Byline: Graeme Roberts An automotive interiors specialist is to collaborate with a materials supplier to replace the use of petrochemicals with natural polymers. Yanfeng Automotive Interiors (YFAI) and Prisma Renewable [...]
Qi Liu, Haiguang Wang, Pei Cheng, Liu Ruan, Xiaolong Li, Rui Wang, Feng Qin, Zhanhong Ma, and Hui Wang
Subjects
0106 biological sciences, Leaves, Support Vector Machine, Light, lcsh:Medicine, Plant Science, 01 natural sciences, Rust, Remote Sensing, Machine Learning, Partial least squares regression, Statistics, lcsh:Science, Triticum, Multidisciplinary, biology, Plant Anatomy, Physics, Electromagnetic Radiation, Plant Fungal Pathogens, food and beverages, Hyperspectral imaging, Agriculture, 04 agricultural and veterinary sciences, Plants, Data Acquisition, Spectrophotometry, Wheat, Physical Sciences, Engineering and Technology, Research Article, Paper, Computer and Information Sciences, China, Mean squared error, Plant Pathogens, Crops, Wheat Stripe Rust, Cross-validation, Wheat leaf rust, Artificial Intelligence, Support Vector Machines, Grasses, Least-Squares Analysis, Plant Diseases, Basidiomycota, lcsh:R, Organisms, Biology and Life Sciences, Plant Pathology, biology.organism_classification, Plant Leaves, Support vector machine, Agronomy, Remote Sensing Technology, 040103 agronomy & agriculture, Cognitive Science, 0401 agriculture, forestry, and fisheries, lcsh:Q, Data pre-processing, Crop Science, Cereal Crops, Neuroscience, 010606 plant biology & botany
Abstract
It is important to implement detection and assessment of plant diseases based on remotely sensed data for disease monitoring and control. Hyperspectral data of healthy leaves, leaves in incubation period and leaves in diseased period of wheat stripe rust and wheat leaf rust were collected under in-field conditions using a black-paper-based measuring method developed in this study. After data preprocessing, the models to identify the diseases were built using distinguished partial least squares (DPLS) and support vector machine (SVM), and the disease severity inversion models of stripe rust and the disease severity inversion models of leaf rust were built using quantitative partial least squares (QPLS) and support vector regression (SVR). All the models were validated by using leave-one-out cross validation and external validation. The diseases could be discriminated using both distinguished partial least squares and support vector machine with the accuracies of more than 99%. For each wheat rust, disease severity levels were accurately retrieved using both the optimal QPLS models and the optimal SVR models with the coefficients of determination (R2) of more than 0.90 and the root mean square errors (RMSE) of less than 0.15. The results demonstrated that identification and severity evaluation of stripe rust and leaf rust at the leaf level could be implemented based on the hyperspectral data acquired using the developed method. A scientific basis was provided for implementing disease monitoring by using aerial and space remote sensing technologies.