using Pearson correlation. The optimal modeling combination was FD-SPA-VI-RR, with the coefficient of determination (R²) of 0.807 and the root-mean-square error (RMSE) of 0.794 for the training set, R² of 0.878 and RMSE of 0.773 for the validation set 1, and R² of 0.705 and RMSE of 1.026 for the validation set 2. The results indicated that the present model may predict the rice LAI accurately, meeting the requirements of large-scale statistical monitoring of rice growth indicators in the field.

Detection of the Fusarium head blight (FHB) is crucial for wheat yield protection, with precise and rapid FHB detection increasing wheat yield and protecting the agricultural ecological environment. FHB detection tasks in agricultural production are currently handled by cloud servers and utilize unmanned aerial vehicles (UAVs). Hence, this paper proposed a lightweight model for wheat ear FHB detection based on UAV-enabled edge computing, aiming to achieve the purpose of intelligent prevention and control of agricultural disease. Our model utilized the You Only Look Once version 4 (YOLOv4) and MobileNet deep learning architectures and was applicable in edge devices, balancing accuracy, and FHB detection in real-time. Specifically, the backbone network Cross Stage Partial Darknet53 (CSPDarknet53) of YOLOv4 was replaced by a lightweight network, significantly decreasing the network parameters and the computing complexity. Additionally, we employed the Complete Intersection over Union (CIoU) and Non-Maximum Suppression (NMS) to regress the loss function to guarantee the detection accuracy of FHB. Furthermore, the loss function incorporated the focal loss to reduce the error caused by the unbalanced positive and negative sample distribution. Finally, mixed-up and transfer learning schemes enhanced the model’s generalization ability. The experimental results demonstrated that the proposed model performed admirably well in detecting FHB of the wheat ear, with an accuracy of 93.69%, and it was somewhat better than the MobileNetv2-YOLOv4 model (F1 by 4%, AP by 3.5%, Recall by 4.1%, and Precision by 1.6%). Meanwhile, the suggested model was scaled down to a fifth of the size of the state-of-the-art object detection models. Overall, the proposed model could be deployed on UAVs so that wheat ear FHB detection results could be sent back to the end-users to intelligently decide in time, promoting the intelligent control of agricultural disease.

Sheath blight (ShB), caused by Rhizoctonia solani AG1-I, is one of the most important diseases in rice worldwide. The symptoms of ShB primarily develop on leaf sheaths and leaf blades. Hyperspectral remote sensing technology has the potential of rapid, efficient and accurate detection and monitoring of the occurrence and development of rice ShB and other crop diseases. This study evaluated the spectral responses of leaf blade fractions with different development stages of ShB symptoms to construct the spectral feature library of rice ShB based on “three-edge” parameters and narrow-band vegetation indices to identify the disease on the leaves. The spectral curves of leaf blade lesions have significant changes in the blue edge, green peak, yellow edge, red valley, red edge and near-infrared regions. The variables of the normalized index between green peak amplitude and red valley amplitude (Rg − Ro)/(Rg + Ro), the normalized index between the yellow edge area and blue edge area (SDy − SDb)/(SDy + SDb), the ratio index of green peak amplitude and red valley amplitude (Rg/Ro) and the nitrogen reflectance index (NRI) had high relevance to the disease. At the leaf scale, the importance weights of all attributes decreased with the effect of non-infected areas in a leaf by the ReliefF algorithm, with Rg/Ro being the indicator having the highest importance weight. Estimation rate of 95.5% was achieved in the decision tree classifier with the parameter of Rg/Ro. In addition, it was found that the variety degree of absorptive valley, reflection peak and reflecting steep slope was different in the blue edge, green and red edge regions, although there were similar spectral curve shapes between leaf sheath lesions and leaf blade lesions. The significant difference characteristic was the ratio index of the red edge area and green peak area (SDr/SDg) between them. These results can provide the basis for the development of a specific sensor or sensors system for detecting the ShB disease in rice.

Yield is an important indicator in evaluating rice planting, and it is the collective result of various factors over multiple growth stages. To achieve a large-scale accurate prediction of rice yield, based on yield estimation models using a single growth stage and conventional spectral transformation methods, this study introduced the continuous wavelet transform algorithm and constructed models under the premise of combined multiple growth stages. In this study, canopy reflectance spectra at four important stages of rice elongation, heading, flowering and milky were selected, and then, a rice yield estimation model was constructed by combining vegetation index, first derivative and wavelet transform based on random forest algorithm or multiple stepwise regression. This study found that the combination of multiple growth stages significantly improved the model accuracy. In addition, after two validations, the optimal model combination for rice yield estimation is first derivative-wavelet transform-vegetation index-random forest model based on four growth stages, with the coefficient of determination (R²) of 0.86, the root mean square error (RMSE) of 35.50 g·m⁻² and the mean absolute percentage error (MAPE) of 4.6% for the training set, R² of 0.85, RMSE of 33.40 g.m⁻² and MAPE 4.30% for the validation set 1, and R² of 0.80, RMSE of 37.40 g·m⁻² and MAPE of 4.60% for the validation set 2. The research results demonstrated that the established model could accurately predict rice yield, providing technical support and a foundation for large-scale statistical estimating of rice yield.

In order to effectively support wheat breeding, farmland ridge segmentation can be used to visualize the size and spacing of a wheat field. At the same time, accurate ridge information collecting can deliver useful data support for farmland management. However, in the farming ridge segmentation scenarios based on remote sensing photos, the commonly used semantic segmentation methods tend to overlook the ridge edges and ridge strip features, which impair the segmentation effect. In order to efficiently collect ridge information, this paper proposes a segmentation method based on encoder-decoder of network with strip pooling module and ASPP module. First, in order to extract context information for multi-scale features, ASPP module are integrated in the deepest feature map. Second, the remote dependence of the ridge features is improved in both horizontal and vertical directions by using the strip pooling module. The final segmentation map is generated by fusing the boundary features and semantic features using an encoder and decoder architecture. As a result, the accuracy of the proposed method in the validation set is 98.0% and mIoU is 94.6%. The results of the experiments demonstrate that the method suggested in this paper can precisely segment the ridge information, as well as its value in obtaining data on the distribution of farmland and its potential for practical application.