Yellow rust in winter wheat is a widespread and serious fungal disease, resulting in significant yield losses globally. Effective monitoring and accurate detection of yellow rust are crucial to ensure stable and reliable wheat production and food security. The existing standard methods often rely on manual inspection of disease symptoms in a small crop area by agronomists or trained surveyors. This is costly, time consuming and prone to error due to the subjectivity of surveyors. Recent advances in unmanned aerial vehicles (UAVs) mounted with hyperspectral image sensors have the potential to address these issues with low cost and high efficiency. This work proposed a new deep convolutional neural network (DCNN) based approach for automated crop disease detection using very high spatial resolution hyperspectral images captured with UAVs. The proposed model introduced multiple Inception-Resnet layers for feature extraction and was optimized to establish the most suitable depth and width of the network. Benefiting from the ability of convolution layers to handle three-dimensional data, the model used both spatial and spectral information for yellow rust detection. The model was calibrated with hyperspectral imagery collected by UAVs in five different dates across a whole crop cycle over a well-controlled field experiment with healthy and rust infected wheat plots. Its performance was compared across sampling dates and with random forest, a representative of traditional classification methods in which only spectral information was used. It was found that the method has high performance across all the growing cycle, particularly at late stages of the disease spread. The overall accuracy of the proposed model (0.85) was higher than that of the random forest classifier (0.77). These results showed that combining both spectral and spatial information is a suitable approach to improving the accuracy of crop disease detection with high resolution UAV hyperspectral images.

Yellow rust is a worldwide disease that poses a serious threat to the safety of wheat production. Numerous studies on near-surface hyperspectral remote sensing at the leaf scale have achieved good results for disease monitoring. The next step is to monitor the disease at the field scale, which is of great significance for disease control. In our study, an unmanned aerial vehicle (UAV) equipped with a hyperspectral sensor was used to obtain hyperspectral images at the field scale. Vegetation indices (VIs) and texture features (TFs) extracted from the UAV-based hyperspectral images and their combination were used to establish partial least-squares regression (PLSR)-based disease monitoring models in different infection periods. In addition, we resampled the original images with 1.2 cm spatial resolution to images with different spatial resolutions (3 cm, 5 cm, 7 cm, 10 cm, 15 cm, and 20 cm) to evaluate the effect of spatial resolution on disease monitoring accuracy. The findings showed that the VI-based model had the highest monitoring accuracy (R² = 0.75) in the mid-infection period. The TF-based model could be used to monitor yellow rust at the field scale and obtained the highest R² in the mid- and late-infection periods (0.65 and 0.82, respectively). The VI-TF-based models had the highest accuracy in each infection period and outperformed the VI-based or TF-based models. The spatial resolution had a negligible influence on the VI-based monitoring accuracy, but significantly influenced the TF-based monitoring accuracy. Furthermore, the optimal spatial resolution for monitoring yellow rust using the VI-TF-based model in each infection period was 10 cm. The findings provide a reference for accurate disease monitoring using UAV hyperspectral images.

Wheat yellow rust is one of the most destructive diseases in wheat production and significantly affects wheat quality and yield. Accurate and non-destructive identification of yellow rust is critical to wheat production management. Hyperspectral imaging technology has proven to be effective in identifying plant diseases. We investigated the feasibility of identifying yellow rust on wheat leaves using spectral features and textural features (TFs) of hyperspectral images. First, the hyperspectral images were preprocessed, and healthy and yellow rust-infected samples were obtained by creating regions of interest. Second, the extraction of spectral reflectance characteristics and vegetation indices (VIs) were performed from the preprocessed hyperspectral images, and the TFs were extracted using the grey-level co-occurrence matrix from the images transformed by principal component analysis. Third, the successive projections algorithm was employed to choose the optimum wavebands (OWs), and correlation-based feature selection was employed to select the optimal VIs and TFs (those most sensitive to yellow rust and having minimal redundancy between features). Finally, identification models of wheat yellow rust were established using a support vector machine and different features. Six OWs (538, 598, 689, 702, 751, and 895 nm), four VIs (nitrogen reflectance index, photochemical reflectance index, greenness index, and anthocyanin reflectance index), and four TFs (correlation 1, correlation 2, entropy 2, and second moment 3) were selected. The identification models based on the OWs, VIs, and TFs provided overall accuracies of 83.3%, 89.5%, and 86.5%, respectively. The TF results were especially encouraging. The models with the combination of spectral features and TFs exhibited better performance than those using the spectral features or TFs alone. The accuracies of the models with the combined features (OWs and TFs, Vis, and TFs) were 90.6% and 95.8%, respectively. These values were 7.3% and 6.3% higher, respectively, than those of the models using only the OWs or VIs. The model with the combined feature (VIs and TFs) had the highest accuracy (95.8%) and was used to map the yellow rust lesions on wheat leaves with different damage levels. The results showed that the yellow rust lesions on the leaves could be identified accurately. Overall, the combination of spectral features and TFs of hyperspectral images significantly improved the identification accuracy of wheat yellow rust.

Yellow rust, a widely known destructive wheat disease, affects wheat quality and causes large economic losses in wheat production. Hyperspectral remote sensing has shown potential for the detection of plant disease. This study aimed to analyze the spectral reflectance of the wheat canopy in the range of 350–1000 nm and to develop optimal spectral indices to detect yellow rust disease in wheat at different growth stages. The sensitive wavebands of healthy and infected wheat were located in the range 460–720 nm in the early-mid growth stage (from booting to anthesis), and in the ranges 568–709 nm and 725–1000 nm in the mid-late growth stage (from filling to milky ripeness), respectively. All possible three-band combinations over these sensitive wavebands were calculated as the forms of PRI (Photochemical Reflectance Index) and ARI (Anthocyanin Reflectance Index) at different growth stages and assessed to determine whether they could be used for estimating the severity of yellow rust disease. The optimal spectral index for estimating wheat infected by yellow rust disease was PRI (570, 525, 705) during the early-mid growth stage with R² of 0.669, and ARI (860, 790, 750) during the mid-late growth stage with R² of 0.888. Comparison of the proposed spectral indices with previously reported vegetation indices were able to satisfactorily discriminate wheat yellow rust. The classification accuracy for PRI (570, 525, 705) was 80.6% and the kappa coefficient was 0.61 in early-mid growth stage, and the classification accuracy for ARI (860, 790, 750) was 91.9% and the kappa coefficient was 0.75 in mid-late growth stage. The classification accuracy of the two indices reached 84.1% and 93.2% in the early-mid and mid-late growth stages in the validated dataset, respectively. We conclude that the three-band spectral indices PRI (570, 525, 705) and ARI (860, 790, 750) are optimal for monitoring yellow rust infection in these two growth stages, respectively. Our method is expected to provide a technical basis for wheat disease detection and prevention in the early-mid growth stage, and the estimation of yield losses in the mid-late growth stage.

The monitoring of winter wheat Fusarium head blight via rapid and non-destructive measures is important for agricultural production and disease control. Images of unmanned aerial vehicles (UAVs) are particularly suitable for the monitoring of wheat diseases because they feature high spatial resolution and flexible acquisition time. This study evaluated the potential to monitor Fusarium head blight via UAV hyperspectral imagery. The field site investigated by this study is located in Lujiang County, Anhui Province, China. The hyperspectral UAV images were acquired on 3 and 8 May 2019, when wheat was at the grain filling stage. Several features, including original spectral bands, vegetation indexes, and texture features, were extracted from these hyperspectral images. Based on these extracted features, univariate Fusarium monitoring models were developed, and backward feature selection was applied to filter these features. The backpropagation (BP) neural network was improved by integrating a simulated annealing algorithm in the experiment. A multivariate Fusarium head blight monitoring model was developed using the improved BP neural network. The results showed that bands in the red region provide important information for discriminating between wheat canopies that are either slightly or severely Fusarium-head-blight-infected. The modified chlorophyll absorption reflectance index performed best among all features, with an area under the curve and standard deviation of 1.0 and 0.0, respectively. Five commonly used methods were compared with this improved BP neural network. The results showed that the developed Fusarium head blight monitoring model achieved the highest overall accuracy of 98%. In addition, the difference between the producer accuracy and user accuracy of the improved BP neural network was smallest among all models, indicating that this model achieved better stability. These results demonstrate that hyperspectral images of UAVs can be used to monitor Fusarium head blight in winter wheat.

Appropriate modeling methods and feature selection algorithms must be selected to improve the accuracy of early and mid-term remote sensing detection of wheat stripe rust. In the current study, we explored the effectiveness of the random forest (RF) algorithm combined with the extreme gradient boosting (XGboost) method for early and mid-term wheat stripe rust detection based on the vegetation indices extracted from canopy level hyperspectral measurements. Initially, 21 vegetation indices that were related to the early and mid-term winter wheat stripe rust were calculated on the basis of canopy level hyperspectral reflectance. Subsequently, the optimal vegetation index combination for disease detection was determined using correlation analysis (CA) combined with RF algorithms. Then, the disease severity detection model of early and mid-term winter wheat stripe rust was constructed using XGBoost method based on the optimal vegetation index combination. For the evaluation and comparison of the initial results, three commonly used classification methods, namely, RF, backpropagation neural network (BPNN), and support vector machine (SVM), were utilized. The vegetation index combinations determined by the single CA algorithm were also used to construct detection models. Compared with the detection models based on the vegetation index combination obtained using the single CA algorithm, the overall accuracy of the four detection models based on the optimal vegetation index combination based on CA combined with RF algorithms increased by 16.1% (XGBoost), 9.7% (RF), 8.1% (SVM), and 8.1% (BPNN). Among the eight models, the XGBoost detection model based on the optimal vegetation index combination using CA combined with RF algorithms, CA-RF-XGBoost, achieved the highest overall accuracy of 87.1% and the highest kappa coefficient of 0.798. Our results indicate that the RF combined with XGBoost can improve the detection accuracy of early and mid-term winter wheat stripe rust effectively at canopy scale.