Abstract
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.
Highlights
Wheat stripe rust is an airborne epidemic disease that causes high yield loss and extensive damage in wheat production globally
The correlation analysis (CA)-random forest (RF)-XGBoost model based on canopy hyperspectral data was applied to detect the severity of winter wheat stripe rust in the early and mid-term
The model was combined with the XGBoost algorithm to construct a detection model through the feature selection of vegetation indices by the CA-RF feature selection algorithm
Summary
Wheat stripe rust is an airborne epidemic disease that causes high yield loss and extensive damage in wheat production globally. Wheat stripe rust will cause the wheat yield to decrease by more than 40% [1,2]. It is a low-temperature, high-moisture, high-light fungal disease that produces fungal spores on leaves infected by this pathogen and forms narrow yellow stripes parallel to the leaf veins, with dashed stripes [3]. Hyperspectral remote sensing data can provide detailed spectral information of landforms to invert the degree of crop stress by diseases quantitatively [5,6,7]. Some scholars have used wheat hyperspectral remote sensing data to detect the stress degree of winter wheat affected by stripe rust quantitatively [8,9]. Huang et al [10] stated that the photochemical reflectance index (PRI) could detect the occurrence of winter wheat rust disease on the scale of the crown layer and field effectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
