Abstract

Hyperspectral imaging was explored to detect Sclerotinia stem rot (SSR) on oilseed rape leaves with chemometric methods, and the influences of variable selection, machine learning, and calibration transfer methods on detection performances were evaluated. Three different sample sets containing healthy and infected oilseed rape leaves were acquired under different imaging acquisition parameters. Four discriminant models were built using full spectra, including partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM), soft independent modeling of class analogies (SIMCA), and k-nearest neighbors (KNN). PLS-DA and SVM models were also built with the optimal wavelengths selected by principal component analysis (PCA) loadings, second derivative spectra, competitive adaptive reweighted sampling (CARS), and successive projections algorithm (SPA). The optimal wavelengths selected for each sample set by different methods were different; however, the optimal wavelengths selected by PCA loadings and second derivative spectra showed similarity between different sample sets. Direct standardization (DS) was successfully applied to reduce spectral differences among different sample sets. Overall, the results demonstrated that using hyperspectral imaging with chemometrics for plant disease detection can be efficient and will also help in the selection of optimal variable selection, machine learning, and calibration transfer methods for fast and accurate plant disease detection.

Highlights

  • Oilseed rape is one of the major oil crops in the world, and diseases represent severe threats to oilseed rape plants

  • When four or five expanded leaves were on each plant, 90 oilseed plants were transplanted into flower-pots in the greenhouse

  • When the plants adjusted to the environment, mycelial pellets were placed on the plant leaves and each leaf received two mycelial pellets symmetrically placed along the main vein

Read more

Summary

Introduction

Oilseed rape is one of the major oil crops in the world, and diseases represent severe threats to oilseed rape plants. Sclerotinia sclerotiorum is the major disease of oilseed rape in all major growing regions, including China. Sclerotinia sclerotiorum can affect the leaf, stem, pod, and flowers of oilseed rape plants. Sclerotinia sclerotiorum can cause 0–20% of yield loss every year and the severe situation of Sclerotinia sclerotiorum infection in China can reach 80% of yield loss [1]. The timely and accurate detection of Sclerotinia sclerotiorum is urgent in precision oilseed rape disease management.

Objectives
Methods
Results
Full Text
Published version (Free)

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 call