The accurate and timely monitoring and evaluation of the regional grain crop yield is more significant for formulating import and export plans of agricultural products, regulating grain markets and adjusting the planting structure. In this study, an improved Carnegie–Ames–Stanford approach (CASA) model was coupled with time-series satellite remote sensing images to estimate winter wheat yield. Firstly, in 2009 the entire growing season of winter wheat in the two districts of Tongzhou and Shunyi of Beijing was divided into 54 stages at five-day intervals. Net Primary Production (NPP) of winter wheat was estimated by the improved CASA model with HJ-1A/B satellite images from 39 transits. For the 15 stages without HJ-1A/B transit, MOD17A2H data products were interpolated to obtain the spatial distribution of winter wheat NPP at 5-day intervals over the entire growing season of winter wheat. Then, an NPP-yield conversion model was utilized to estimate winter wheat yield in the study area. Finally, the accuracy of the method to estimate winter wheat yield with remote sensing images was verified by comparing its results to the ground-measured yield. The results showed that the estimated yield of winter wheat based on remote sensing images is consistent with the ground-measured yield, with R² of 0.56, RMSE of 1.22 t ha⁻¹, and an average relative error of −6.01%. Based on time-series satellite remote sensing images, the improved CASA model can be used to estimate the NPP and thereby the yield of regional winter wheat. This approach satisfies the accuracy requirements for estimating regional winter wheat yield and thus may be used in actual applications. It also provides a technical reference for estimating large-scale crop yield.

Powdery mildew (PM, Blumeria graminis f. sp. tritici) is a devastating disease for wheat growth and production. It is highly meaningful that the disease severities can be objectively and accurately identified by image visualization technology. In this study, an integral method was proposed based on a hyperspectral imaging dataset and machine learning algorithms. The disease severities of wheat leaves infected with PM were quantitatively identified based on hyperspectral images and image segmentation techniques. A technical procedure was proposed to perform the identification and evaluation of leaf-scale wheat PM, specifically including three primary steps of the acquisition and preprocessing of hyperspectral images, the selection of characteristic bands, and model construction. Firstly, three-dimensional reduction algorithms, namely principal component analysis (PCA), random forest (RF), and the successive projections algorithm (SPA), were comparatively used to select the bands that were most sensitive to PM. Then, three diagnosis models were constructed by a support vector machine (SVM), RF, and a probabilistic neural network (PNN). Finally, the best model was selected by comparing the overall accuracies. The results show that the SVM model constructed by PCA dimensionality reduction had the best result, and the classification accuracy reached 93.33% by a cross-validation method. There was an obvious improvement of the identification accuracy with the model, which achieved an 88.00% accuracy derived from the original hyperspectral images. This study can provide a reference for accurately estimating the disease severity of leaf-scale wheat PM and other plant diseases by non-contact measurement technology.

Fusarium head blight (FHB), one of the most prevalent and damaging infection diseases of wheat, affects quality and safety of associated food. In this study, to realize the early accurate monitoring of FHB, a diagnostic model of disease severity was proposed based on the fusion features of image and spectral features. First, the hyperspectral image of FHB infected in the range of the 400–1000 nm spectrum was collected, and the color parameters of wheat ear and spot region were segmented based on image features. Twelve sensitive bands were extracted using the successive projection algorithm, gray-scale co-occurrence matrix, and RGB color model. Four texture features were extracted from each feature band image as texture variables, and nine color feature variables were extracted from R, G, and B component images. Texture features with high correlation and color features were selected to participate in the final model building parameters via correlation analysis. Finally, the particle swarm optimization support vector machine (PSO-SVM) algorithm was used to build the model based on the diagnosis model of disease severity of FHB with different combinations of characteristic variables. The experimental results showed that the PSO-SVM model based on spectral and color feature fusion was optimal. Moreover, the accuracy of the training and prediction set was 95% and 92%, respectively. The method based on fusion features of image and spectral features can accurately and effectively diagnose the severity of FHB, thereby providing a technical basis for the timely and effective control of FHB and precise application of a pesticide.

Remote image semantic segmentation technology is one of the core research elements in the field of computer vision and has a wide range of applications in production life. Most remote image semantic segmentation methods are based on CNN. Recently, Transformer provided a view of long-distance dependencies in images. In this paper, we propose RCCT-ASPPNet, which includes the dual-encoder structure of Residual Multiscale Channel Cross-Fusion with Transformer (RCCT) and Atrous Spatial Pyramid Pooling (ASPP). RCCT uses Transformer to cross fuse global multiscale semantic information; the residual structure is then used to connect the inputs and outputs. ASPP based on CNN extracts contextual information of high-level semantics from different perspectives and uses Convolutional Block Attention Module (CBAM) to extract spatial and channel information, which will further improve the model segmentation ability. The experimental results show that the mIoU of our method is 94.14% and 61.30% on the datasets Farmland and AeroScapes, respectively, and that the mPA is 97.12% and 84.36%, respectively, both outperforming DeepLabV3+ and UCTransNet.

Identification of soybean kernel damages is significant to prevent further disoperation. Hyperspectral imaging (HSI) has shown great potential in cereal kernel identification, but its low spatial resolution leads to external feature infidelity and limits the analysis accuracy. In this study, the fusion of HSI and RGB images and improved ShuffleNet were combined to develop an identification method for soybean kernel damages. First, the HSI-RGB fusion network (HRFN) was designed based on super-resolution and spectral modification modules to process the registered HSI and RGB image pairs and generate super-resolution HSI (SR-HSI) images. ShuffleNet improved with convolution optimization and cross-stage partial architecture (ShuffleNet_COCSP) was used to build classification models with the optimal image set of effective wavelengths (OISEW) of SR-HSI images obtained by support vector machine and ShuffleNet. High-quality fusion of HSI and RGB with the obvious spatial promotion and satisfactory spectral conservation was gained by HRFN. ShuffleNet_COCSP and OISEW obtained the optimal recognition performance of ACC_p=98.36%, Params=0.805 M, and FLOPs=0.097 G, outperforming other classification methods and other types of images. Overall, the proposed method provides an accurate and reliable identification of soybean kernel damages and would be extended to analysis of other quality indicators of various crop kernels.

As one of the main disasters that limit the formation of wheat yield and affect the quality of wheat, lodging poses a great threat to safety production. Therefore, an improved PSPNet (Pyramid Scene Parsing Network) integrating the Normalization-based Attention Module (NAM) (NAM-PSPNet) was applied to the high-definition UAV RGB images of wheat lodging areas at the grain-filling stage and maturity stage with the height of 20 m and 40 m. First, based on the PSPNet network, the lightweight neural network MobileNetV2 was used to replace ResNet as the feature extraction backbone network. The deep separable convolution was used to replace the standard convolution to reduce the amount of model parameters and calculations and then improve the extraction speed. Secondly, the pyramid pool structure of multi-dimensional feature fusion was constructed to obtain more detailed features of UAV images and improve accuracy. Then, the extracted feature map was processed by the NAM to identify the less significant features and compress the model to reduce the calculation. The U-Net, SegNet and DeepLabv3+ were selected as the comparison models. The results show that the extraction effect at the height of 20 m and the maturity stage is the best. For the NAM-PSPNet, the MPA (Mean Pixel Accuracy), MIoU (Mean Intersection over Union), Precision, Accuracy and Recall is, respectively, 89.32%, 89.32%, 94.95%, 94.30% and 95.43% which are significantly better than the comparison models. It is concluded that NAM-PSPNet has better extraction performance for wheat lodging areas which can provide the decisionmaking basis for severity estimation, yield loss assessment, agricultural operation, etc.